maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/lib/Target/SystemZ/SystemZInstrInfo.td

1510 lines
67 KiB
TableGen
Raw Normal View History

[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
//===-- SystemZInstrInfo.td - General SystemZ instructions ----*- tblgen-*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//===----------------------------------------------------------------------===//
// Stack allocation
//===----------------------------------------------------------------------===//
def ADJCALLSTACKDOWN : Pseudo<(outs), (ins i64imm:$amt),
[(callseq_start timm:$amt)]>;
def ADJCALLSTACKUP : Pseudo<(outs), (ins i64imm:$amt1, i64imm:$amt2),
[(callseq_end timm:$amt1, timm:$amt2)]>;
Replace neverHasSideEffects=1 with hasSideEffects=0 in all .td files. llvm-svn: 222801
2014-11-26 08:46:26 +08:00
let hasSideEffects = 0 in {
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Takes as input the value of the stack pointer after a dynamic allocation
// has been made. Sets the output to the address of the dynamically-
// allocated area itself, skipping the outgoing arguments.
//
// This expands to an LA or LAY instruction. We restrict the offset
// to the range of LA and keep the LAY range in reserve for when
// the size of the outgoing arguments is added.
def ADJDYNALLOC : Pseudo<(outs GR64:$dst), (ins dynalloc12only:$src),
[(set GR64:$dst, dynalloc12only:$src)]>;
}
//===----------------------------------------------------------------------===//
// Control flow instructions
//===----------------------------------------------------------------------===//
[SystemZ] Define the return instruction as a pseudo alias of BR This is the first of a few patches to reduce the dupliation of encoding information. The return instruction is a normal BR in which one of the registers is fixed. llvm-svn: 191364
2013-09-25 18:20:08 +08:00
// A return instruction (br %r14).
let isReturn = 1, isTerminator = 1, isBarrier = 1, hasCtrlDep = 1 in
def Return : Alias<2, (outs), (ins), [(z_retflag)]>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Unconditional branches. R1 is the condition-code mask (all 1s).
let isBranch = 1, isTerminator = 1, isBarrier = 1, R1 = 15 in {
let isIndirectBranch = 1 in
[SystemZ] Match operands to fields by name rather than by order The SystemZ port currently relies on the order of the instruction operands matching the order of the instruction field lists. This isn't desirable for disassembly, where the two are matched only by name. E.g. the R1 and R2 fields of an RR instruction should have corresponding R1 and R2 operands. The main complication is that addresses are compound operands, and as far as I know there is no mechanism to allow individual suboperands to be selected by name in "let Inst{...} = ..." assignments. Luckily it doesn't really matter though. The SystemZ instruction encoding groups all address fields together in a predictable order, so it's just as valid to see the entire compound address operand as a single field. That's the approach taken in this patch. Matching by name in turn means that the operands to COPY SIGN and CONVERT TO FIXED instructions can be given in natural order. (It was easier to do this at the same time as the rename, since otherwise the intermediate step was too confusing.) No functional change intended. llvm-svn: 181769
2013-05-14 17:28:21 +08:00
def BR : InstRR<0x07, (outs), (ins ADDR64:$R2),
"br\t$R2", [(brind ADDR64:$R2)]>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
[SystemZ] Add long branch pass Before this change, the SystemZ backend would use BRCL for all branches and only consider shortening them to BRC when generating an object file. E.g. a branch on equal would use the JGE alias of BRCL in assembly output, but might be shortened to the JE alias of BRC in ELF output. This was a useful first step, but it had two problems: (1) The z assembler isn't traditionally supposed to perform branch shortening or branch relaxation. We followed this rule by not relaxing branches in assembler input, but that meant that generating assembly code and then assembling it would not produce the same result as going directly to object code; the former would give long branches everywhere, whereas the latter would use short branches where possible. (2) Other useful branches, like COMPARE AND BRANCH, do not have long forms. We would need to do something else before supporting them. (Although COMPARE AND BRANCH does not change the condition codes, the plan is to model COMPARE AND BRANCH as a CC-clobbering instruction during codegen, so that we can safely lower it to a separate compare and long branch where necessary. This is not a valid transformation for the assembler proper to make.) This patch therefore moves branch relaxation to a pre-emit pass. For now, calls are still shortened from BRASL to BRAS by the assembler, although this too is not really the traditional behaviour. The first test takes about 1.5s to run, and there are likely to be more tests in this vein once further branch types are added. The feeling on IRC was that 1.5s is a bit much for a single test, so I've restricted it to SystemZ hosts for now. The patch exposes (and fixes) some typos in the main CodeGen/SystemZ tests. A later patch will remove the {{g}}s from that directory. llvm-svn: 182274
2013-05-20 22:23:08 +08:00
// An assembler extended mnemonic for BRC.
def J : InstRI<0xA74, (outs), (ins brtarget16:$I2), "j\t$I2",
[(br bb:$I2)]>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// An assembler extended mnemonic for BRCL. (The extension is "G"
// rather than "L" because "JL" is "Jump if Less".)
[SystemZ] Add long branch pass Before this change, the SystemZ backend would use BRCL for all branches and only consider shortening them to BRC when generating an object file. E.g. a branch on equal would use the JGE alias of BRCL in assembly output, but might be shortened to the JE alias of BRC in ELF output. This was a useful first step, but it had two problems: (1) The z assembler isn't traditionally supposed to perform branch shortening or branch relaxation. We followed this rule by not relaxing branches in assembler input, but that meant that generating assembly code and then assembling it would not produce the same result as going directly to object code; the former would give long branches everywhere, whereas the latter would use short branches where possible. (2) Other useful branches, like COMPARE AND BRANCH, do not have long forms. We would need to do something else before supporting them. (Although COMPARE AND BRANCH does not change the condition codes, the plan is to model COMPARE AND BRANCH as a CC-clobbering instruction during codegen, so that we can safely lower it to a separate compare and long branch where necessary. This is not a valid transformation for the assembler proper to make.) This patch therefore moves branch relaxation to a pre-emit pass. For now, calls are still shortened from BRASL to BRAS by the assembler, although this too is not really the traditional behaviour. The first test takes about 1.5s to run, and there are likely to be more tests in this vein once further branch types are added. The feeling on IRC was that 1.5s is a bit much for a single test, so I've restricted it to SystemZ hosts for now. The patch exposes (and fixes) some typos in the main CodeGen/SystemZ tests. A later patch will remove the {{g}}s from that directory. llvm-svn: 182274
2013-05-20 22:23:08 +08:00
def JG : InstRIL<0xC04, (outs), (ins brtarget32:$I2), "jg\t$I2", []>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
// Conditional branches. It's easier for LLVM to handle these branches
// in their raw BRC/BRCL form, with the 4-bit condition-code mask being
// the first operand. It seems friendlier to use mnemonic forms like
// JE and JLH when writing out the assembly though.
[SystemZ] Be more careful about inverting CC masks System z branches have a mask to select which of the 4 CC values should cause the branch to be taken. We can invert a branch by inverting the mask. However, not all instructions can produce all 4 CC values, so inverting the branch like this can lead to some oddities. For example, integer comparisons only produce a CC of 0 (equal), 1 (less) or 2 (greater). If an integer EQ is reversed to NE before instruction selection, the branch will test for 1 or 2. If instead the branch is reversed after instruction selection (by inverting the mask), it will test for 1, 2 or 3. Both are correct, but the second isn't really canonical. This patch therefore keeps track of which CC values are possible and uses this when inverting a mask. Although this is mostly cosmestic, it fixes undefined behavior for the CIJNLH in branch-08.ll. Another fix would have been to mask out bit 0 when generating the fused compare and branch, but the point of this patch is that we shouldn't need to do that in the first place. The patch also makes it easier to reuse CC results from other instructions. llvm-svn: 187495
2013-07-31 20:30:20 +08:00
let isBranch = 1, isTerminator = 1, Uses = [CC] in {
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
let isCodeGenOnly = 1, CCMaskFirst = 1 in {
[SystemZ] Be more careful about inverting CC masks System z branches have a mask to select which of the 4 CC values should cause the branch to be taken. We can invert a branch by inverting the mask. However, not all instructions can produce all 4 CC values, so inverting the branch like this can lead to some oddities. For example, integer comparisons only produce a CC of 0 (equal), 1 (less) or 2 (greater). If an integer EQ is reversed to NE before instruction selection, the branch will test for 1 or 2. If instead the branch is reversed after instruction selection (by inverting the mask), it will test for 1, 2 or 3. Both are correct, but the second isn't really canonical. This patch therefore keeps track of which CC values are possible and uses this when inverting a mask. Although this is mostly cosmestic, it fixes undefined behavior for the CIJNLH in branch-08.ll. Another fix would have been to mask out bit 0 when generating the fused compare and branch, but the point of this patch is that we shouldn't need to do that in the first place. The patch also makes it easier to reuse CC results from other instructions. llvm-svn: 187495
2013-07-31 20:30:20 +08:00
def BRC : InstRI<0xA74, (outs), (ins cond4:$valid, cond4:$R1,
brtarget16:$I2), "j$R1\t$I2",
[(z_br_ccmask cond4:$valid, cond4:$R1, bb:$I2)]>;
def BRCL : InstRIL<0xC04, (outs), (ins cond4:$valid, cond4:$R1,
brtarget32:$I2), "jg$R1\t$I2", []>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
[SystemZ] Avoid using i8 constants for immediate fields Immediate fields that have no natural MVT type tended to use i8 if the field was small enough. This was a bit confusing since i8 isn't a legal type for the target. Fields for short immediates in a 32-bit or 64-bit operation use i32 or i64 instead, so it would be better to do the same for all fields. No behavioral change intended. llvm-svn: 212702
2014-07-10 18:52:51 +08:00
def AsmBRC : InstRI<0xA74, (outs), (ins imm32zx4:$R1, brtarget16:$I2),
[SystemZ] Be more careful about inverting CC masks System z branches have a mask to select which of the 4 CC values should cause the branch to be taken. We can invert a branch by inverting the mask. However, not all instructions can produce all 4 CC values, so inverting the branch like this can lead to some oddities. For example, integer comparisons only produce a CC of 0 (equal), 1 (less) or 2 (greater). If an integer EQ is reversed to NE before instruction selection, the branch will test for 1 or 2. If instead the branch is reversed after instruction selection (by inverting the mask), it will test for 1, 2 or 3. Both are correct, but the second isn't really canonical. This patch therefore keeps track of which CC values are possible and uses this when inverting a mask. Although this is mostly cosmestic, it fixes undefined behavior for the CIJNLH in branch-08.ll. Another fix would have been to mask out bit 0 when generating the fused compare and branch, but the point of this patch is that we shouldn't need to do that in the first place. The patch also makes it easier to reuse CC results from other instructions. llvm-svn: 187495
2013-07-31 20:30:20 +08:00
"brc\t$R1, $I2", []>;
[SystemZ] Avoid using i8 constants for immediate fields Immediate fields that have no natural MVT type tended to use i8 if the field was small enough. This was a bit confusing since i8 isn't a legal type for the target. Fields for short immediates in a 32-bit or 64-bit operation use i32 or i64 instead, so it would be better to do the same for all fields. No behavioral change intended. llvm-svn: 212702
2014-07-10 18:52:51 +08:00
def AsmBRCL : InstRIL<0xC04, (outs), (ins imm32zx4:$R1, brtarget32:$I2),
[SystemZ] Be more careful about inverting CC masks System z branches have a mask to select which of the 4 CC values should cause the branch to be taken. We can invert a branch by inverting the mask. However, not all instructions can produce all 4 CC values, so inverting the branch like this can lead to some oddities. For example, integer comparisons only produce a CC of 0 (equal), 1 (less) or 2 (greater). If an integer EQ is reversed to NE before instruction selection, the branch will test for 1 or 2. If instead the branch is reversed after instruction selection (by inverting the mask), it will test for 1, 2 or 3. Both are correct, but the second isn't really canonical. This patch therefore keeps track of which CC values are possible and uses this when inverting a mask. Although this is mostly cosmestic, it fixes undefined behavior for the CIJNLH in branch-08.ll. Another fix would have been to mask out bit 0 when generating the fused compare and branch, but the point of this patch is that we shouldn't need to do that in the first place. The patch also makes it easier to reuse CC results from other instructions. llvm-svn: 187495
2013-07-31 20:30:20 +08:00
"brcl\t$R1, $I2", []>;
[SystemZ] Avoid using i8 constants for immediate fields Immediate fields that have no natural MVT type tended to use i8 if the field was small enough. This was a bit confusing since i8 isn't a legal type for the target. Fields for short immediates in a 32-bit or 64-bit operation use i32 or i64 instead, so it would be better to do the same for all fields. No behavioral change intended. llvm-svn: 212702
2014-07-10 18:52:51 +08:00
def AsmBCR : InstRR<0x07, (outs), (ins imm32zx4:$R1, GR64:$R2),
[SystemZ] Add the general form of BCR At the moment this is just the MC support. llvm-svn: 194585
2013-11-14 00:57:53 +08:00
"bcr\t$R1, $R2", []>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
[SystemZ] Register compare-and-branch support This patch adds support for the CRJ and CGRJ instructions. Support for the immediate forms will be a separate patch. The architecture has a large number of comparison instructions. I think it's generally better to concentrate on using the "best" comparison instruction first and foremost, then only use something like CRJ if CR really was the natual choice of comparison instruction. The patch therefore opportunistically converts separate CR and BRC instructions into a single CRJ while emitting instructions in ISelLowering. llvm-svn: 182764
2013-05-28 18:41:11 +08:00
// Fused compare-and-branch instructions. As for normal branches,
// we handle these instructions internally in their raw CRJ-like form,
// but use assembly macros like CRJE when writing them out.
//
// These instructions do not use or clobber the condition codes.
// We nevertheless pretend that they clobber CC, so that we can lower
// them to separate comparisons and BRCLs if the branch ends up being
// out of range.
multiclass CompareBranches<Operand ccmask, string pos1, string pos2> {
let isBranch = 1, isTerminator = 1, Defs = [CC] in {
def RJ : InstRIEb<0xEC76, (outs), (ins GR32:$R1, GR32:$R2, ccmask:$M3,
brtarget16:$RI4),
[SystemZ] Immediate compare-and-branch support This patch adds support for the CIJ and CGIJ instructions. llvm-svn: 182846
2013-05-29 19:58:52 +08:00
"crj"##pos1##"\t$R1, $R2, "##pos2##"$RI4", []>;
[SystemZ] Register compare-and-branch support This patch adds support for the CRJ and CGRJ instructions. Support for the immediate forms will be a separate patch. The architecture has a large number of comparison instructions. I think it's generally better to concentrate on using the "best" comparison instruction first and foremost, then only use something like CRJ if CR really was the natual choice of comparison instruction. The patch therefore opportunistically converts separate CR and BRC instructions into a single CRJ while emitting instructions in ISelLowering. llvm-svn: 182764
2013-05-28 18:41:11 +08:00
def GRJ : InstRIEb<0xEC64, (outs), (ins GR64:$R1, GR64:$R2, ccmask:$M3,
brtarget16:$RI4),
[SystemZ] Immediate compare-and-branch support This patch adds support for the CIJ and CGIJ instructions. llvm-svn: 182846
2013-05-29 19:58:52 +08:00
"cgrj"##pos1##"\t$R1, $R2, "##pos2##"$RI4", []>;
def IJ : InstRIEc<0xEC7E, (outs), (ins GR32:$R1, imm32sx8:$I2, ccmask:$M3,
brtarget16:$RI4),
"cij"##pos1##"\t$R1, $I2, "##pos2##"$RI4", []>;
def GIJ : InstRIEc<0xEC7C, (outs), (ins GR64:$R1, imm64sx8:$I2, ccmask:$M3,
brtarget16:$RI4),
"cgij"##pos1##"\t$R1, $I2, "##pos2##"$RI4", []>;
[SystemZ] Add unsigned compare-and-branch instructions For some reason I never got around to adding these at the same time as the signed versions. No idea why. I'm not sure whether this SystemZII::BranchC* stuff is useful, or whether it should just be replaced with an "is normal" flag. I'll leave that for later though. There are some boundary conditions that can be tweaked, such as preferring unsigned comparisons for equality with [128, 256), and "<= 255" over "< 256", but again I'll leave those for a separate patch. llvm-svn: 190930
2013-09-18 17:56:40 +08:00
def LRJ : InstRIEb<0xEC77, (outs), (ins GR32:$R1, GR32:$R2, ccmask:$M3,
brtarget16:$RI4),
"clrj"##pos1##"\t$R1, $R2, "##pos2##"$RI4", []>;
def LGRJ : InstRIEb<0xEC65, (outs), (ins GR64:$R1, GR64:$R2, ccmask:$M3,
brtarget16:$RI4),
"clgrj"##pos1##"\t$R1, $R2, "##pos2##"$RI4", []>;
def LIJ : InstRIEc<0xEC7F, (outs), (ins GR32:$R1, imm32zx8:$I2, ccmask:$M3,
brtarget16:$RI4),
"clij"##pos1##"\t$R1, $I2, "##pos2##"$RI4", []>;
def LGIJ : InstRIEc<0xEC7D, (outs), (ins GR64:$R1, imm64zx8:$I2, ccmask:$M3,
brtarget16:$RI4),
"clgij"##pos1##"\t$R1, $I2, "##pos2##"$RI4", []>;
[SystemZ] Register compare-and-branch support This patch adds support for the CRJ and CGRJ instructions. Support for the immediate forms will be a separate patch. The architecture has a large number of comparison instructions. I think it's generally better to concentrate on using the "best" comparison instruction first and foremost, then only use something like CRJ if CR really was the natual choice of comparison instruction. The patch therefore opportunistically converts separate CR and BRC instructions into a single CRJ while emitting instructions in ISelLowering. llvm-svn: 182764
2013-05-28 18:41:11 +08:00
}
}
let isCodeGenOnly = 1 in
defm C : CompareBranches<cond4, "$M3", "">;
[SystemZ] Avoid using i8 constants for immediate fields Immediate fields that have no natural MVT type tended to use i8 if the field was small enough. This was a bit confusing since i8 isn't a legal type for the target. Fields for short immediates in a 32-bit or 64-bit operation use i32 or i64 instead, so it would be better to do the same for all fields. No behavioral change intended. llvm-svn: 212702
2014-07-10 18:52:51 +08:00
defm AsmC : CompareBranches<imm32zx4, "", "$M3, ">;
[SystemZ] Register compare-and-branch support This patch adds support for the CRJ and CGRJ instructions. Support for the immediate forms will be a separate patch. The architecture has a large number of comparison instructions. I think it's generally better to concentrate on using the "best" comparison instruction first and foremost, then only use something like CRJ if CR really was the natual choice of comparison instruction. The patch therefore opportunistically converts separate CR and BRC instructions into a single CRJ while emitting instructions in ISelLowering. llvm-svn: 182764
2013-05-28 18:41:11 +08:00
// Define AsmParser mnemonics for each general condition-code mask
// (integer or floating-point)
multiclass CondExtendedMnemonic<bits<4> ccmask, string name> {
let R1 = ccmask in {
[SystemZ] Add STOC and STOCG These instructions are allowed to trap even if the condition is false, so for now they are only used for "*ptr = (cond ? x : *ptr)"-style constructs. llvm-svn: 187111
2013-07-25 16:57:02 +08:00
def J : InstRI<0xA74, (outs), (ins brtarget16:$I2),
"j"##name##"\t$I2", []>;
def JG : InstRIL<0xC04, (outs), (ins brtarget32:$I2),
[SystemZ] Immediate compare-and-branch support This patch adds support for the CIJ and CGIJ instructions. llvm-svn: 182846
2013-05-29 19:58:52 +08:00
"jg"##name##"\t$I2", []>;
[SystemZ] Add the general form of BCR At the moment this is just the MC support. llvm-svn: 194585
2013-11-14 00:57:53 +08:00
def BR : InstRR<0x07, (outs), (ins ADDR64:$R2), "b"##name##"r\t$R2", []>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
[SystemZ] Add LOCR and LOCGR llvm-svn: 187113
2013-07-25 17:11:15 +08:00
def LOCR : FixedCondUnaryRRF<"locr"##name, 0xB9F2, GR32, GR32, ccmask>;
def LOCGR : FixedCondUnaryRRF<"locgr"##name, 0xB9E2, GR64, GR64, ccmask>;
[SystemZ] Add LOC and LOCG As with the stores, these instructions can trap when the condition is false, so they are only used for things like (cond ? x : *ptr). llvm-svn: 187112
2013-07-25 17:04:52 +08:00
def LOC : FixedCondUnaryRSY<"loc"##name, 0xEBF2, GR32, ccmask, 4>;
def LOCG : FixedCondUnaryRSY<"locg"##name, 0xEBE2, GR64, ccmask, 8>;
[SystemZ] Add STOC and STOCG These instructions are allowed to trap even if the condition is false, so for now they are only used for "*ptr = (cond ? x : *ptr)"-style constructs. llvm-svn: 187111
2013-07-25 16:57:02 +08:00
def STOC : FixedCondStoreRSY<"stoc"##name, 0xEBF3, GR32, ccmask, 4>;
def STOCG : FixedCondStoreRSY<"stocg"##name, 0xEBE3, GR64, ccmask, 8>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
[SystemZ] Add STOC and STOCG These instructions are allowed to trap even if the condition is false, so for now they are only used for "*ptr = (cond ? x : *ptr)"-style constructs. llvm-svn: 187111
2013-07-25 16:57:02 +08:00
defm AsmO : CondExtendedMnemonic<1, "o">;
defm AsmH : CondExtendedMnemonic<2, "h">;
defm AsmNLE : CondExtendedMnemonic<3, "nle">;
defm AsmL : CondExtendedMnemonic<4, "l">;
defm AsmNHE : CondExtendedMnemonic<5, "nhe">;
defm AsmLH : CondExtendedMnemonic<6, "lh">;
defm AsmNE : CondExtendedMnemonic<7, "ne">;
defm AsmE : CondExtendedMnemonic<8, "e">;
defm AsmNLH : CondExtendedMnemonic<9, "nlh">;
defm AsmHE : CondExtendedMnemonic<10, "he">;
defm AsmNL : CondExtendedMnemonic<11, "nl">;
defm AsmLE : CondExtendedMnemonic<12, "le">;
defm AsmNH : CondExtendedMnemonic<13, "nh">;
defm AsmNO : CondExtendedMnemonic<14, "no">;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
[SystemZ] Register compare-and-branch support This patch adds support for the CRJ and CGRJ instructions. Support for the immediate forms will be a separate patch. The architecture has a large number of comparison instructions. I think it's generally better to concentrate on using the "best" comparison instruction first and foremost, then only use something like CRJ if CR really was the natual choice of comparison instruction. The patch therefore opportunistically converts separate CR and BRC instructions into a single CRJ while emitting instructions in ISelLowering. llvm-svn: 182764
2013-05-28 18:41:11 +08:00
// Define AsmParser mnemonics for each integer condition-code mask.
// This is like the list above, except that condition 3 is not possible
// and that the low bit of the mask is therefore always 0. This means
// that each condition has two names. Conditions "o" and "no" are not used.
//
// We don't make one of the two names an alias of the other because
// we need the custom parsing routines to select the correct register class.
multiclass IntCondExtendedMnemonicA<bits<4> ccmask, string name> {
let M3 = ccmask in {
def CR : InstRIEb<0xEC76, (outs), (ins GR32:$R1, GR32:$R2,
brtarget16:$RI4),
"crj"##name##"\t$R1, $R2, $RI4", []>;
def CGR : InstRIEb<0xEC64, (outs), (ins GR64:$R1, GR64:$R2,
brtarget16:$RI4),
"cgrj"##name##"\t$R1, $R2, $RI4", []>;
[SystemZ] Immediate compare-and-branch support This patch adds support for the CIJ and CGIJ instructions. llvm-svn: 182846
2013-05-29 19:58:52 +08:00
def CI : InstRIEc<0xEC7E, (outs), (ins GR32:$R1, imm32sx8:$I2,
brtarget16:$RI4),
"cij"##name##"\t$R1, $I2, $RI4", []>;
def CGI : InstRIEc<0xEC7C, (outs), (ins GR64:$R1, imm64sx8:$I2,
brtarget16:$RI4),
"cgij"##name##"\t$R1, $I2, $RI4", []>;
[SystemZ] Add unsigned compare-and-branch instructions For some reason I never got around to adding these at the same time as the signed versions. No idea why. I'm not sure whether this SystemZII::BranchC* stuff is useful, or whether it should just be replaced with an "is normal" flag. I'll leave that for later though. There are some boundary conditions that can be tweaked, such as preferring unsigned comparisons for equality with [128, 256), and "<= 255" over "< 256", but again I'll leave those for a separate patch. llvm-svn: 190930
2013-09-18 17:56:40 +08:00
def CLR : InstRIEb<0xEC77, (outs), (ins GR32:$R1, GR32:$R2,
brtarget16:$RI4),
"clrj"##name##"\t$R1, $R2, $RI4", []>;
def CLGR : InstRIEb<0xEC65, (outs), (ins GR64:$R1, GR64:$R2,
brtarget16:$RI4),
"clgrj"##name##"\t$R1, $R2, $RI4", []>;
def CLI : InstRIEc<0xEC7F, (outs), (ins GR32:$R1, imm32zx8:$I2,
brtarget16:$RI4),
"clij"##name##"\t$R1, $I2, $RI4", []>;
def CLGI : InstRIEc<0xEC7D, (outs), (ins GR64:$R1, imm64zx8:$I2,
brtarget16:$RI4),
"clgij"##name##"\t$R1, $I2, $RI4", []>;
[SystemZ] Register compare-and-branch support This patch adds support for the CRJ and CGRJ instructions. Support for the immediate forms will be a separate patch. The architecture has a large number of comparison instructions. I think it's generally better to concentrate on using the "best" comparison instruction first and foremost, then only use something like CRJ if CR really was the natual choice of comparison instruction. The patch therefore opportunistically converts separate CR and BRC instructions into a single CRJ while emitting instructions in ISelLowering. llvm-svn: 182764
2013-05-28 18:41:11 +08:00
}
}
multiclass IntCondExtendedMnemonic<bits<4> ccmask, string name1, string name2>
: IntCondExtendedMnemonicA<ccmask, name1> {
let isAsmParserOnly = 1 in
defm Alt : IntCondExtendedMnemonicA<ccmask, name2>;
}
defm AsmJH : IntCondExtendedMnemonic<2, "h", "nle">;
defm AsmJL : IntCondExtendedMnemonic<4, "l", "nhe">;
defm AsmJLH : IntCondExtendedMnemonic<6, "lh", "ne">;
defm AsmJE : IntCondExtendedMnemonic<8, "e", "nlh">;
defm AsmJHE : IntCondExtendedMnemonic<10, "he", "nl">;
defm AsmJLE : IntCondExtendedMnemonic<12, "le", "nh">;
[SystemZ] Add definitions for BRCT and BRCTG llvm-svn: 187721
2013-08-05 19:07:38 +08:00
// Decrement a register and branch if it is nonzero. These don't clobber CC,
// but we might need to split long branches into sequences that do.
let Defs = [CC] in {
def BRCT : BranchUnaryRI<"brct", 0xA76, GR32>;
def BRCTG : BranchUnaryRI<"brctg", 0xA77, GR64>;
}
[SystemZ] Add conditional store patterns Add pseudo conditional store instructions, so that we use: branch foo: store foo: instead of: load branch foo: move foo: store z196 has real 32-bit and 64-bit conditional stores, but we don't use any z196 instructions yet. llvm-svn: 185065
2013-06-27 17:27:40 +08:00
//===----------------------------------------------------------------------===//
// Select instructions
//===----------------------------------------------------------------------===//
[SystemZ] Allow selects with a high-word destination llvm-svn: 191751
2013-10-01 21:10:16 +08:00
def Select32Mux : SelectWrapper<GRX32>, Requires<[FeatureHighWord]>;
def Select32 : SelectWrapper<GR32>;
def Select64 : SelectWrapper<GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
[SystemZ] Extend pseudo conditional 8- and 16-bit stores to high words As the comment says, we always want to use STOC for 32-bit stores. llvm-svn: 191767
2013-10-01 22:33:55 +08:00
// We don't define 32-bit Mux stores because the low-only STOC should
// always be used if possible.
defm CondStore8Mux : CondStores<GRX32, nonvolatile_truncstorei8,
nonvolatile_anyextloadi8, bdxaddr20only>,
Requires<[FeatureHighWord]>;
defm CondStore16Mux : CondStores<GRX32, nonvolatile_truncstorei16,
nonvolatile_anyextloadi16, bdxaddr20only>,
Requires<[FeatureHighWord]>;
defm CondStore8 : CondStores<GR32, nonvolatile_truncstorei8,
nonvolatile_anyextloadi8, bdxaddr20only>;
defm CondStore16 : CondStores<GR32, nonvolatile_truncstorei16,
nonvolatile_anyextloadi16, bdxaddr20only>;
defm CondStore32 : CondStores<GR32, nonvolatile_store,
nonvolatile_load, bdxaddr20only>;
[SystemZ] Use subregs for 64-bit truncating stores Another patch to reduce the duplication of encoding information. Rather than define separate patterns for truncating 64-bit stores, use the 32-bit stores with a subreg. No behavioral changed intended. llvm-svn: 191365
2013-09-25 18:29:47 +08:00
defm : CondStores64<CondStore8, CondStore8Inv, nonvolatile_truncstorei8,
nonvolatile_anyextloadi8, bdxaddr20only>;
defm : CondStores64<CondStore16, CondStore16Inv, nonvolatile_truncstorei16,
nonvolatile_anyextloadi16, bdxaddr20only>;
defm : CondStores64<CondStore32, CondStore32Inv, nonvolatile_truncstorei32,
nonvolatile_anyextloadi32, bdxaddr20only>;
[SystemZ] Add conditional store patterns Add pseudo conditional store instructions, so that we use: branch foo: store foo: instead of: load branch foo: move foo: store z196 has real 32-bit and 64-bit conditional stores, but we don't use any z196 instructions yet. llvm-svn: 185065
2013-06-27 17:27:40 +08:00
defm CondStore64 : CondStores<GR64, nonvolatile_store,
nonvolatile_load, bdxaddr20only>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
//===----------------------------------------------------------------------===//
// Call instructions
//===----------------------------------------------------------------------===//
[SystemZ] Use SystemZCallingConv.td to define callee-saved registers Just a clean-up. No behavioral change intended. llvm-svn: 212711
2014-07-10 19:44:37 +08:00
let isCall = 1, Defs = [R14D, CC] in {
[SystemZ] Define the call instructions as pseudo aliases. Similar to r191364, but for calls. This patch also removes the shortening of BRASL to BRAS within a TU. Doing that was a bit controversial internally, since there's a strong expectation with the z assembler that WYWIWYG. llvm-svn: 191366
2013-09-25 18:37:17 +08:00
def CallBRASL : Alias<6, (outs), (ins pcrel32:$I2, variable_ops),
[(z_call pcrel32:$I2)]>;
def CallBASR : Alias<2, (outs), (ins ADDR64:$R2, variable_ops),
[(z_call ADDR64:$R2)]>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
[SystemZ] Add support for sibling calls This first cut is pretty conservative. The final argument register (R6) is call-saved, so we would need to make sure that the R6 argument to a sibling call is the same as the R6 argument to the calling function, which seems worth keeping as a separate patch. Saying that integer truncations are free means that we no longer use the extending instructions LGF and LLGF for spills in int-conv-09.ll and int-conv-10.ll. Instead we treat the registers as 64 bits wide and truncate them to 32-bits where necessary. I think it's unlikely we'd use LGF and LLGF for spills in other situations for the same reason, so I'm removing the tests rather than replacing them. The associated code is generic and applies to many more instructions than just LGF and LLGF, so there is no corresponding code removal. llvm-svn: 188669
2013-08-19 20:42:31 +08:00
// Sibling calls. Indirect sibling calls must be via R1, since R2 upwards
// are argument registers and since branching to R0 is a no-op.
[SystemZ] Define the call instructions as pseudo aliases. Similar to r191364, but for calls. This patch also removes the shortening of BRASL to BRAS within a TU. Doing that was a bit controversial internally, since there's a strong expectation with the z assembler that WYWIWYG. llvm-svn: 191366
2013-09-25 18:37:17 +08:00
let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1 in {
def CallJG : Alias<6, (outs), (ins pcrel32:$I2),
[(z_sibcall pcrel32:$I2)]>;
let Uses = [R1D] in
def CallBR : Alias<2, (outs), (ins), [(z_sibcall R1D)]>;
[SystemZ] Add support for sibling calls This first cut is pretty conservative. The final argument register (R6) is call-saved, so we would need to make sure that the R6 argument to a sibling call is the same as the R6 argument to the calling function, which seems worth keeping as a separate patch. Saying that integer truncations are free means that we no longer use the extending instructions LGF and LLGF for spills in int-conv-09.ll and int-conv-10.ll. Instead we treat the registers as 64 bits wide and truncate them to 32-bits where necessary. I think it's unlikely we'd use LGF and LLGF for spills in other situations for the same reason, so I'm removing the tests rather than replacing them. The associated code is generic and applies to many more instructions than just LGF and LLGF, so there is no corresponding code removal. llvm-svn: 188669
2013-08-19 20:42:31 +08:00
}
[SystemZ] Support all TLS access models - CodeGen part The current SystemZ back-end only supports the local-exec TLS access model. This patch adds all required CodeGen support for the other TLS models, which means in particular: - Expand initial-exec TLS accesses by loading TLS offsets from the GOT using @indntpoff relocations. - Expand general-dynamic and local-dynamic accesses by generating the appropriate calls to __tls_get_offset. Note that this routine has a non-standard ABI and requires loading the GOT pointer into %r12, so the patch also adds support for the GLOBAL_OFFSET_TABLE ISD node. - Add a new platform-specific optimization pass to remove redundant __tls_get_offset calls in the local-dynamic model (modeled after the corresponding X86 pass). - Add test cases verifying all access models and optimizations. llvm-svn: 229654
2015-02-18 17:13:27 +08:00
// TLS calls. These will be lowered into a call to __tls_get_offset,
// with an extra relocation specifying the TLS symbol.
let isCall = 1, Defs = [R14D, CC] in {
def TLS_GDCALL : Alias<6, (outs), (ins tlssym:$I2, variable_ops),
[(z_tls_gdcall tglobaltlsaddr:$I2)]>;
def TLS_LDCALL : Alias<6, (outs), (ins tlssym:$I2, variable_ops),
[(z_tls_ldcall tglobaltlsaddr:$I2)]>;
}
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Define the general form of the call instructions for the asm parser.
// These instructions don't hard-code %r14 as the return address register.
[SystemZ] Support all TLS access models - MC part The current SystemZ back-end only supports the local-exec TLS access model. This patch adds all required MC support for the other TLS models, which means in particular: - Support additional relocation types for Initial-exec model: R_390_TLS_IEENT Local-dynamic-model: R_390_TLS_LDO32, R_390_TLS_LDO64, R_390_TLS_LDM32, R_390_TLS_LDM64, R_390_TLS_LDCALL General-dynamic model: R_390_TLS_GD32, R_390_TLS_GD64, R_390_TLS_GDCALL - Support assembler syntax to generate additional relocations for use with __tls_get_offset calls: :tls_gdcall: :tls_ldcall: The patch also adds a new test to verify fixups and relocations, and removes the (already unused) FK_390_PLT16DBL/FK_390_PLT32DBL fixup kinds. llvm-svn: 229652
2015-02-18 17:11:36 +08:00
// Allow an optional TLS marker symbol to generate TLS call relocations.
def BRAS : InstRI<0xA75, (outs), (ins GR64:$R1, brtarget16tls:$I2),
[SystemZ] Define the call instructions as pseudo aliases. Similar to r191364, but for calls. This patch also removes the shortening of BRASL to BRAS within a TU. Doing that was a bit controversial internally, since there's a strong expectation with the z assembler that WYWIWYG. llvm-svn: 191366
2013-09-25 18:37:17 +08:00
"bras\t$R1, $I2", []>;
[SystemZ] Support all TLS access models - MC part The current SystemZ back-end only supports the local-exec TLS access model. This patch adds all required MC support for the other TLS models, which means in particular: - Support additional relocation types for Initial-exec model: R_390_TLS_IEENT Local-dynamic-model: R_390_TLS_LDO32, R_390_TLS_LDO64, R_390_TLS_LDM32, R_390_TLS_LDM64, R_390_TLS_LDCALL General-dynamic model: R_390_TLS_GD32, R_390_TLS_GD64, R_390_TLS_GDCALL - Support assembler syntax to generate additional relocations for use with __tls_get_offset calls: :tls_gdcall: :tls_ldcall: The patch also adds a new test to verify fixups and relocations, and removes the (already unused) FK_390_PLT16DBL/FK_390_PLT32DBL fixup kinds. llvm-svn: 229652
2015-02-18 17:11:36 +08:00
def BRASL : InstRIL<0xC05, (outs), (ins GR64:$R1, brtarget32tls:$I2),
[SystemZ] Define the call instructions as pseudo aliases. Similar to r191364, but for calls. This patch also removes the shortening of BRASL to BRAS within a TU. Doing that was a bit controversial internally, since there's a strong expectation with the z assembler that WYWIWYG. llvm-svn: 191366
2013-09-25 18:37:17 +08:00
"brasl\t$R1, $I2", []>;
def BASR : InstRR<0x0D, (outs), (ins GR64:$R1, ADDR64:$R2),
"basr\t$R1, $R2", []>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
//===----------------------------------------------------------------------===//
// Move instructions
//===----------------------------------------------------------------------===//
// Register moves.
Replace neverHasSideEffects=1 with hasSideEffects=0 in all .td files. llvm-svn: 222801
2014-11-26 08:46:26 +08:00
let hasSideEffects = 0 in {
[SystemZ] Use upper words of GR64s for codegen This just adds the basics necessary for allocating the upper words to virtual registers (move, load and store). The move support is parameterised in a way that makes it easy to handle zero extensions, but the associated zero-extend patterns are added by a later patch. The easiest way of testing this seemed to be add a new "h" register constraint for high words. I don't expect the constraint to be useful in real inline asms, but it should work, so I didn't try to hide it behind an option. llvm-svn: 191739
2013-10-01 19:26:28 +08:00
// Expands to LR, RISBHG or RISBLG, depending on the choice of registers.
def LRMux : UnaryRRPseudo<"l", null_frag, GRX32, GRX32>,
Requires<[FeatureHighWord]>;
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def LR : UnaryRR <"l", 0x18, null_frag, GR32, GR32>;
def LGR : UnaryRRE<"lg", 0xB904, null_frag, GR64, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
[SystemZ] Optimize floating-point comparisons with zero This follows the same lines as the integer code. In the end it seemed easier to have a second 4-bit mask in TSFlags to specify the compare-like CC values. That eats one more TSFlags bit than adding a CCHasUnordered would have done, but it feels more concise. llvm-svn: 187883
2013-08-07 19:10:06 +08:00
let Defs = [CC], CCValues = 0xE, CompareZeroCCMask = 0xE in {
[SystemZ] Add LOAD AND TEST instructions Just the definitions and MC support. The next patch uses them for codegen. llvm-svn: 187719
2013-08-05 19:00:53 +08:00
def LTR : UnaryRR <"lt", 0x12, null_frag, GR32, GR32>;
def LTGR : UnaryRRE<"ltg", 0xB902, null_frag, GR64, GR64>;
}
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
[SystemZ] Add LOCR and LOCGR llvm-svn: 187113
2013-07-25 17:11:15 +08:00
// Move on condition.
let isCodeGenOnly = 1, Uses = [CC] in {
def LOCR : CondUnaryRRF<"loc", 0xB9F2, GR32, GR32>;
def LOCGR : CondUnaryRRF<"locg", 0xB9E2, GR64, GR64>;
}
let Uses = [CC] in {
def AsmLOCR : AsmCondUnaryRRF<"loc", 0xB9F2, GR32, GR32>;
def AsmLOCGR : AsmCondUnaryRRF<"locg", 0xB9E2, GR64, GR64>;
}
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Immediate moves.
Replace neverHasSideEffects=1 with hasSideEffects=0 in all .td files. llvm-svn: 222801
2014-11-26 08:46:26 +08:00
let hasSideEffects = 0, isAsCheapAsAMove = 1, isMoveImm = 1,
[SystemZ] Allow immediate moves to be rematerialized llvm-svn: 185068
2013-06-27 17:38:48 +08:00
isReMaterializable = 1 in {
[SystemZ] Add patterns to load a constant into a high word (IIHF) Similar to low words, we can use the shorter LLIHL and LLIHH if it turns out that the other half of the GR64 isn't live. llvm-svn: 191750
2013-10-01 21:02:28 +08:00
// 16-bit sign-extended immediates. LHIMux expands to LHI or IIHF,
// deopending on the choice of register.
def LHIMux : UnaryRIPseudo<bitconvert, GRX32, imm32sx16>,
Requires<[FeatureHighWord]>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
def LHI : UnaryRI<"lhi", 0xA78, bitconvert, GR32, imm32sx16>;
def LGHI : UnaryRI<"lghi", 0xA79, bitconvert, GR64, imm64sx16>;
// Other 16-bit immediates.
def LLILL : UnaryRI<"llill", 0xA5F, bitconvert, GR64, imm64ll16>;
def LLILH : UnaryRI<"llilh", 0xA5E, bitconvert, GR64, imm64lh16>;
def LLIHL : UnaryRI<"llihl", 0xA5D, bitconvert, GR64, imm64hl16>;
def LLIHH : UnaryRI<"llihh", 0xA5C, bitconvert, GR64, imm64hh16>;
// 32-bit immediates.
def LGFI : UnaryRIL<"lgfi", 0xC01, bitconvert, GR64, imm64sx32>;
def LLILF : UnaryRIL<"llilf", 0xC0F, bitconvert, GR64, imm64lf32>;
def LLIHF : UnaryRIL<"llihf", 0xC0E, bitconvert, GR64, imm64hf32>;
}
// Register loads.
let canFoldAsLoad = 1, SimpleBDXLoad = 1 in {
[SystemZ] Use upper words of GR64s for codegen This just adds the basics necessary for allocating the upper words to virtual registers (move, load and store). The move support is parameterised in a way that makes it easy to handle zero extensions, but the associated zero-extend patterns are added by a later patch. The easiest way of testing this seemed to be add a new "h" register constraint for high words. I don't expect the constraint to be useful in real inline asms, but it should work, so I didn't try to hide it behind an option. llvm-svn: 191739
2013-10-01 19:26:28 +08:00
// Expands to L, LY or LFH, depending on the choice of register.
def LMux : UnaryRXYPseudo<"l", load, GRX32, 4>,
Requires<[FeatureHighWord]>;
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
defm L : UnaryRXPair<"l", 0x58, 0xE358, load, GR32, 4>;
[SystemZ] Reapply: Add definitions of LFH and STFH Originally committed as r191661, but reverted because it changed the matching order of comparisons on some hosts. That should have been fixed by r191735. llvm-svn: 191738
2013-10-01 18:31:04 +08:00
def LFH : UnaryRXY<"lfh", 0xE3CA, load, GRH32, 4>,
Requires<[FeatureHighWord]>;
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def LG : UnaryRXY<"lg", 0xE304, load, GR64, 8>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// These instructions are split after register allocation, so we don't
// want a custom inserter.
let Has20BitOffset = 1, HasIndex = 1, Is128Bit = 1 in {
def L128 : Pseudo<(outs GR128:$dst), (ins bdxaddr20only128:$src),
[(set GR128:$dst, (load bdxaddr20only128:$src))]>;
}
}
[SystemZ] Optimize floating-point comparisons with zero This follows the same lines as the integer code. In the end it seemed easier to have a second 4-bit mask in TSFlags to specify the compare-like CC values. That eats one more TSFlags bit than adding a CCHasUnordered would have done, but it feels more concise. llvm-svn: 187883
2013-08-07 19:10:06 +08:00
let Defs = [CC], CCValues = 0xE, CompareZeroCCMask = 0xE in {
[SystemZ] Add LOAD AND TEST instructions Just the definitions and MC support. The next patch uses them for codegen. llvm-svn: 187719
2013-08-05 19:00:53 +08:00
def LT : UnaryRXY<"lt", 0xE312, load, GR32, 4>;
def LTG : UnaryRXY<"ltg", 0xE302, load, GR64, 8>;
}
[SystemZ] Use MVC to spill loads and stores Try to use MVC when spilling the destination of a simple load or the source of a simple store. As explained in the comment, this doesn't yet handle the case where the load or store location is also a frame index, since that could lead to two simultaneous scavenger spills, something the backend can't handle yet. spill-02.py tests that this restriction kicks in, but unfortunately I've not yet found a case that would fail without it. The volatile trick I used for other scavenger tests doesn't work here because we can't use MVC for volatile accesses anyway. I'm planning on relaxing the restriction later, hopefully with a test that does trigger the problem... Tests @f8 and @f9 also showed that L(G)RL and ST(G)RL were wrongly classified as SimpleBDX{Load,Store}. It wouldn't be easy to test for that bug separately, which is why I didn't split out the fix as a separate patch. llvm-svn: 185434
2013-07-02 23:28:56 +08:00
let canFoldAsLoad = 1 in {
def LRL : UnaryRILPC<"lrl", 0xC4D, aligned_load, GR32>;
def LGRL : UnaryRILPC<"lgrl", 0xC48, aligned_load, GR64>;
}
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
[SystemZ] Add LOC and LOCG As with the stores, these instructions can trap when the condition is false, so they are only used for things like (cond ? x : *ptr). llvm-svn: 187112
2013-07-25 17:04:52 +08:00
// Load on condition.
let isCodeGenOnly = 1, Uses = [CC] in {
[SystemZ] Be more careful about inverting CC masks (conditional loads) Extend r187495 to conditional loads. I split this out because the easiest way seemed to be to force a particular operand order in SystemZISelDAGToDAG.cpp. llvm-svn: 187496
2013-07-31 20:38:08 +08:00
def LOC : CondUnaryRSY<"loc", 0xEBF2, nonvolatile_load, GR32, 4>;
def LOCG : CondUnaryRSY<"locg", 0xEBE2, nonvolatile_load, GR64, 8>;
[SystemZ] Add LOC and LOCG As with the stores, these instructions can trap when the condition is false, so they are only used for things like (cond ? x : *ptr). llvm-svn: 187112
2013-07-25 17:04:52 +08:00
}
let Uses = [CC] in {
def AsmLOC : AsmCondUnaryRSY<"loc", 0xEBF2, GR32, 4>;
def AsmLOCG : AsmCondUnaryRSY<"locg", 0xEBE2, GR64, 8>;
}
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Register stores.
let SimpleBDXStore = 1 in {
[SystemZ] Use upper words of GR64s for codegen This just adds the basics necessary for allocating the upper words to virtual registers (move, load and store). The move support is parameterised in a way that makes it easy to handle zero extensions, but the associated zero-extend patterns are added by a later patch. The easiest way of testing this seemed to be add a new "h" register constraint for high words. I don't expect the constraint to be useful in real inline asms, but it should work, so I didn't try to hide it behind an option. llvm-svn: 191739
2013-10-01 19:26:28 +08:00
// Expands to ST, STY or STFH, depending on the choice of register.
def STMux : StoreRXYPseudo<store, GRX32, 4>,
Requires<[FeatureHighWord]>;
[SystemZ] Use subregs for 64-bit truncating stores Another patch to reduce the duplication of encoding information. Rather than define separate patterns for truncating 64-bit stores, use the 32-bit stores with a subreg. No behavioral changed intended. llvm-svn: 191365
2013-09-25 18:29:47 +08:00
defm ST : StoreRXPair<"st", 0x50, 0xE350, store, GR32, 4>;
[SystemZ] Reapply: Add definitions of LFH and STFH Originally committed as r191661, but reverted because it changed the matching order of comparisons on some hosts. That should have been fixed by r191735. llvm-svn: 191738
2013-10-01 18:31:04 +08:00
def STFH : StoreRXY<"stfh", 0xE3CB, store, GRH32, 4>,
Requires<[FeatureHighWord]>;
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def STG : StoreRXY<"stg", 0xE324, store, GR64, 8>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// These instructions are split after register allocation, so we don't
// want a custom inserter.
let Has20BitOffset = 1, HasIndex = 1, Is128Bit = 1 in {
def ST128 : Pseudo<(outs), (ins GR128:$src, bdxaddr20only128:$dst),
[(store GR128:$src, bdxaddr20only128:$dst)]>;
}
}
[SystemZ] Use subregs for 64-bit truncating stores Another patch to reduce the duplication of encoding information. Rather than define separate patterns for truncating 64-bit stores, use the 32-bit stores with a subreg. No behavioral changed intended. llvm-svn: 191365
2013-09-25 18:29:47 +08:00
def STRL : StoreRILPC<"strl", 0xC4F, aligned_store, GR32>;
[SystemZ] Use MVC to spill loads and stores Try to use MVC when spilling the destination of a simple load or the source of a simple store. As explained in the comment, this doesn't yet handle the case where the load or store location is also a frame index, since that could lead to two simultaneous scavenger spills, something the backend can't handle yet. spill-02.py tests that this restriction kicks in, but unfortunately I've not yet found a case that would fail without it. The volatile trick I used for other scavenger tests doesn't work here because we can't use MVC for volatile accesses anyway. I'm planning on relaxing the restriction later, hopefully with a test that does trigger the problem... Tests @f8 and @f9 also showed that L(G)RL and ST(G)RL were wrongly classified as SimpleBDX{Load,Store}. It wouldn't be easy to test for that bug separately, which is why I didn't split out the fix as a separate patch. llvm-svn: 185434
2013-07-02 23:28:56 +08:00
def STGRL : StoreRILPC<"stgrl", 0xC4B, aligned_store, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
[SystemZ] Add STOC and STOCG These instructions are allowed to trap even if the condition is false, so for now they are only used for "*ptr = (cond ? x : *ptr)"-style constructs. llvm-svn: 187111
2013-07-25 16:57:02 +08:00
// Store on condition.
let isCodeGenOnly = 1, Uses = [CC] in {
[SystemZ] Use subregs for 64-bit truncating stores Another patch to reduce the duplication of encoding information. Rather than define separate patterns for truncating 64-bit stores, use the 32-bit stores with a subreg. No behavioral changed intended. llvm-svn: 191365
2013-09-25 18:29:47 +08:00
def STOC : CondStoreRSY<"stoc", 0xEBF3, GR32, 4>;
def STOCG : CondStoreRSY<"stocg", 0xEBE3, GR64, 8>;
[SystemZ] Add STOC and STOCG These instructions are allowed to trap even if the condition is false, so for now they are only used for "*ptr = (cond ? x : *ptr)"-style constructs. llvm-svn: 187111
2013-07-25 16:57:02 +08:00
}
let Uses = [CC] in {
def AsmSTOC : AsmCondStoreRSY<"stoc", 0xEBF3, GR32, 4>;
def AsmSTOCG : AsmCondStoreRSY<"stocg", 0xEBE3, GR64, 8>;
}
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// 8-bit immediate stores to 8-bit fields.
defm MVI : StoreSIPair<"mvi", 0x92, 0xEB52, truncstorei8, imm32zx8trunc>;
// 16-bit immediate stores to 16-, 32- or 64-bit fields.
def MVHHI : StoreSIL<"mvhhi", 0xE544, truncstorei16, imm32sx16trunc>;
def MVHI : StoreSIL<"mvhi", 0xE54C, store, imm32sx16>;
def MVGHI : StoreSIL<"mvghi", 0xE548, store, imm64sx16>;
[SystemZ] Add the MVC instruction This is the first use of D(L,B) addressing, which required a fair bit of surgery. For that reason, the patch just adds the instruction definition and the associated assembler and disassembler support. A later patch will actually make use of it for codegen. llvm-svn: 185433
2013-07-02 22:56:45 +08:00
// Memory-to-memory moves.
let mayLoad = 1, mayStore = 1 in
[SystemZ] Extend memcpy and memset support to all constant lengths Lengths up to a certain threshold (currently 6 * 256) use a series of MVCs. Lengths above that threshold use a loop to handle X*256 bytes followed by a single MVC to handle the excess (if any). This loop will also be needed in future when support for variable lengths is added. Because the same tablegen classes are used to define MVC and CLC, the patch also has the side-effect of defining a pseudo loop instruction for CLC. That instruction isn't used yet (and wouldn't be handled correctly if it were). I'm planning to use it soon though. llvm-svn: 189331
2013-08-27 17:54:29 +08:00
defm MVC : MemorySS<"mvc", 0xD2, z_mvc, z_mvc_loop>;
[SystemZ] Use MVC for memcpy Use MVC for memcpy in cases where a single MVC is enough. Using MVC is a win for longer copies too, but I'll leave that for later. llvm-svn: 185802
2013-07-08 17:35:23 +08:00
[SystemZ] Use MVST to implement strcpy and stpcpy llvm-svn: 188546
2013-08-16 19:29:37 +08:00
// String moves.
[SystemZ] Rename 32-bit GPR registers I'm about to add support for high-word operations, so it seemed better for the low-word registers to have names like R0L rather than R0W. No behavioral change intended. llvm-svn: 191655
2013-09-30 16:48:38 +08:00
let mayLoad = 1, mayStore = 1, Defs = [CC], Uses = [R0L] in
[SystemZ] Use MVST to implement strcpy and stpcpy llvm-svn: 188546
2013-08-16 19:29:37 +08:00
defm MVST : StringRRE<"mvst", 0xB255, z_stpcpy>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
//===----------------------------------------------------------------------===//
// Sign extensions
//===----------------------------------------------------------------------===//
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
//
// Note that putting these before zero extensions mean that we will prefer
// them for anyextload*. There's not really much to choose between the two
// either way, but signed-extending loads have a short LH and a long LHY,
// while zero-extending loads have only the long LLH.
//
//===----------------------------------------------------------------------===//
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// 32-bit extensions from registers.
Replace neverHasSideEffects=1 with hasSideEffects=0 in all .td files. llvm-svn: 222801
2014-11-26 08:46:26 +08:00
let hasSideEffects = 0 in {
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def LBR : UnaryRRE<"lb", 0xB926, sext8, GR32, GR32>;
def LHR : UnaryRRE<"lh", 0xB927, sext16, GR32, GR32>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
// 64-bit extensions from registers.
Replace neverHasSideEffects=1 with hasSideEffects=0 in all .td files. llvm-svn: 222801
2014-11-26 08:46:26 +08:00
let hasSideEffects = 0 in {
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def LGBR : UnaryRRE<"lgb", 0xB906, sext8, GR64, GR64>;
def LGHR : UnaryRRE<"lgh", 0xB907, sext16, GR64, GR64>;
def LGFR : UnaryRRE<"lgf", 0xB914, sext32, GR64, GR32>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
[SystemZ] Optimize floating-point comparisons with zero This follows the same lines as the integer code. In the end it seemed easier to have a second 4-bit mask in TSFlags to specify the compare-like CC values. That eats one more TSFlags bit than adding a CCHasUnordered would have done, but it feels more concise. llvm-svn: 187883
2013-08-07 19:10:06 +08:00
let Defs = [CC], CCValues = 0xE, CompareZeroCCMask = 0xE in
[SystemZ] Add LOAD AND TEST instructions Just the definitions and MC support. The next patch uses them for codegen. llvm-svn: 187719
2013-08-05 19:00:53 +08:00
def LTGFR : UnaryRRE<"ltgf", 0xB912, null_frag, GR64, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Match 32-to-64-bit sign extensions in which the source is already
// in a 64-bit register.
def : Pat<(sext_inreg GR64:$src, i32),
[SystemZ] Rename subregs and add subreg_h32 Use subreg_hNN and subreg_lNN for the high and low NN bits of a register. List the low registers first, so that subreg_l32 also means the low 32 bits of a 128-bit register. Floats are stored in the upper 32 bits of a 64-bit register, so they should use subreg_h32 rather than subreg_l32. No behavioral change intended. llvm-svn: 191659
2013-09-30 18:28:35 +08:00
(LGFR (EXTRACT_SUBREG GR64:$src, subreg_l32))>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
[SystemZ] Add sign-extending high-word loads (LBH and LHH) llvm-svn: 191740
2013-10-01 20:11:47 +08:00
// 32-bit extensions from 8-bit memory. LBMux expands to LB or LBH,
// depending on the choice of register.
def LBMux : UnaryRXYPseudo<"lb", asextloadi8, GRX32, 1>,
Requires<[FeatureHighWord]>;
def LB : UnaryRXY<"lb", 0xE376, asextloadi8, GR32, 1>;
def LBH : UnaryRXY<"lbh", 0xE3C0, asextloadi8, GRH32, 1>,
Requires<[FeatureHighWord]>;
// 32-bit extensions from 16-bit memory. LHMux expands to LH or LHH,
// depending on the choice of register.
def LHMux : UnaryRXYPseudo<"lh", asextloadi16, GRX32, 2>,
Requires<[FeatureHighWord]>;
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
defm LH : UnaryRXPair<"lh", 0x48, 0xE378, asextloadi16, GR32, 2>;
[SystemZ] Add sign-extending high-word loads (LBH and LHH) llvm-svn: 191740
2013-10-01 20:11:47 +08:00
def LHH : UnaryRXY<"lhh", 0xE3C4, asextloadi16, GRH32, 2>,
Requires<[FeatureHighWord]>;
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
def LHRL : UnaryRILPC<"lhrl", 0xC45, aligned_asextloadi16, GR32>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// 64-bit extensions from memory.
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
def LGB : UnaryRXY<"lgb", 0xE377, asextloadi8, GR64, 1>;
def LGH : UnaryRXY<"lgh", 0xE315, asextloadi16, GR64, 2>;
def LGF : UnaryRXY<"lgf", 0xE314, asextloadi32, GR64, 4>;
def LGHRL : UnaryRILPC<"lghrl", 0xC44, aligned_asextloadi16, GR64>;
def LGFRL : UnaryRILPC<"lgfrl", 0xC4C, aligned_asextloadi32, GR64>;
[SystemZ] Optimize floating-point comparisons with zero This follows the same lines as the integer code. In the end it seemed easier to have a second 4-bit mask in TSFlags to specify the compare-like CC values. That eats one more TSFlags bit than adding a CCHasUnordered would have done, but it feels more concise. llvm-svn: 187883
2013-08-07 19:10:06 +08:00
let Defs = [CC], CCValues = 0xE, CompareZeroCCMask = 0xE in
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
def LTGF : UnaryRXY<"ltgf", 0xE332, asextloadi32, GR64, 4>;
[SystemZ] Use MVC for simple load/store pairs Look for patterns of the form (store (load ...), ...) in which the two locations are known not to partially overlap. (Identical locations are OK.) These sequences are better implemented by MVC unless either the load or the store could use RELATIVE LONG instructions. The testcase showed that we weren't using LHRL and LGHRL for extload16, only sextloadi16. The patch fixes that too. llvm-svn: 185919
2013-07-09 17:46:39 +08:00
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
//===----------------------------------------------------------------------===//
// Zero extensions
//===----------------------------------------------------------------------===//
// 32-bit extensions from registers.
Replace neverHasSideEffects=1 with hasSideEffects=0 in all .td files. llvm-svn: 222801
2014-11-26 08:46:26 +08:00
let hasSideEffects = 0 in {
[SystemZ] Add register zero extensions involving at least one high word llvm-svn: 191746
2013-10-01 20:49:07 +08:00
// Expands to LLCR or RISB[LH]G, depending on the choice of registers.
def LLCRMux : UnaryRRPseudo<"llc", zext8, GRX32, GRX32>,
Requires<[FeatureHighWord]>;
def LLCR : UnaryRRE<"llc", 0xB994, zext8, GR32, GR32>;
// Expands to LLHR or RISB[LH]G, depending on the choice of registers.
def LLHRMux : UnaryRRPseudo<"llh", zext16, GRX32, GRX32>,
Requires<[FeatureHighWord]>;
def LLHR : UnaryRRE<"llh", 0xB995, zext16, GR32, GR32>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
// 64-bit extensions from registers.
Replace neverHasSideEffects=1 with hasSideEffects=0 in all .td files. llvm-svn: 222801
2014-11-26 08:46:26 +08:00
let hasSideEffects = 0 in {
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def LLGCR : UnaryRRE<"llgc", 0xB984, zext8, GR64, GR64>;
def LLGHR : UnaryRRE<"llgh", 0xB985, zext16, GR64, GR64>;
def LLGFR : UnaryRRE<"llgf", 0xB916, zext32, GR64, GR32>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
// Match 32-to-64-bit zero extensions in which the source is already
// in a 64-bit register.
def : Pat<(and GR64:$src, 0xffffffff),
[SystemZ] Rename subregs and add subreg_h32 Use subreg_hNN and subreg_lNN for the high and low NN bits of a register. List the low registers first, so that subreg_l32 also means the low 32 bits of a 128-bit register. Floats are stored in the upper 32 bits of a 64-bit register, so they should use subreg_h32 rather than subreg_l32. No behavioral change intended. llvm-svn: 191659
2013-09-30 18:28:35 +08:00
(LLGFR (EXTRACT_SUBREG GR64:$src, subreg_l32))>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
[SystemZ] Add zero-extending high-word loads (LLCH and LLHH) llvm-svn: 191742
2013-10-01 20:19:08 +08:00
// 32-bit extensions from 8-bit memory. LLCMux expands to LLC or LLCH,
// depending on the choice of register.
def LLCMux : UnaryRXYPseudo<"llc", azextloadi8, GRX32, 1>,
Requires<[FeatureHighWord]>;
def LLC : UnaryRXY<"llc", 0xE394, azextloadi8, GR32, 1>;
def LLCH : UnaryRXY<"llch", 0xE3C2, azextloadi8, GR32, 1>,
Requires<[FeatureHighWord]>;
// 32-bit extensions from 16-bit memory. LLHMux expands to LLH or LLHH,
// depending on the choice of register.
def LLHMux : UnaryRXYPseudo<"llh", azextloadi16, GRX32, 2>,
Requires<[FeatureHighWord]>;
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
def LLH : UnaryRXY<"llh", 0xE395, azextloadi16, GR32, 2>;
[SystemZ] Add zero-extending high-word loads (LLCH and LLHH) llvm-svn: 191742
2013-10-01 20:19:08 +08:00
def LLHH : UnaryRXY<"llhh", 0xE3C6, azextloadi16, GR32, 2>,
Requires<[FeatureHighWord]>;
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
def LLHRL : UnaryRILPC<"llhrl", 0xC42, aligned_azextloadi16, GR32>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// 64-bit extensions from memory.
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
def LLGC : UnaryRXY<"llgc", 0xE390, azextloadi8, GR64, 1>;
def LLGH : UnaryRXY<"llgh", 0xE391, azextloadi16, GR64, 2>;
def LLGF : UnaryRXY<"llgf", 0xE316, azextloadi32, GR64, 4>;
def LLGHRL : UnaryRILPC<"llghrl", 0xC46, aligned_azextloadi16, GR64>;
def LLGFRL : UnaryRILPC<"llgfrl", 0xC4E, aligned_azextloadi32, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
//===----------------------------------------------------------------------===//
// Truncations
//===----------------------------------------------------------------------===//
// Truncations of 64-bit registers to 32-bit registers.
def : Pat<(i32 (trunc GR64:$src)),
[SystemZ] Rename subregs and add subreg_h32 Use subreg_hNN and subreg_lNN for the high and low NN bits of a register. List the low registers first, so that subreg_l32 also means the low 32 bits of a 128-bit register. Floats are stored in the upper 32 bits of a 64-bit register, so they should use subreg_h32 rather than subreg_l32. No behavioral change intended. llvm-svn: 191659
2013-09-30 18:28:35 +08:00
(EXTRACT_SUBREG GR64:$src, subreg_l32)>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
[SystemZ] Add truncating high-word stores (STCH and STHH) llvm-svn: 191743
2013-10-01 20:22:49 +08:00
// Truncations of 32-bit registers to 8-bit memory. STCMux expands to
// STC, STCY or STCH, depending on the choice of register.
def STCMux : StoreRXYPseudo<truncstorei8, GRX32, 1>,
Requires<[FeatureHighWord]>;
defm STC : StoreRXPair<"stc", 0x42, 0xE372, truncstorei8, GR32, 1>;
def STCH : StoreRXY<"stch", 0xE3C3, truncstorei8, GRH32, 1>,
Requires<[FeatureHighWord]>;
// Truncations of 32-bit registers to 16-bit memory. STHMux expands to
// STH, STHY or STHH, depending on the choice of register.
def STHMux : StoreRXYPseudo<truncstorei16, GRX32, 1>,
Requires<[FeatureHighWord]>;
defm STH : StoreRXPair<"sth", 0x40, 0xE370, truncstorei16, GR32, 2>;
def STHH : StoreRXY<"sthh", 0xE3C7, truncstorei16, GRH32, 2>,
Requires<[FeatureHighWord]>;
def STHRL : StoreRILPC<"sthrl", 0xC47, aligned_truncstorei16, GR32>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Truncations of 64-bit registers to memory.
[SystemZ] Use subregs for 64-bit truncating stores Another patch to reduce the duplication of encoding information. Rather than define separate patterns for truncating 64-bit stores, use the 32-bit stores with a subreg. No behavioral changed intended. llvm-svn: 191365
2013-09-25 18:29:47 +08:00
defm : StoreGR64Pair<STC, STCY, truncstorei8>;
defm : StoreGR64Pair<STH, STHY, truncstorei16>;
def : StoreGR64PC<STHRL, aligned_truncstorei16>;
defm : StoreGR64Pair<ST, STY, truncstorei32>;
def : StoreGR64PC<STRL, aligned_truncstorei32>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
//===----------------------------------------------------------------------===//
// Multi-register moves
//===----------------------------------------------------------------------===//
// Multi-register loads.
def LMG : LoadMultipleRSY<"lmg", 0xEB04, GR64>;
// Multi-register stores.
def STMG : StoreMultipleRSY<"stmg", 0xEB24, GR64>;
//===----------------------------------------------------------------------===//
// Byte swaps
//===----------------------------------------------------------------------===//
// Byte-swapping register moves.
Replace neverHasSideEffects=1 with hasSideEffects=0 in all .td files. llvm-svn: 222801
2014-11-26 08:46:26 +08:00
let hasSideEffects = 0 in {
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def LRVR : UnaryRRE<"lrv", 0xB91F, bswap, GR32, GR32>;
def LRVGR : UnaryRRE<"lrvg", 0xB90F, bswap, GR64, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
[SystemZ] Don't use LOAD and STORE REVERSED for volatile accesses Unlike most -- hopefully "all other", but I'm still checking -- memory instructions we support, LOAD REVERSED and STORE REVERSED may access the memory location several times. This means that they are not suitable for volatile loads and stores. This patch is a prerequisite for better atomic load and store support. The same principle applies there: almost all memory instructions we support are inherently atomic ("block concurrent"), but LOAD REVERSED and STORE REVERSED are exceptions. Other instructions continue to allow volatile operands. I will add positive "allows volatile" tests at the same time as the "allows atomic load or store" tests. llvm-svn: 183002
2013-05-31 21:25:22 +08:00
// Byte-swapping loads. Unlike normal loads, these instructions are
// allowed to access storage more than once.
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def LRV : UnaryRXY<"lrv", 0xE31E, loadu<bswap, nonvolatile_load>, GR32, 4>;
def LRVG : UnaryRXY<"lrvg", 0xE30F, loadu<bswap, nonvolatile_load>, GR64, 8>;
[SystemZ] Don't use LOAD and STORE REVERSED for volatile accesses Unlike most -- hopefully "all other", but I'm still checking -- memory instructions we support, LOAD REVERSED and STORE REVERSED may access the memory location several times. This means that they are not suitable for volatile loads and stores. This patch is a prerequisite for better atomic load and store support. The same principle applies there: almost all memory instructions we support are inherently atomic ("block concurrent"), but LOAD REVERSED and STORE REVERSED are exceptions. Other instructions continue to allow volatile operands. I will add positive "allows volatile" tests at the same time as the "allows atomic load or store" tests. llvm-svn: 183002
2013-05-31 21:25:22 +08:00
// Likewise byte-swapping stores.
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def STRV : StoreRXY<"strv", 0xE33E, storeu<bswap, nonvolatile_store>, GR32, 4>;
def STRVG : StoreRXY<"strvg", 0xE32F, storeu<bswap, nonvolatile_store>,
GR64, 8>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
//===----------------------------------------------------------------------===//
// Load address instructions
//===----------------------------------------------------------------------===//
// Load BDX-style addresses.
Replace neverHasSideEffects=1 with hasSideEffects=0 in all .td files. llvm-svn: 222801
2014-11-26 08:46:26 +08:00
let hasSideEffects = 0, isAsCheapAsAMove = 1, isReMaterializable = 1,
[SystemZ] Rename mapping table fields Rename Function->DispKey and PairType->DispSize. I'd originally used "Function" because I thought it might be useful for other InstMappings. However, it turns out that having two very similar instructions with the same Function makes it pretty useless for anything other than the displacement size key. Other InstMappings will want the key to be defined for only one instruction in the pair. No behavioural change intended. llvm-svn: 185526
2013-07-03 17:19:58 +08:00
DispKey = "la" in {
let DispSize = "12" in
[SystemZ] Match operands to fields by name rather than by order The SystemZ port currently relies on the order of the instruction operands matching the order of the instruction field lists. This isn't desirable for disassembly, where the two are matched only by name. E.g. the R1 and R2 fields of an RR instruction should have corresponding R1 and R2 operands. The main complication is that addresses are compound operands, and as far as I know there is no mechanism to allow individual suboperands to be selected by name in "let Inst{...} = ..." assignments. Luckily it doesn't really matter though. The SystemZ instruction encoding groups all address fields together in a predictable order, so it's just as valid to see the entire compound address operand as a single field. That's the approach taken in this patch. Matching by name in turn means that the operands to COPY SIGN and CONVERT TO FIXED instructions can be given in natural order. (It was easier to do this at the same time as the rename, since otherwise the intermediate step was too confusing.) No functional change intended. llvm-svn: 181769
2013-05-14 17:28:21 +08:00
def LA : InstRX<0x41, (outs GR64:$R1), (ins laaddr12pair:$XBD2),
"la\t$R1, $XBD2",
[(set GR64:$R1, laaddr12pair:$XBD2)]>;
[SystemZ] Rename mapping table fields Rename Function->DispKey and PairType->DispSize. I'd originally used "Function" because I thought it might be useful for other InstMappings. However, it turns out that having two very similar instructions with the same Function makes it pretty useless for anything other than the displacement size key. Other InstMappings will want the key to be defined for only one instruction in the pair. No behavioural change intended. llvm-svn: 185526
2013-07-03 17:19:58 +08:00
let DispSize = "20" in
[SystemZ] Match operands to fields by name rather than by order The SystemZ port currently relies on the order of the instruction operands matching the order of the instruction field lists. This isn't desirable for disassembly, where the two are matched only by name. E.g. the R1 and R2 fields of an RR instruction should have corresponding R1 and R2 operands. The main complication is that addresses are compound operands, and as far as I know there is no mechanism to allow individual suboperands to be selected by name in "let Inst{...} = ..." assignments. Luckily it doesn't really matter though. The SystemZ instruction encoding groups all address fields together in a predictable order, so it's just as valid to see the entire compound address operand as a single field. That's the approach taken in this patch. Matching by name in turn means that the operands to COPY SIGN and CONVERT TO FIXED instructions can be given in natural order. (It was easier to do this at the same time as the rename, since otherwise the intermediate step was too confusing.) No functional change intended. llvm-svn: 181769
2013-05-14 17:28:21 +08:00
def LAY : InstRXY<0xE371, (outs GR64:$R1), (ins laaddr20pair:$XBD2),
"lay\t$R1, $XBD2",
[(set GR64:$R1, laaddr20pair:$XBD2)]>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
// Load a PC-relative address. There's no version of this instruction
// with a 16-bit offset, so there's no relaxation.
Replace neverHasSideEffects=1 with hasSideEffects=0 in all .td files. llvm-svn: 222801
2014-11-26 08:46:26 +08:00
let hasSideEffects = 0, isAsCheapAsAMove = 1, isMoveImm = 1,
[SystemZ] Allow LA and LARL to be rematerialized llvm-svn: 185069
2013-06-27 17:42:10 +08:00
isReMaterializable = 1 in {
[SystemZ] Match operands to fields by name rather than by order The SystemZ port currently relies on the order of the instruction operands matching the order of the instruction field lists. This isn't desirable for disassembly, where the two are matched only by name. E.g. the R1 and R2 fields of an RR instruction should have corresponding R1 and R2 operands. The main complication is that addresses are compound operands, and as far as I know there is no mechanism to allow individual suboperands to be selected by name in "let Inst{...} = ..." assignments. Luckily it doesn't really matter though. The SystemZ instruction encoding groups all address fields together in a predictable order, so it's just as valid to see the entire compound address operand as a single field. That's the approach taken in this patch. Matching by name in turn means that the operands to COPY SIGN and CONVERT TO FIXED instructions can be given in natural order. (It was easier to do this at the same time as the rename, since otherwise the intermediate step was too confusing.) No functional change intended. llvm-svn: 181769
2013-05-14 17:28:21 +08:00
def LARL : InstRIL<0xC00, (outs GR64:$R1), (ins pcrel32:$I2),
"larl\t$R1, $I2",
[(set GR64:$R1, pcrel32:$I2)]>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
[SystemZ] Support all TLS access models - CodeGen part The current SystemZ back-end only supports the local-exec TLS access model. This patch adds all required CodeGen support for the other TLS models, which means in particular: - Expand initial-exec TLS accesses by loading TLS offsets from the GOT using @indntpoff relocations. - Expand general-dynamic and local-dynamic accesses by generating the appropriate calls to __tls_get_offset. Note that this routine has a non-standard ABI and requires loading the GOT pointer into %r12, so the patch also adds support for the GLOBAL_OFFSET_TABLE ISD node. - Add a new platform-specific optimization pass to remove redundant __tls_get_offset calls in the local-dynamic model (modeled after the corresponding X86 pass). - Add test cases verifying all access models and optimizations. llvm-svn: 229654
2015-02-18 17:13:27 +08:00
// Load the Global Offset Table address. This will be lowered into a
// larl $R1, _GLOBAL_OFFSET_TABLE_
// instruction.
def GOT : Alias<6, (outs GR64:$R1), (ins),
[(set GR64:$R1, (global_offset_table))]>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
//===----------------------------------------------------------------------===//
[SystemZ] Add integer absolute (load positive) llvm-svn: 188670
2013-08-19 20:48:54 +08:00
// Absolute and Negation
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
//===----------------------------------------------------------------------===//
[SystemZ] Add integer absolute (load positive) llvm-svn: 188670
2013-08-19 20:48:54 +08:00
let Defs = [CC] in {
let CCValues = 0xF, CompareZeroCCMask = 0x8 in {
[SystemZ] Extend integer absolute selection This patch makes more use of LPGFR and LNGFR. It builds on top of the LTGFR selection from r197234. Most of the tests are motivated by what InstCombine would produce. llvm-svn: 197236
2013-12-13 23:35:00 +08:00
def LPR : UnaryRR <"lp", 0x10, z_iabs, GR32, GR32>;
def LPGR : UnaryRRE<"lpg", 0xB900, z_iabs, GR64, GR64>;
[SystemZ] Add integer absolute (load positive) llvm-svn: 188670
2013-08-19 20:48:54 +08:00
}
let CCValues = 0xE, CompareZeroCCMask = 0xE in
def LPGFR : UnaryRRE<"lpgf", 0xB910, null_frag, GR64, GR32>;
}
[SystemZ] Extend integer absolute selection This patch makes more use of LPGFR and LNGFR. It builds on top of the LTGFR selection from r197234. Most of the tests are motivated by what InstCombine would produce. llvm-svn: 197236
2013-12-13 23:35:00 +08:00
def : Pat<(z_iabs32 GR32:$src), (LPR GR32:$src)>;
def : Pat<(z_iabs64 GR64:$src), (LPGR GR64:$src)>;
defm : SXU<z_iabs, LPGFR>;
[SystemZ] Add integer absolute (load positive) llvm-svn: 188670
2013-08-19 20:48:54 +08:00
defm : SXU<z_iabs64, LPGFR>;
[SystemZ] Add negative integer absolute (load negative) For now this matches the equivalent of (neg (abs ...)), which did hit a few times in projects/test-suite. We should probably also match cases where absolute-like selects are used with reversed arguments. llvm-svn: 188671
2013-08-19 20:56:58 +08:00
let Defs = [CC] in {
let CCValues = 0xF, CompareZeroCCMask = 0x8 in {
[SystemZ] Extend integer absolute selection This patch makes more use of LPGFR and LNGFR. It builds on top of the LTGFR selection from r197234. Most of the tests are motivated by what InstCombine would produce. llvm-svn: 197236
2013-12-13 23:35:00 +08:00
def LNR : UnaryRR <"ln", 0x11, z_inegabs, GR32, GR32>;
def LNGR : UnaryRRE<"lng", 0xB901, z_inegabs, GR64, GR64>;
[SystemZ] Add negative integer absolute (load negative) For now this matches the equivalent of (neg (abs ...)), which did hit a few times in projects/test-suite. We should probably also match cases where absolute-like selects are used with reversed arguments. llvm-svn: 188671
2013-08-19 20:56:58 +08:00
}
let CCValues = 0xE, CompareZeroCCMask = 0xE in
def LNGFR : UnaryRRE<"lngf", 0xB911, null_frag, GR64, GR32>;
}
[SystemZ] Extend integer absolute selection This patch makes more use of LPGFR and LNGFR. It builds on top of the LTGFR selection from r197234. Most of the tests are motivated by what InstCombine would produce. llvm-svn: 197236
2013-12-13 23:35:00 +08:00
def : Pat<(z_inegabs32 GR32:$src), (LNR GR32:$src)>;
def : Pat<(z_inegabs64 GR64:$src), (LNGR GR64:$src)>;
defm : SXU<z_inegabs, LNGFR>;
[SystemZ] Add negative integer absolute (load negative) For now this matches the equivalent of (neg (abs ...)), which did hit a few times in projects/test-suite. We should probably also match cases where absolute-like selects are used with reversed arguments. llvm-svn: 188671
2013-08-19 20:56:58 +08:00
defm : SXU<z_inegabs64, LNGFR>;
[SystemZ] Rename PSW to CC Addresses a review comment from Ulrich Weigand. No functional change intended. I'm not sure whether the old TODO that this patch touches still holds, but that's something we'd get to when adding a targetted scheduling description. llvm-svn: 182474
2013-05-22 21:38:45 +08:00
let Defs = [CC] in {
[SystemZ] Optimize floating-point comparisons with zero This follows the same lines as the integer code. In the end it seemed easier to have a second 4-bit mask in TSFlags to specify the compare-like CC values. That eats one more TSFlags bit than adding a CCHasUnordered would have done, but it feels more concise. llvm-svn: 187883
2013-08-07 19:10:06 +08:00
let CCValues = 0xF, CompareZeroCCMask = 0x8 in {
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
def LCR : UnaryRR <"lc", 0x13, ineg, GR32, GR32>;
def LCGR : UnaryRRE<"lcg", 0xB903, ineg, GR64, GR64>;
}
[SystemZ] Optimize floating-point comparisons with zero This follows the same lines as the integer code. In the end it seemed easier to have a second 4-bit mask in TSFlags to specify the compare-like CC values. That eats one more TSFlags bit than adding a CCHasUnordered would have done, but it feels more concise. llvm-svn: 187883
2013-08-07 19:10:06 +08:00
let CCValues = 0xE, CompareZeroCCMask = 0xE in
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
def LCGFR : UnaryRRE<"lcgf", 0xB913, null_frag, GR64, GR32>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
defm : SXU<ineg, LCGFR>;
//===----------------------------------------------------------------------===//
// Insertion
//===----------------------------------------------------------------------===//
let isCodeGenOnly = 1 in
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
defm IC32 : BinaryRXPair<"ic", 0x43, 0xE373, inserti8, GR32, azextloadi8, 1>;
defm IC : BinaryRXPair<"ic", 0x43, 0xE373, inserti8, GR64, azextloadi8, 1>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
defm : InsertMem<"inserti8", IC32, GR32, azextloadi8, bdxaddr12pair>;
defm : InsertMem<"inserti8", IC32Y, GR32, azextloadi8, bdxaddr20pair>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
defm : InsertMem<"inserti8", IC, GR64, azextloadi8, bdxaddr12pair>;
defm : InsertMem<"inserti8", ICY, GR64, azextloadi8, bdxaddr20pair>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Insertions of a 16-bit immediate, leaving other bits unaffected.
// We don't have or_as_insert equivalents of these operations because
// OI is available instead.
[SystemZ] Allow integer insertions with a high-word destination llvm-svn: 191753
2013-10-01 21:18:56 +08:00
//
// IIxMux expands to II[LH]x, depending on the choice of register.
def IILMux : BinaryRIPseudo<insertll, GRX32, imm32ll16>,
Requires<[FeatureHighWord]>;
def IIHMux : BinaryRIPseudo<insertlh, GRX32, imm32lh16>,
Requires<[FeatureHighWord]>;
[SystemZ] Define the GR64 low-word logic instructions as pseudo aliases. Another patch to avoid duplication of encoding information. Things like NILF, NILL and NILH are used as both 32-bit and 64-bit instructions. Here the 64-bit versions are defined as aliases of the 32-bit ones. llvm-svn: 191369
2013-09-25 19:11:53 +08:00
def IILL : BinaryRI<"iill", 0xA53, insertll, GR32, imm32ll16>;
def IILH : BinaryRI<"iilh", 0xA52, insertlh, GR32, imm32lh16>;
[SystemZ] Allow integer insertions with a high-word destination llvm-svn: 191753
2013-10-01 21:18:56 +08:00
def IIHL : BinaryRI<"iihl", 0xA51, insertll, GRH32, imm32ll16>;
def IIHH : BinaryRI<"iihh", 0xA50, insertlh, GRH32, imm32lh16>;
[SystemZ] Define the GR64 low-word logic instructions as pseudo aliases. Another patch to avoid duplication of encoding information. Things like NILF, NILL and NILH are used as both 32-bit and 64-bit instructions. Here the 64-bit versions are defined as aliases of the 32-bit ones. llvm-svn: 191369
2013-09-25 19:11:53 +08:00
def IILL64 : BinaryAliasRI<insertll, GR64, imm64ll16>;
def IILH64 : BinaryAliasRI<insertlh, GR64, imm64lh16>;
[SystemZ] Allow integer insertions with a high-word destination llvm-svn: 191753
2013-10-01 21:18:56 +08:00
def IIHL64 : BinaryAliasRI<inserthl, GR64, imm64hl16>;
def IIHH64 : BinaryAliasRI<inserthh, GR64, imm64hh16>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// ...likewise for 32-bit immediates. For GR32s this is a general
// full-width move. (We use IILF rather than something like LLILF
// for 32-bit moves because IILF leaves the upper 32 bits of the
// GR64 unchanged.)
[SystemZ] Add patterns to load a constant into a high word (IIHF) Similar to low words, we can use the shorter LLIHL and LLIHH if it turns out that the other half of the GR64 isn't live. llvm-svn: 191750
2013-10-01 21:02:28 +08:00
let isAsCheapAsAMove = 1, isMoveImm = 1, isReMaterializable = 1 in {
def IIFMux : UnaryRIPseudo<bitconvert, GRX32, uimm32>,
Requires<[FeatureHighWord]>;
[SystemZ] Define the GR64 low-word logic instructions as pseudo aliases. Another patch to avoid duplication of encoding information. Things like NILF, NILL and NILH are used as both 32-bit and 64-bit instructions. Here the 64-bit versions are defined as aliases of the 32-bit ones. llvm-svn: 191369
2013-09-25 19:11:53 +08:00
def IILF : UnaryRIL<"iilf", 0xC09, bitconvert, GR32, uimm32>;
[SystemZ] Add patterns to load a constant into a high word (IIHF) Similar to low words, we can use the shorter LLIHL and LLIHH if it turns out that the other half of the GR64 isn't live. llvm-svn: 191750
2013-10-01 21:02:28 +08:00
def IIHF : UnaryRIL<"iihf", 0xC08, bitconvert, GRH32, uimm32>;
}
[SystemZ] Define the GR64 low-word logic instructions as pseudo aliases. Another patch to avoid duplication of encoding information. Things like NILF, NILL and NILH are used as both 32-bit and 64-bit instructions. Here the 64-bit versions are defined as aliases of the 32-bit ones. llvm-svn: 191369
2013-09-25 19:11:53 +08:00
def IILF64 : BinaryAliasRIL<insertlf, GR64, imm64lf32>;
[SystemZ] Add patterns to load a constant into a high word (IIHF) Similar to low words, we can use the shorter LLIHL and LLIHH if it turns out that the other half of the GR64 isn't live. llvm-svn: 191750
2013-10-01 21:02:28 +08:00
def IIHF64 : BinaryAliasRIL<inserthf, GR64, imm64hf32>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// An alternative model of inserthf, with the first operand being
// a zero-extended value.
def : Pat<(or (zext32 GR32:$src), imm64hf32:$imm),
[SystemZ] Add patterns to load a constant into a high word (IIHF) Similar to low words, we can use the shorter LLIHL and LLIHH if it turns out that the other half of the GR64 isn't live. llvm-svn: 191750
2013-10-01 21:02:28 +08:00
(IIHF64 (INSERT_SUBREG (i64 (IMPLICIT_DEF)), GR32:$src, subreg_l32),
imm64hf32:$imm)>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
//===----------------------------------------------------------------------===//
// Addition
//===----------------------------------------------------------------------===//
// Plain addition.
[SystemZ] Optimize floating-point comparisons with zero This follows the same lines as the integer code. In the end it seemed easier to have a second 4-bit mask in TSFlags to specify the compare-like CC values. That eats one more TSFlags bit than adding a CCHasUnordered would have done, but it feels more concise. llvm-svn: 187883
2013-08-07 19:10:06 +08:00
let Defs = [CC], CCValues = 0xF, CompareZeroCCMask = 0x8 in {
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Addition of a register.
let isCommutable = 1 in {
[SystemZ] Add ARK, AGRK, SRK and SGRK The testsuite changes follow the same lines as for r186683. llvm-svn: 186686
2013-07-20 00:26:39 +08:00
defm AR : BinaryRRAndK<"a", 0x1A, 0xB9F8, add, GR32, GR32>;
defm AGR : BinaryRREAndK<"ag", 0xB908, 0xB9E8, add, GR64, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def AGFR : BinaryRRE<"agf", 0xB918, null_frag, GR64, GR32>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Addition of signed 16-bit immediates.
[SystemZ] Add immediate addition involving high words llvm-svn: 191774
2013-10-01 22:53:46 +08:00
defm AHIMux : BinaryRIAndKPseudo<"ahimux", add, GRX32, imm32sx16>;
[SystemZ] Add AHIK and AGHIK I did these as a separate patch because it uses a slightly different form of RIE layout. llvm-svn: 186687
2013-07-20 00:32:12 +08:00
defm AHI : BinaryRIAndK<"ahi", 0xA7A, 0xECD8, add, GR32, imm32sx16>;
defm AGHI : BinaryRIAndK<"aghi", 0xA7B, 0xECD9, add, GR64, imm64sx16>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Addition of signed 32-bit immediates.
[SystemZ] Add immediate addition involving high words llvm-svn: 191774
2013-10-01 22:53:46 +08:00
def AFIMux : BinaryRIPseudo<add, GRX32, simm32>,
Requires<[FeatureHighWord]>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
def AFI : BinaryRIL<"afi", 0xC29, add, GR32, simm32>;
[SystemZ] Add immediate addition involving high words llvm-svn: 191774
2013-10-01 22:53:46 +08:00
def AIH : BinaryRIL<"aih", 0xCC8, add, GRH32, simm32>,
Requires<[FeatureHighWord]>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
def AGFI : BinaryRIL<"agfi", 0xC28, add, GR64, imm64sx32>;
// Addition of memory.
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
defm AH : BinaryRXPair<"ah", 0x4A, 0xE37A, add, GR32, asextloadi16, 2>;
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
defm A : BinaryRXPair<"a", 0x5A, 0xE35A, add, GR32, load, 4>;
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
def AGF : BinaryRXY<"agf", 0xE318, add, GR64, asextloadi32, 4>;
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def AG : BinaryRXY<"ag", 0xE308, add, GR64, load, 8>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Addition to memory.
def ASI : BinarySIY<"asi", 0xEB6A, add, imm32sx8>;
def AGSI : BinarySIY<"agsi", 0xEB7A, add, imm64sx8>;
}
defm : SXB<add, GR64, AGFR>;
// Addition producing a carry.
[SystemZ] Rename PSW to CC Addresses a review comment from Ulrich Weigand. No functional change intended. I'm not sure whether the old TODO that this patch touches still holds, but that's something we'd get to when adding a targetted scheduling description. llvm-svn: 182474
2013-05-22 21:38:45 +08:00
let Defs = [CC] in {
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Addition of a register.
let isCommutable = 1 in {
[SystemZ] Add ALRK, AGLRK, SLRK and SGLRK Follows the same lines as r186686, but much more limited, since we only use ADD LOGICAL for multi-i64 additions. llvm-svn: 186689
2013-07-20 00:37:00 +08:00
defm ALR : BinaryRRAndK<"al", 0x1E, 0xB9FA, addc, GR32, GR32>;
defm ALGR : BinaryRREAndK<"alg", 0xB90A, 0xB9EA, addc, GR64, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def ALGFR : BinaryRRE<"algf", 0xB91A, null_frag, GR64, GR32>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
[SystemZ] Add ALRK, AGLRK, SLRK and SGLRK Follows the same lines as r186686, but much more limited, since we only use ADD LOGICAL for multi-i64 additions. llvm-svn: 186689
2013-07-20 00:37:00 +08:00
// Addition of signed 16-bit immediates.
def ALHSIK : BinaryRIE<"alhsik", 0xECDA, addc, GR32, imm32sx16>,
Requires<[FeatureDistinctOps]>;
def ALGHSIK : BinaryRIE<"alghsik", 0xECDB, addc, GR64, imm64sx16>,
Requires<[FeatureDistinctOps]>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Addition of unsigned 32-bit immediates.
def ALFI : BinaryRIL<"alfi", 0xC2B, addc, GR32, uimm32>;
def ALGFI : BinaryRIL<"algfi", 0xC2A, addc, GR64, imm64zx32>;
// Addition of memory.
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
defm AL : BinaryRXPair<"al", 0x5E, 0xE35E, addc, GR32, load, 4>;
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
def ALGF : BinaryRXY<"algf", 0xE31A, addc, GR64, azextloadi32, 4>;
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def ALG : BinaryRXY<"alg", 0xE30A, addc, GR64, load, 8>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
defm : ZXB<addc, GR64, ALGFR>;
// Addition producing and using a carry.
[SystemZ] Rename PSW to CC Addresses a review comment from Ulrich Weigand. No functional change intended. I'm not sure whether the old TODO that this patch touches still holds, but that's something we'd get to when adding a targetted scheduling description. llvm-svn: 182474
2013-05-22 21:38:45 +08:00
let Defs = [CC], Uses = [CC] in {
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Addition of a register.
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def ALCR : BinaryRRE<"alc", 0xB998, adde, GR32, GR32>;
def ALCGR : BinaryRRE<"alcg", 0xB988, adde, GR64, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Addition of memory.
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def ALC : BinaryRXY<"alc", 0xE398, adde, GR32, load, 4>;
def ALCG : BinaryRXY<"alcg", 0xE388, adde, GR64, load, 8>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
//===----------------------------------------------------------------------===//
// Subtraction
//===----------------------------------------------------------------------===//
Fix known typos Sweep the codebase for common typos. Includes some changes to visible function names that were misspelt. llvm-svn: 200018
2014-01-25 01:20:08 +08:00
// Plain subtraction. Although immediate forms exist, we use the
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// add-immediate instruction instead.
[SystemZ] Optimize floating-point comparisons with zero This follows the same lines as the integer code. In the end it seemed easier to have a second 4-bit mask in TSFlags to specify the compare-like CC values. That eats one more TSFlags bit than adding a CCHasUnordered would have done, but it feels more concise. llvm-svn: 187883
2013-08-07 19:10:06 +08:00
let Defs = [CC], CCValues = 0xF, CompareZeroCCMask = 0x8 in {
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Subtraction of a register.
[SystemZ] Add ARK, AGRK, SRK and SGRK The testsuite changes follow the same lines as for r186683. llvm-svn: 186686
2013-07-20 00:26:39 +08:00
defm SR : BinaryRRAndK<"s", 0x1B, 0xB9F9, sub, GR32, GR32>;
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def SGFR : BinaryRRE<"sgf", 0xB919, null_frag, GR64, GR32>;
[SystemZ] Add ARK, AGRK, SRK and SGRK The testsuite changes follow the same lines as for r186683. llvm-svn: 186686
2013-07-20 00:26:39 +08:00
defm SGR : BinaryRREAndK<"sg", 0xB909, 0xB9E9, sub, GR64, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Subtraction of memory.
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
defm SH : BinaryRXPair<"sh", 0x4B, 0xE37B, sub, GR32, asextloadi16, 2>;
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
defm S : BinaryRXPair<"s", 0x5B, 0xE35B, sub, GR32, load, 4>;
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
def SGF : BinaryRXY<"sgf", 0xE319, sub, GR64, asextloadi32, 4>;
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def SG : BinaryRXY<"sg", 0xE309, sub, GR64, load, 8>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
defm : SXB<sub, GR64, SGFR>;
// Subtraction producing a carry.
[SystemZ] Rename PSW to CC Addresses a review comment from Ulrich Weigand. No functional change intended. I'm not sure whether the old TODO that this patch touches still holds, but that's something we'd get to when adding a targetted scheduling description. llvm-svn: 182474
2013-05-22 21:38:45 +08:00
let Defs = [CC] in {
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Subtraction of a register.
[SystemZ] Add ALRK, AGLRK, SLRK and SGLRK Follows the same lines as r186686, but much more limited, since we only use ADD LOGICAL for multi-i64 additions. llvm-svn: 186689
2013-07-20 00:37:00 +08:00
defm SLR : BinaryRRAndK<"sl", 0x1F, 0xB9FB, subc, GR32, GR32>;
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def SLGFR : BinaryRRE<"slgf", 0xB91B, null_frag, GR64, GR32>;
[SystemZ] Add ALRK, AGLRK, SLRK and SGLRK Follows the same lines as r186686, but much more limited, since we only use ADD LOGICAL for multi-i64 additions. llvm-svn: 186689
2013-07-20 00:37:00 +08:00
defm SLGR : BinaryRREAndK<"slg", 0xB90B, 0xB9EB, subc, GR64, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Subtraction of unsigned 32-bit immediates. These don't match
// subc because we prefer addc for constants.
def SLFI : BinaryRIL<"slfi", 0xC25, null_frag, GR32, uimm32>;
def SLGFI : BinaryRIL<"slgfi", 0xC24, null_frag, GR64, imm64zx32>;
// Subtraction of memory.
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
defm SL : BinaryRXPair<"sl", 0x5F, 0xE35F, subc, GR32, load, 4>;
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
def SLGF : BinaryRXY<"slgf", 0xE31B, subc, GR64, azextloadi32, 4>;
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def SLG : BinaryRXY<"slg", 0xE30B, subc, GR64, load, 8>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
defm : ZXB<subc, GR64, SLGFR>;
// Subtraction producing and using a carry.
[SystemZ] Rename PSW to CC Addresses a review comment from Ulrich Weigand. No functional change intended. I'm not sure whether the old TODO that this patch touches still holds, but that's something we'd get to when adding a targetted scheduling description. llvm-svn: 182474
2013-05-22 21:38:45 +08:00
let Defs = [CC], Uses = [CC] in {
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Subtraction of a register.
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def SLBR : BinaryRRE<"slb", 0xB999, sube, GR32, GR32>;
def SLGBR : BinaryRRE<"slbg", 0xB989, sube, GR64, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Subtraction of memory.
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def SLB : BinaryRXY<"slb", 0xE399, sube, GR32, load, 4>;
def SLBG : BinaryRXY<"slbg", 0xE389, sube, GR64, load, 8>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
//===----------------------------------------------------------------------===//
// AND
//===----------------------------------------------------------------------===//
[SystemZ] Rename PSW to CC Addresses a review comment from Ulrich Weigand. No functional change intended. I'm not sure whether the old TODO that this patch touches still holds, but that's something we'd get to when adding a targetted scheduling description. llvm-svn: 182474
2013-05-22 21:38:45 +08:00
let Defs = [CC] in {
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// ANDs of a register.
[SystemZ] Optimize floating-point comparisons with zero This follows the same lines as the integer code. In the end it seemed easier to have a second 4-bit mask in TSFlags to specify the compare-like CC values. That eats one more TSFlags bit than adding a CCHasUnordered would have done, but it feels more concise. llvm-svn: 187883
2013-08-07 19:10:06 +08:00
let isCommutable = 1, CCValues = 0xC, CompareZeroCCMask = 0x8 in {
[SystemZ] Add NRK, ORK and XRK The atomic tests assume the two-operand forms, so I've restricted them to z10. Running and-01.ll, or-01.ll and xor-01.ll for z196 as well as z10 shows why using convertToThreeAddress() is better than exposing the three-operand forms first and then converting back to two operands where possible (which is what I'd originally tried). Using the three-operand form first stops us from taking advantage of NG, OG and XG for spills. llvm-svn: 186683
2013-07-20 00:21:55 +08:00
defm NR : BinaryRRAndK<"n", 0x14, 0xB9F4, and, GR32, GR32>;
[SystemZ] Add NGRK, OGRK and XGRK Like r186683, but for 64 bits. llvm-svn: 186685
2013-07-20 00:24:22 +08:00
defm NGR : BinaryRREAndK<"ng", 0xB980, 0xB9E4, and, GR64, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
[SystemZ] Postpone NI->RISBG conversion to convertToThreeAddress() r186399 aggressively used the RISBG instruction for immediate ANDs, both because it can handle some values that AND IMMEDIATE can't, and because it allows the destination register to be different from the source. I realized later while implementing the distinct-ops support that it would be better to leave the choice up to convertToThreeAddress() instead. The AND IMMEDIATE form is shorter and is less likely to be cracked. This is a problem for 32-bit ANDs because we assume that all 32-bit operations will leave the high word untouched, whereas RISBG used in this way will either clear the high word or copy it from the source register. The patch uses the z196 instruction RISBLG for this instead. This means that z10 will be restricted to NILL, NILH and NILF for 32-bit ANDs, but I think that should be OK for now. Although we're using z10 as the base architecture, the optimization work is going to be focused more on z196 and zEC12. llvm-svn: 187492
2013-07-31 19:36:35 +08:00
let isConvertibleToThreeAddress = 1 in {
// ANDs of a 16-bit immediate, leaving other bits unaffected.
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
// The CC result only reflects the 16-bit field, not the full register.
[SystemZ] Allow integer AND involving high words llvm-svn: 191762
2013-10-01 22:20:41 +08:00
//
// NIxMux expands to NI[LH]x, depending on the choice of register.
def NILMux : BinaryRIPseudo<and, GRX32, imm32ll16c>,
Requires<[FeatureHighWord]>;
def NIHMux : BinaryRIPseudo<and, GRX32, imm32lh16c>,
Requires<[FeatureHighWord]>;
[SystemZ] Define the GR64 low-word logic instructions as pseudo aliases. Another patch to avoid duplication of encoding information. Things like NILF, NILL and NILH are used as both 32-bit and 64-bit instructions. Here the 64-bit versions are defined as aliases of the 32-bit ones. llvm-svn: 191369
2013-09-25 19:11:53 +08:00
def NILL : BinaryRI<"nill", 0xA57, and, GR32, imm32ll16c>;
def NILH : BinaryRI<"nilh", 0xA56, and, GR32, imm32lh16c>;
[SystemZ] Allow integer AND involving high words llvm-svn: 191762
2013-10-01 22:20:41 +08:00
def NIHL : BinaryRI<"nihl", 0xA55, and, GRH32, imm32ll16c>;
def NIHH : BinaryRI<"nihh", 0xA54, and, GRH32, imm32lh16c>;
[SystemZ] Define the GR64 low-word logic instructions as pseudo aliases. Another patch to avoid duplication of encoding information. Things like NILF, NILL and NILH are used as both 32-bit and 64-bit instructions. Here the 64-bit versions are defined as aliases of the 32-bit ones. llvm-svn: 191369
2013-09-25 19:11:53 +08:00
def NILL64 : BinaryAliasRI<and, GR64, imm64ll16c>;
def NILH64 : BinaryAliasRI<and, GR64, imm64lh16c>;
[SystemZ] Allow integer AND involving high words llvm-svn: 191762
2013-10-01 22:20:41 +08:00
def NIHL64 : BinaryAliasRI<and, GR64, imm64hl16c>;
def NIHH64 : BinaryAliasRI<and, GR64, imm64hh16c>;
[SystemZ] Postpone NI->RISBG conversion to convertToThreeAddress() r186399 aggressively used the RISBG instruction for immediate ANDs, both because it can handle some values that AND IMMEDIATE can't, and because it allows the destination register to be different from the source. I realized later while implementing the distinct-ops support that it would be better to leave the choice up to convertToThreeAddress() instead. The AND IMMEDIATE form is shorter and is less likely to be cracked. This is a problem for 32-bit ANDs because we assume that all 32-bit operations will leave the high word untouched, whereas RISBG used in this way will either clear the high word or copy it from the source register. The patch uses the z196 instruction RISBLG for this instead. This means that z10 will be restricted to NILL, NILH and NILF for 32-bit ANDs, but I think that should be OK for now. Although we're using z10 as the base architecture, the optimization work is going to be focused more on z196 and zEC12. llvm-svn: 187492
2013-07-31 19:36:35 +08:00
// ANDs of a 32-bit immediate, leaving other bits unaffected.
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
// The CC result only reflects the 32-bit field, which means we can
// use it as a zero indicator for i32 operations but not otherwise.
[SystemZ] Allow integer AND involving high words llvm-svn: 191762
2013-10-01 22:20:41 +08:00
let CCValues = 0xC, CompareZeroCCMask = 0x8 in {
// Expands to NILF or NIHF, depending on the choice of register.
def NIFMux : BinaryRIPseudo<and, GRX32, uimm32>,
Requires<[FeatureHighWord]>;
[SystemZ] Define the GR64 low-word logic instructions as pseudo aliases. Another patch to avoid duplication of encoding information. Things like NILF, NILL and NILH are used as both 32-bit and 64-bit instructions. Here the 64-bit versions are defined as aliases of the 32-bit ones. llvm-svn: 191369
2013-09-25 19:11:53 +08:00
def NILF : BinaryRIL<"nilf", 0xC0B, and, GR32, uimm32>;
[SystemZ] Allow integer AND involving high words llvm-svn: 191762
2013-10-01 22:20:41 +08:00
def NIHF : BinaryRIL<"nihf", 0xC0A, and, GRH32, uimm32>;
}
[SystemZ] Define the GR64 low-word logic instructions as pseudo aliases. Another patch to avoid duplication of encoding information. Things like NILF, NILL and NILH are used as both 32-bit and 64-bit instructions. Here the 64-bit versions are defined as aliases of the 32-bit ones. llvm-svn: 191369
2013-09-25 19:11:53 +08:00
def NILF64 : BinaryAliasRIL<and, GR64, imm64lf32c>;
[SystemZ] Allow integer AND involving high words llvm-svn: 191762
2013-10-01 22:20:41 +08:00
def NIHF64 : BinaryAliasRIL<and, GR64, imm64hf32c>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
// ANDs of memory.
[SystemZ] Optimize floating-point comparisons with zero This follows the same lines as the integer code. In the end it seemed easier to have a second 4-bit mask in TSFlags to specify the compare-like CC values. That eats one more TSFlags bit than adding a CCHasUnordered would have done, but it feels more concise. llvm-svn: 187883
2013-08-07 19:10:06 +08:00
let CCValues = 0xC, CompareZeroCCMask = 0x8 in {
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
defm N : BinaryRXPair<"n", 0x54, 0xE354, and, GR32, load, 4>;
def NG : BinaryRXY<"ng", 0xE380, and, GR64, load, 8>;
}
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// AND to memory
[SystemZ] Avoid using i8 constants for immediate fields Immediate fields that have no natural MVT type tended to use i8 if the field was small enough. This was a bit confusing since i8 isn't a legal type for the target. Fields for short immediates in a 32-bit or 64-bit operation use i32 or i64 instead, so it would be better to do the same for all fields. No behavioral change intended. llvm-svn: 212702
2014-07-10 18:52:51 +08:00
defm NI : BinarySIPair<"ni", 0x94, 0xEB54, null_frag, imm32zx8>;
[SystemZ] Add NC, OC and XC For now these are just used to handle scalar ANDs, ORs and XORs in which all operands are memory. llvm-svn: 190041
2013-09-05 18:36:45 +08:00
// Block AND.
let mayLoad = 1, mayStore = 1 in
defm NC : MemorySS<"nc", 0xD4, z_nc, z_nc_loop>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
defm : RMWIByte<and, bdaddr12pair, NI>;
defm : RMWIByte<and, bdaddr20pair, NIY>;
//===----------------------------------------------------------------------===//
// OR
//===----------------------------------------------------------------------===//
[SystemZ] Rename PSW to CC Addresses a review comment from Ulrich Weigand. No functional change intended. I'm not sure whether the old TODO that this patch touches still holds, but that's something we'd get to when adding a targetted scheduling description. llvm-svn: 182474
2013-05-22 21:38:45 +08:00
let Defs = [CC] in {
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// ORs of a register.
[SystemZ] Optimize floating-point comparisons with zero This follows the same lines as the integer code. In the end it seemed easier to have a second 4-bit mask in TSFlags to specify the compare-like CC values. That eats one more TSFlags bit than adding a CCHasUnordered would have done, but it feels more concise. llvm-svn: 187883
2013-08-07 19:10:06 +08:00
let isCommutable = 1, CCValues = 0xC, CompareZeroCCMask = 0x8 in {
[SystemZ] Add NRK, ORK and XRK The atomic tests assume the two-operand forms, so I've restricted them to z10. Running and-01.ll, or-01.ll and xor-01.ll for z196 as well as z10 shows why using convertToThreeAddress() is better than exposing the three-operand forms first and then converting back to two operands where possible (which is what I'd originally tried). Using the three-operand form first stops us from taking advantage of NG, OG and XG for spills. llvm-svn: 186683
2013-07-20 00:21:55 +08:00
defm OR : BinaryRRAndK<"o", 0x16, 0xB9F6, or, GR32, GR32>;
[SystemZ] Add NGRK, OGRK and XGRK Like r186683, but for 64 bits. llvm-svn: 186685
2013-07-20 00:24:22 +08:00
defm OGR : BinaryRREAndK<"og", 0xB981, 0xB9E6, or, GR64, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
// ORs of a 16-bit immediate, leaving other bits unaffected.
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
// The CC result only reflects the 16-bit field, not the full register.
[SystemZ] Allow integer OR involving high words llvm-svn: 191755
2013-10-01 21:22:41 +08:00
//
// OIxMux expands to OI[LH]x, depending on the choice of register.
def OILMux : BinaryRIPseudo<or, GRX32, imm32ll16>,
Requires<[FeatureHighWord]>;
def OIHMux : BinaryRIPseudo<or, GRX32, imm32lh16>,
Requires<[FeatureHighWord]>;
[SystemZ] Define the GR64 low-word logic instructions as pseudo aliases. Another patch to avoid duplication of encoding information. Things like NILF, NILL and NILH are used as both 32-bit and 64-bit instructions. Here the 64-bit versions are defined as aliases of the 32-bit ones. llvm-svn: 191369
2013-09-25 19:11:53 +08:00
def OILL : BinaryRI<"oill", 0xA5B, or, GR32, imm32ll16>;
def OILH : BinaryRI<"oilh", 0xA5A, or, GR32, imm32lh16>;
[SystemZ] Allow integer OR involving high words llvm-svn: 191755
2013-10-01 21:22:41 +08:00
def OIHL : BinaryRI<"oihl", 0xA59, or, GRH32, imm32ll16>;
def OIHH : BinaryRI<"oihh", 0xA58, or, GRH32, imm32lh16>;
[SystemZ] Define the GR64 low-word logic instructions as pseudo aliases. Another patch to avoid duplication of encoding information. Things like NILF, NILL and NILH are used as both 32-bit and 64-bit instructions. Here the 64-bit versions are defined as aliases of the 32-bit ones. llvm-svn: 191369
2013-09-25 19:11:53 +08:00
def OILL64 : BinaryAliasRI<or, GR64, imm64ll16>;
def OILH64 : BinaryAliasRI<or, GR64, imm64lh16>;
[SystemZ] Allow integer OR involving high words llvm-svn: 191755
2013-10-01 21:22:41 +08:00
def OIHL64 : BinaryAliasRI<or, GR64, imm64hl16>;
def OIHH64 : BinaryAliasRI<or, GR64, imm64hh16>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// ORs of a 32-bit immediate, leaving other bits unaffected.
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
// The CC result only reflects the 32-bit field, which means we can
// use it as a zero indicator for i32 operations but not otherwise.
[SystemZ] Allow integer OR involving high words llvm-svn: 191755
2013-10-01 21:22:41 +08:00
let CCValues = 0xC, CompareZeroCCMask = 0x8 in {
// Expands to OILF or OIHF, depending on the choice of register.
def OIFMux : BinaryRIPseudo<or, GRX32, uimm32>,
Requires<[FeatureHighWord]>;
[SystemZ] Define the GR64 low-word logic instructions as pseudo aliases. Another patch to avoid duplication of encoding information. Things like NILF, NILL and NILH are used as both 32-bit and 64-bit instructions. Here the 64-bit versions are defined as aliases of the 32-bit ones. llvm-svn: 191369
2013-09-25 19:11:53 +08:00
def OILF : BinaryRIL<"oilf", 0xC0D, or, GR32, uimm32>;
[SystemZ] Allow integer OR involving high words llvm-svn: 191755
2013-10-01 21:22:41 +08:00
def OIHF : BinaryRIL<"oihf", 0xC0C, or, GRH32, uimm32>;
}
[SystemZ] Define the GR64 low-word logic instructions as pseudo aliases. Another patch to avoid duplication of encoding information. Things like NILF, NILL and NILH are used as both 32-bit and 64-bit instructions. Here the 64-bit versions are defined as aliases of the 32-bit ones. llvm-svn: 191369
2013-09-25 19:11:53 +08:00
def OILF64 : BinaryAliasRIL<or, GR64, imm64lf32>;
[SystemZ] Allow integer OR involving high words llvm-svn: 191755
2013-10-01 21:22:41 +08:00
def OIHF64 : BinaryAliasRIL<or, GR64, imm64hf32>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// ORs of memory.
[SystemZ] Optimize floating-point comparisons with zero This follows the same lines as the integer code. In the end it seemed easier to have a second 4-bit mask in TSFlags to specify the compare-like CC values. That eats one more TSFlags bit than adding a CCHasUnordered would have done, but it feels more concise. llvm-svn: 187883
2013-08-07 19:10:06 +08:00
let CCValues = 0xC, CompareZeroCCMask = 0x8 in {
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
defm O : BinaryRXPair<"o", 0x56, 0xE356, or, GR32, load, 4>;
def OG : BinaryRXY<"og", 0xE381, or, GR64, load, 8>;
}
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// OR to memory
[SystemZ] Avoid using i8 constants for immediate fields Immediate fields that have no natural MVT type tended to use i8 if the field was small enough. This was a bit confusing since i8 isn't a legal type for the target. Fields for short immediates in a 32-bit or 64-bit operation use i32 or i64 instead, so it would be better to do the same for all fields. No behavioral change intended. llvm-svn: 212702
2014-07-10 18:52:51 +08:00
defm OI : BinarySIPair<"oi", 0x96, 0xEB56, null_frag, imm32zx8>;
[SystemZ] Add NC, OC and XC For now these are just used to handle scalar ANDs, ORs and XORs in which all operands are memory. llvm-svn: 190041
2013-09-05 18:36:45 +08:00
// Block OR.
let mayLoad = 1, mayStore = 1 in
defm OC : MemorySS<"oc", 0xD6, z_oc, z_oc_loop>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
defm : RMWIByte<or, bdaddr12pair, OI>;
defm : RMWIByte<or, bdaddr20pair, OIY>;
//===----------------------------------------------------------------------===//
// XOR
//===----------------------------------------------------------------------===//
[SystemZ] Rename PSW to CC Addresses a review comment from Ulrich Weigand. No functional change intended. I'm not sure whether the old TODO that this patch touches still holds, but that's something we'd get to when adding a targetted scheduling description. llvm-svn: 182474
2013-05-22 21:38:45 +08:00
let Defs = [CC] in {
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// XORs of a register.
[SystemZ] Optimize floating-point comparisons with zero This follows the same lines as the integer code. In the end it seemed easier to have a second 4-bit mask in TSFlags to specify the compare-like CC values. That eats one more TSFlags bit than adding a CCHasUnordered would have done, but it feels more concise. llvm-svn: 187883
2013-08-07 19:10:06 +08:00
let isCommutable = 1, CCValues = 0xC, CompareZeroCCMask = 0x8 in {
[SystemZ] Add NRK, ORK and XRK The atomic tests assume the two-operand forms, so I've restricted them to z10. Running and-01.ll, or-01.ll and xor-01.ll for z196 as well as z10 shows why using convertToThreeAddress() is better than exposing the three-operand forms first and then converting back to two operands where possible (which is what I'd originally tried). Using the three-operand form first stops us from taking advantage of NG, OG and XG for spills. llvm-svn: 186683
2013-07-20 00:21:55 +08:00
defm XR : BinaryRRAndK<"x", 0x17, 0xB9F7, xor, GR32, GR32>;
[SystemZ] Add NGRK, OGRK and XGRK Like r186683, but for 64 bits. llvm-svn: 186685
2013-07-20 00:24:22 +08:00
defm XGR : BinaryRREAndK<"xg", 0xB982, 0xB9E7, xor, GR64, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
// XORs of a 32-bit immediate, leaving other bits unaffected.
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
// The CC result only reflects the 32-bit field, which means we can
// use it as a zero indicator for i32 operations but not otherwise.
[SystemZ] Allow integer XOR involving high words llvm-svn: 191759
2013-10-01 22:08:44 +08:00
let CCValues = 0xC, CompareZeroCCMask = 0x8 in {
// Expands to XILF or XIHF, depending on the choice of register.
def XIFMux : BinaryRIPseudo<xor, GRX32, uimm32>,
Requires<[FeatureHighWord]>;
[SystemZ] Define the GR64 low-word logic instructions as pseudo aliases. Another patch to avoid duplication of encoding information. Things like NILF, NILL and NILH are used as both 32-bit and 64-bit instructions. Here the 64-bit versions are defined as aliases of the 32-bit ones. llvm-svn: 191369
2013-09-25 19:11:53 +08:00
def XILF : BinaryRIL<"xilf", 0xC07, xor, GR32, uimm32>;
[SystemZ] Allow integer XOR involving high words llvm-svn: 191759
2013-10-01 22:08:44 +08:00
def XIHF : BinaryRIL<"xihf", 0xC06, xor, GRH32, uimm32>;
}
[SystemZ] Define the GR64 low-word logic instructions as pseudo aliases. Another patch to avoid duplication of encoding information. Things like NILF, NILL and NILH are used as both 32-bit and 64-bit instructions. Here the 64-bit versions are defined as aliases of the 32-bit ones. llvm-svn: 191369
2013-09-25 19:11:53 +08:00
def XILF64 : BinaryAliasRIL<xor, GR64, imm64lf32>;
[SystemZ] Allow integer XOR involving high words llvm-svn: 191759
2013-10-01 22:08:44 +08:00
def XIHF64 : BinaryAliasRIL<xor, GR64, imm64hf32>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// XORs of memory.
[SystemZ] Optimize floating-point comparisons with zero This follows the same lines as the integer code. In the end it seemed easier to have a second 4-bit mask in TSFlags to specify the compare-like CC values. That eats one more TSFlags bit than adding a CCHasUnordered would have done, but it feels more concise. llvm-svn: 187883
2013-08-07 19:10:06 +08:00
let CCValues = 0xC, CompareZeroCCMask = 0x8 in {
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
defm X : BinaryRXPair<"x",0x57, 0xE357, xor, GR32, load, 4>;
def XG : BinaryRXY<"xg", 0xE382, xor, GR64, load, 8>;
}
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// XOR to memory
[SystemZ] Avoid using i8 constants for immediate fields Immediate fields that have no natural MVT type tended to use i8 if the field was small enough. This was a bit confusing since i8 isn't a legal type for the target. Fields for short immediates in a 32-bit or 64-bit operation use i32 or i64 instead, so it would be better to do the same for all fields. No behavioral change intended. llvm-svn: 212702
2014-07-10 18:52:51 +08:00
defm XI : BinarySIPair<"xi", 0x97, 0xEB57, null_frag, imm32zx8>;
[SystemZ] Add NC, OC and XC For now these are just used to handle scalar ANDs, ORs and XORs in which all operands are memory. llvm-svn: 190041
2013-09-05 18:36:45 +08:00
// Block XOR.
let mayLoad = 1, mayStore = 1 in
defm XC : MemorySS<"xc", 0xD7, z_xc, z_xc_loop>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
defm : RMWIByte<xor, bdaddr12pair, XI>;
defm : RMWIByte<xor, bdaddr20pair, XIY>;
//===----------------------------------------------------------------------===//
// Multiplication
//===----------------------------------------------------------------------===//
// Multiplication of a register.
let isCommutable = 1 in {
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def MSR : BinaryRRE<"ms", 0xB252, mul, GR32, GR32>;
def MSGR : BinaryRRE<"msg", 0xB90C, mul, GR64, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def MSGFR : BinaryRRE<"msgf", 0xB91C, null_frag, GR64, GR32>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
defm : SXB<mul, GR64, MSGFR>;
// Multiplication of a signed 16-bit immediate.
def MHI : BinaryRI<"mhi", 0xA7C, mul, GR32, imm32sx16>;
def MGHI : BinaryRI<"mghi", 0xA7D, mul, GR64, imm64sx16>;
// Multiplication of a signed 32-bit immediate.
def MSFI : BinaryRIL<"msfi", 0xC21, mul, GR32, simm32>;
def MSGFI : BinaryRIL<"msgfi", 0xC20, mul, GR64, imm64sx32>;
// Multiplication of memory.
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
defm MH : BinaryRXPair<"mh", 0x4C, 0xE37C, mul, GR32, asextloadi16, 2>;
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
defm MS : BinaryRXPair<"ms", 0x71, 0xE351, mul, GR32, load, 4>;
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
def MSGF : BinaryRXY<"msgf", 0xE31C, mul, GR64, asextloadi32, 4>;
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def MSG : BinaryRXY<"msg", 0xE30C, mul, GR64, load, 8>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Multiplication of a register, producing two results.
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def MLGR : BinaryRRE<"mlg", 0xB986, z_umul_lohi64, GR128, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Multiplication of memory, producing two results.
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def MLG : BinaryRXY<"mlg", 0xE386, z_umul_lohi64, GR128, load, 8>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
//===----------------------------------------------------------------------===//
// Division and remainder
//===----------------------------------------------------------------------===//
// Division and remainder, from registers.
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def DSGFR : BinaryRRE<"dsgf", 0xB91D, z_sdivrem32, GR128, GR32>;
def DSGR : BinaryRRE<"dsg", 0xB90D, z_sdivrem64, GR128, GR64>;
def DLR : BinaryRRE<"dl", 0xB997, z_udivrem32, GR128, GR32>;
def DLGR : BinaryRRE<"dlg", 0xB987, z_udivrem64, GR128, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Division and remainder, from memory.
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def DSGF : BinaryRXY<"dsgf", 0xE31D, z_sdivrem32, GR128, load, 4>;
def DSG : BinaryRXY<"dsg", 0xE30D, z_sdivrem64, GR128, load, 8>;
def DL : BinaryRXY<"dl", 0xE397, z_udivrem32, GR128, load, 4>;
def DLG : BinaryRXY<"dlg", 0xE387, z_udivrem64, GR128, load, 8>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
//===----------------------------------------------------------------------===//
// Shifts
//===----------------------------------------------------------------------===//
// Shift left.
Replace neverHasSideEffects=1 with hasSideEffects=0 in all .td files. llvm-svn: 222801
2014-11-26 08:46:26 +08:00
let hasSideEffects = 0 in {
[SystemZ] Tweak instruction format classifications There's no real need to have Shift as a separate format type from Binary. The comments for other format types were too specific and in some cases no longer accurate. Just a clean-up, no behavioral change intended. llvm-svn: 212707
2014-07-10 19:29:23 +08:00
defm SLL : BinaryRSAndK<"sll", 0x89, 0xEBDF, shl, GR32>;
def SLLG : BinaryRSY<"sllg", 0xEB0D, shl, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
// Logical shift right.
Replace neverHasSideEffects=1 with hasSideEffects=0 in all .td files. llvm-svn: 222801
2014-11-26 08:46:26 +08:00
let hasSideEffects = 0 in {
[SystemZ] Tweak instruction format classifications There's no real need to have Shift as a separate format type from Binary. The comments for other format types were too specific and in some cases no longer accurate. Just a clean-up, no behavioral change intended. llvm-svn: 212707
2014-07-10 19:29:23 +08:00
defm SRL : BinaryRSAndK<"srl", 0x88, 0xEBDE, srl, GR32>;
def SRLG : BinaryRSY<"srlg", 0xEB0C, srl, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
// Arithmetic shift right.
[SystemZ] Optimize floating-point comparisons with zero This follows the same lines as the integer code. In the end it seemed easier to have a second 4-bit mask in TSFlags to specify the compare-like CC values. That eats one more TSFlags bit than adding a CCHasUnordered would have done, but it feels more concise. llvm-svn: 187883
2013-08-07 19:10:06 +08:00
let Defs = [CC], CCValues = 0xE, CompareZeroCCMask = 0xE in {
[SystemZ] Tweak instruction format classifications There's no real need to have Shift as a separate format type from Binary. The comments for other format types were too specific and in some cases no longer accurate. Just a clean-up, no behavioral change intended. llvm-svn: 212707
2014-07-10 19:29:23 +08:00
defm SRA : BinaryRSAndK<"sra", 0x8A, 0xEBDC, sra, GR32>;
def SRAG : BinaryRSY<"srag", 0xEB0A, sra, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
// Rotate left.
Replace neverHasSideEffects=1 with hasSideEffects=0 in all .td files. llvm-svn: 222801
2014-11-26 08:46:26 +08:00
let hasSideEffects = 0 in {
[SystemZ] Tweak instruction format classifications There's no real need to have Shift as a separate format type from Binary. The comments for other format types were too specific and in some cases no longer accurate. Just a clean-up, no behavioral change intended. llvm-svn: 212707
2014-07-10 19:29:23 +08:00
def RLL : BinaryRSY<"rll", 0xEB1D, rotl, GR32>;
def RLLG : BinaryRSY<"rllg", 0xEB1C, rotl, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
// Rotate second operand left and inserted selected bits into first operand.
// These can act like 32-bit operands provided that the constant start and
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
// end bits (operands 2 and 3) are in the range [32, 64).
[SystemZ] Rename PSW to CC Addresses a review comment from Ulrich Weigand. No functional change intended. I'm not sure whether the old TODO that this patch touches still holds, but that's something we'd get to when adding a targetted scheduling description. llvm-svn: 182474
2013-05-22 21:38:45 +08:00
let Defs = [CC] in {
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
let isCodeGenOnly = 1 in
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
def RISBG32 : RotateSelectRIEf<"risbg", 0xEC55, GR32, GR32>;
[SystemZ] Optimize floating-point comparisons with zero This follows the same lines as the integer code. In the end it seemed easier to have a second 4-bit mask in TSFlags to specify the compare-like CC values. That eats one more TSFlags bit than adding a CCHasUnordered would have done, but it feels more concise. llvm-svn: 187883
2013-08-07 19:10:06 +08:00
let CCValues = 0xE, CompareZeroCCMask = 0xE in
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
def RISBG : RotateSelectRIEf<"risbg", 0xEC55, GR64, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
[SystemZ] Support RISBGN instruction on zEC12 So far, we do not yet support any instruction specific to zEC12. Most of the facilities added with zEC12 are indeed not very useful to compiler code generation, but there is one exception: the miscellaneous-extensions facility provides the RISBGN instruction, which is a variant of RISBG that does not set the condition code. Add support for this facility, MC support for RISBGN, and CodeGen support for prefering RISBGN over RISBG on zEC12, unless we can actually make use of the condition code set by RISBG. llvm-svn: 233690
2015-03-31 20:58:17 +08:00
// On zEC12 we have a variant of RISBG that does not set CC.
let Predicates = [FeatureMiscellaneousExtensions] in
def RISBGN : RotateSelectRIEf<"risbgn", 0xEC59, GR64, GR64>;
[SystemZ] Add RISBLG and RISBHG instruction definitions The next patch will make use of RISBLG for codegen. llvm-svn: 187490
2013-07-31 19:17:35 +08:00
// Forms of RISBG that only affect one word of the destination register.
// They do not set CC.
[SystemZ] Use "let Predicates =" for blocks of new instructions ...instead of a separate Requires for each one. This style was already used in some places and seems more compact. No behavioral change intended. llvm-svn: 204452
2014-03-21 19:04:54 +08:00
let Predicates = [FeatureHighWord] in {
def RISBMux : RotateSelectRIEfPseudo<GRX32, GRX32>;
def RISBLL : RotateSelectAliasRIEf<GR32, GR32>;
def RISBLH : RotateSelectAliasRIEf<GR32, GRH32>;
def RISBHL : RotateSelectAliasRIEf<GRH32, GR32>;
def RISBHH : RotateSelectAliasRIEf<GRH32, GRH32>;
def RISBLG : RotateSelectRIEf<"risblg", 0xEC51, GR32, GR64>;
def RISBHG : RotateSelectRIEf<"risbhg", 0xEC5D, GRH32, GR64>;
}
[SystemZ] Add RISBLG and RISBHG instruction definitions The next patch will make use of RISBLG for codegen. llvm-svn: 187490
2013-07-31 19:17:35 +08:00
[SystemZ] Add MC support for R[NOX]SBG CodeGen support will come later. llvm-svn: 186401
2013-07-16 19:28:08 +08:00
// Rotate second operand left and perform a logical operation with selected
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
// bits of the first operand. The CC result only describes the selected bits,
// so isn't useful for a full comparison against zero.
[SystemZ] Add MC support for R[NOX]SBG CodeGen support will come later. llvm-svn: 186401
2013-07-16 19:28:08 +08:00
let Defs = [CC] in {
def RNSBG : RotateSelectRIEf<"rnsbg", 0xEC54, GR64, GR64>;
def ROSBG : RotateSelectRIEf<"rosbg", 0xEC56, GR64, GR64>;
def RXSBG : RotateSelectRIEf<"rxsbg", 0xEC57, GR64, GR64>;
}
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
//===----------------------------------------------------------------------===//
// Comparison
//===----------------------------------------------------------------------===//
[SystemZ] Tweak integer comparison code The architecture has many comparison instructions, including some that extend one of the operands. The signed comparison instructions use sign extensions and the unsigned comparison instructions use zero extensions. In cases where we had a free choice between signed or unsigned comparisons, we were trying to decide at lowering time which would best fit the available instructions, taking things like extension type into account. The code to do that was getting increasingly hairy and was also making some bad decisions. E.g. when comparing the result of two LLCs, it is better to use CR rather than CLR, since CR can be fused with a branch while CLR can't. This patch removes the lowering code and instead adds an operand to integer comparisons to say whether signed comparison is required, whether unsigned comparison is required, or whether either is OK. We can then leave the choice of instruction up to the normal isel code. llvm-svn: 190138
2013-09-06 19:51:39 +08:00
// Signed comparisons. We put these before the unsigned comparisons because
// some of the signed forms have COMPARE AND BRANCH equivalents whereas none
// of the unsigned forms do.
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
let Defs = [CC], CCValues = 0xE in {
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Comparison with a register.
[SystemZ] Tweak integer comparison code The architecture has many comparison instructions, including some that extend one of the operands. The signed comparison instructions use sign extensions and the unsigned comparison instructions use zero extensions. In cases where we had a free choice between signed or unsigned comparisons, we were trying to decide at lowering time which would best fit the available instructions, taking things like extension type into account. The code to do that was getting increasingly hairy and was also making some bad decisions. E.g. when comparing the result of two LLCs, it is better to use CR rather than CLR, since CR can be fused with a branch while CLR can't. This patch removes the lowering code and instead adds an operand to integer comparisons to say whether signed comparison is required, whether unsigned comparison is required, or whether either is OK. We can then leave the choice of instruction up to the normal isel code. llvm-svn: 190138
2013-09-06 19:51:39 +08:00
def CR : CompareRR <"c", 0x19, z_scmp, GR32, GR32>;
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def CGFR : CompareRRE<"cgf", 0xB930, null_frag, GR64, GR32>;
[SystemZ] Tweak integer comparison code The architecture has many comparison instructions, including some that extend one of the operands. The signed comparison instructions use sign extensions and the unsigned comparison instructions use zero extensions. In cases where we had a free choice between signed or unsigned comparisons, we were trying to decide at lowering time which would best fit the available instructions, taking things like extension type into account. The code to do that was getting increasingly hairy and was also making some bad decisions. E.g. when comparing the result of two LLCs, it is better to use CR rather than CLR, since CR can be fused with a branch while CLR can't. This patch removes the lowering code and instead adds an operand to integer comparisons to say whether signed comparison is required, whether unsigned comparison is required, or whether either is OK. We can then leave the choice of instruction up to the normal isel code. llvm-svn: 190138
2013-09-06 19:51:39 +08:00
def CGR : CompareRRE<"cg", 0xB920, z_scmp, GR64, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Comparison with a signed 16-bit immediate.
[SystemZ] Tweak integer comparison code The architecture has many comparison instructions, including some that extend one of the operands. The signed comparison instructions use sign extensions and the unsigned comparison instructions use zero extensions. In cases where we had a free choice between signed or unsigned comparisons, we were trying to decide at lowering time which would best fit the available instructions, taking things like extension type into account. The code to do that was getting increasingly hairy and was also making some bad decisions. E.g. when comparing the result of two LLCs, it is better to use CR rather than CLR, since CR can be fused with a branch while CLR can't. This patch removes the lowering code and instead adds an operand to integer comparisons to say whether signed comparison is required, whether unsigned comparison is required, or whether either is OK. We can then leave the choice of instruction up to the normal isel code. llvm-svn: 190138
2013-09-06 19:51:39 +08:00
def CHI : CompareRI<"chi", 0xA7E, z_scmp, GR32, imm32sx16>;
def CGHI : CompareRI<"cghi", 0xA7F, z_scmp, GR64, imm64sx16>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
[SystemZ] Add comparisons of large immediates using high words There are no corresponding patterns for small immediates because they would prevent the use of fused compare-and-branch instructions. llvm-svn: 191775
2013-10-01 22:56:23 +08:00
// Comparison with a signed 32-bit immediate. CFIMux expands to CFI or CIH,
// depending on the choice of register.
def CFIMux : CompareRIPseudo<z_scmp, GRX32, simm32>,
Requires<[FeatureHighWord]>;
[SystemZ] Tweak integer comparison code The architecture has many comparison instructions, including some that extend one of the operands. The signed comparison instructions use sign extensions and the unsigned comparison instructions use zero extensions. In cases where we had a free choice between signed or unsigned comparisons, we were trying to decide at lowering time which would best fit the available instructions, taking things like extension type into account. The code to do that was getting increasingly hairy and was also making some bad decisions. E.g. when comparing the result of two LLCs, it is better to use CR rather than CLR, since CR can be fused with a branch while CLR can't. This patch removes the lowering code and instead adds an operand to integer comparisons to say whether signed comparison is required, whether unsigned comparison is required, or whether either is OK. We can then leave the choice of instruction up to the normal isel code. llvm-svn: 190138
2013-09-06 19:51:39 +08:00
def CFI : CompareRIL<"cfi", 0xC2D, z_scmp, GR32, simm32>;
[SystemZ] Add comparisons of large immediates using high words There are no corresponding patterns for small immediates because they would prevent the use of fused compare-and-branch instructions. llvm-svn: 191775
2013-10-01 22:56:23 +08:00
def CIH : CompareRIL<"cih", 0xCCD, z_scmp, GRH32, simm32>,
Requires<[FeatureHighWord]>;
[SystemZ] Tweak integer comparison code The architecture has many comparison instructions, including some that extend one of the operands. The signed comparison instructions use sign extensions and the unsigned comparison instructions use zero extensions. In cases where we had a free choice between signed or unsigned comparisons, we were trying to decide at lowering time which would best fit the available instructions, taking things like extension type into account. The code to do that was getting increasingly hairy and was also making some bad decisions. E.g. when comparing the result of two LLCs, it is better to use CR rather than CLR, since CR can be fused with a branch while CLR can't. This patch removes the lowering code and instead adds an operand to integer comparisons to say whether signed comparison is required, whether unsigned comparison is required, or whether either is OK. We can then leave the choice of instruction up to the normal isel code. llvm-svn: 190138
2013-09-06 19:51:39 +08:00
def CGFI : CompareRIL<"cgfi", 0xC2C, z_scmp, GR64, imm64sx32>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Comparison with memory.
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
defm CH : CompareRXPair<"ch", 0x49, 0xE379, z_scmp, GR32, asextloadi16, 2>;
[SystemZ] Add comparisons of high words and memory llvm-svn: 191777
2013-10-01 23:00:44 +08:00
def CMux : CompareRXYPseudo<z_scmp, GRX32, load, 4>,
Requires<[FeatureHighWord]>;
[SystemZ] Tweak integer comparison code The architecture has many comparison instructions, including some that extend one of the operands. The signed comparison instructions use sign extensions and the unsigned comparison instructions use zero extensions. In cases where we had a free choice between signed or unsigned comparisons, we were trying to decide at lowering time which would best fit the available instructions, taking things like extension type into account. The code to do that was getting increasingly hairy and was also making some bad decisions. E.g. when comparing the result of two LLCs, it is better to use CR rather than CLR, since CR can be fused with a branch while CLR can't. This patch removes the lowering code and instead adds an operand to integer comparisons to say whether signed comparison is required, whether unsigned comparison is required, or whether either is OK. We can then leave the choice of instruction up to the normal isel code. llvm-svn: 190138
2013-09-06 19:51:39 +08:00
defm C : CompareRXPair<"c", 0x59, 0xE359, z_scmp, GR32, load, 4>;
[SystemZ] Add comparisons of high words and memory llvm-svn: 191777
2013-10-01 23:00:44 +08:00
def CHF : CompareRXY<"chf", 0xE3CD, z_scmp, GRH32, load, 4>,
Requires<[FeatureHighWord]>;
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
def CGH : CompareRXY<"cgh", 0xE334, z_scmp, GR64, asextloadi16, 2>;
def CGF : CompareRXY<"cgf", 0xE330, z_scmp, GR64, asextloadi32, 4>;
[SystemZ] Tweak integer comparison code The architecture has many comparison instructions, including some that extend one of the operands. The signed comparison instructions use sign extensions and the unsigned comparison instructions use zero extensions. In cases where we had a free choice between signed or unsigned comparisons, we were trying to decide at lowering time which would best fit the available instructions, taking things like extension type into account. The code to do that was getting increasingly hairy and was also making some bad decisions. E.g. when comparing the result of two LLCs, it is better to use CR rather than CLR, since CR can be fused with a branch while CLR can't. This patch removes the lowering code and instead adds an operand to integer comparisons to say whether signed comparison is required, whether unsigned comparison is required, or whether either is OK. We can then leave the choice of instruction up to the normal isel code. llvm-svn: 190138
2013-09-06 19:51:39 +08:00
def CG : CompareRXY<"cg", 0xE320, z_scmp, GR64, load, 8>;
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
def CHRL : CompareRILPC<"chrl", 0xC65, z_scmp, GR32, aligned_asextloadi16>;
[SystemZ] Tweak integer comparison code The architecture has many comparison instructions, including some that extend one of the operands. The signed comparison instructions use sign extensions and the unsigned comparison instructions use zero extensions. In cases where we had a free choice between signed or unsigned comparisons, we were trying to decide at lowering time which would best fit the available instructions, taking things like extension type into account. The code to do that was getting increasingly hairy and was also making some bad decisions. E.g. when comparing the result of two LLCs, it is better to use CR rather than CLR, since CR can be fused with a branch while CLR can't. This patch removes the lowering code and instead adds an operand to integer comparisons to say whether signed comparison is required, whether unsigned comparison is required, or whether either is OK. We can then leave the choice of instruction up to the normal isel code. llvm-svn: 190138
2013-09-06 19:51:39 +08:00
def CRL : CompareRILPC<"crl", 0xC6D, z_scmp, GR32, aligned_load>;
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
def CGHRL : CompareRILPC<"cghrl", 0xC64, z_scmp, GR64, aligned_asextloadi16>;
def CGFRL : CompareRILPC<"cgfrl", 0xC6C, z_scmp, GR64, aligned_asextloadi32>;
[SystemZ] Tweak integer comparison code The architecture has many comparison instructions, including some that extend one of the operands. The signed comparison instructions use sign extensions and the unsigned comparison instructions use zero extensions. In cases where we had a free choice between signed or unsigned comparisons, we were trying to decide at lowering time which would best fit the available instructions, taking things like extension type into account. The code to do that was getting increasingly hairy and was also making some bad decisions. E.g. when comparing the result of two LLCs, it is better to use CR rather than CLR, since CR can be fused with a branch while CLR can't. This patch removes the lowering code and instead adds an operand to integer comparisons to say whether signed comparison is required, whether unsigned comparison is required, or whether either is OK. We can then leave the choice of instruction up to the normal isel code. llvm-svn: 190138
2013-09-06 19:51:39 +08:00
def CGRL : CompareRILPC<"cgrl", 0xC68, z_scmp, GR64, aligned_load>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Comparison between memory and a signed 16-bit immediate.
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
def CHHSI : CompareSIL<"chhsi", 0xE554, z_scmp, asextloadi16, imm32sx16>;
def CHSI : CompareSIL<"chsi", 0xE55C, z_scmp, load, imm32sx16>;
def CGHSI : CompareSIL<"cghsi", 0xE558, z_scmp, load, imm64sx16>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
[SystemZ] Tweak integer comparison code The architecture has many comparison instructions, including some that extend one of the operands. The signed comparison instructions use sign extensions and the unsigned comparison instructions use zero extensions. In cases where we had a free choice between signed or unsigned comparisons, we were trying to decide at lowering time which would best fit the available instructions, taking things like extension type into account. The code to do that was getting increasingly hairy and was also making some bad decisions. E.g. when comparing the result of two LLCs, it is better to use CR rather than CLR, since CR can be fused with a branch while CLR can't. This patch removes the lowering code and instead adds an operand to integer comparisons to say whether signed comparison is required, whether unsigned comparison is required, or whether either is OK. We can then leave the choice of instruction up to the normal isel code. llvm-svn: 190138
2013-09-06 19:51:39 +08:00
defm : SXB<z_scmp, GR64, CGFR>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Unsigned comparisons.
[SystemZ] Reuse CC results for integer comparisons with zero This also fixes a bug in the predication of LR to LOCR: I'd forgotten that with these in-place instruction builds, the implicit operands need to be added manually. I think this was latent until now, but is tested by int-cmp-45.c. It also adds a CC valid mask to STOC, again tested by int-cmp-45.c. llvm-svn: 187573
2013-08-01 18:39:40 +08:00
let Defs = [CC], CCValues = 0xE, IsLogical = 1 in {
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Comparison with a register.
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def CLR : CompareRR <"cl", 0x15, z_ucmp, GR32, GR32>;
def CLGFR : CompareRRE<"clgf", 0xB931, null_frag, GR64, GR32>;
def CLGR : CompareRRE<"clg", 0xB921, z_ucmp, GR64, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
[SystemZ] Add comparisons of large immediates using high words There are no corresponding patterns for small immediates because they would prevent the use of fused compare-and-branch instructions. llvm-svn: 191775
2013-10-01 22:56:23 +08:00
// Comparison with an unsigned 32-bit immediate. CLFIMux expands to CLFI
// or CLIH, depending on the choice of register.
def CLFIMux : CompareRIPseudo<z_ucmp, GRX32, uimm32>,
Requires<[FeatureHighWord]>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
def CLFI : CompareRIL<"clfi", 0xC2F, z_ucmp, GR32, uimm32>;
[SystemZ] Add comparisons of large immediates using high words There are no corresponding patterns for small immediates because they would prevent the use of fused compare-and-branch instructions. llvm-svn: 191775
2013-10-01 22:56:23 +08:00
def CLIH : CompareRIL<"clih", 0xCCF, z_ucmp, GR32, uimm32>,
Requires<[FeatureHighWord]>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
def CLGFI : CompareRIL<"clgfi", 0xC2E, z_ucmp, GR64, imm64zx32>;
// Comparison with memory.
[SystemZ] Add comparisons of high words and memory llvm-svn: 191777
2013-10-01 23:00:44 +08:00
def CLMux : CompareRXYPseudo<z_ucmp, GRX32, load, 4>,
Requires<[FeatureHighWord]>;
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
defm CL : CompareRXPair<"cl", 0x55, 0xE355, z_ucmp, GR32, load, 4>;
[SystemZ] Add comparisons of high words and memory llvm-svn: 191777
2013-10-01 23:00:44 +08:00
def CLHF : CompareRXY<"clhf", 0xE3CF, z_ucmp, GRH32, load, 4>,
Requires<[FeatureHighWord]>;
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
def CLGF : CompareRXY<"clgf", 0xE331, z_ucmp, GR64, azextloadi32, 4>;
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def CLG : CompareRXY<"clg", 0xE321, z_ucmp, GR64, load, 8>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
def CLHRL : CompareRILPC<"clhrl", 0xC67, z_ucmp, GR32,
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
aligned_azextloadi16>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
def CLRL : CompareRILPC<"clrl", 0xC6F, z_ucmp, GR32,
aligned_load>;
def CLGHRL : CompareRILPC<"clghrl", 0xC66, z_ucmp, GR64,
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
aligned_azextloadi16>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
def CLGFRL : CompareRILPC<"clgfrl", 0xC6E, z_ucmp, GR64,
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
aligned_azextloadi32>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
def CLGRL : CompareRILPC<"clgrl", 0xC6A, z_ucmp, GR64,
aligned_load>;
// Comparison between memory and an unsigned 8-bit immediate.
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
defm CLI : CompareSIPair<"cli", 0x95, 0xEB55, z_ucmp, azextloadi8, imm32zx8>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Comparison between memory and an unsigned 16-bit immediate.
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
def CLHHSI : CompareSIL<"clhhsi", 0xE555, z_ucmp, azextloadi16, imm32zx16>;
def CLFHSI : CompareSIL<"clfhsi", 0xE55D, z_ucmp, load, imm32zx16>;
def CLGHSI : CompareSIL<"clghsi", 0xE559, z_ucmp, load, imm64zx16>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
defm : ZXB<z_ucmp, GR64, CLGFR>;
[SystemZ] Add a definition of the CLC instruction llvm-svn: 188162
2013-08-12 18:17:33 +08:00
// Memory-to-memory comparison.
let mayLoad = 1, Defs = [CC] in
[SystemZ] Extend memcpy and memset support to all constant lengths Lengths up to a certain threshold (currently 6 * 256) use a series of MVCs. Lengths above that threshold use a loop to handle X*256 bytes followed by a single MVC to handle the excess (if any). This loop will also be needed in future when support for variable lengths is added. Because the same tablegen classes are used to define MVC and CLC, the patch also has the side-effect of defining a pseudo loop instruction for CLC. That instruction isn't used yet (and wouldn't be handled correctly if it were). I'm planning to use it soon though. llvm-svn: 189331
2013-08-27 17:54:29 +08:00
defm CLC : MemorySS<"clc", 0xD5, z_clc, z_clc_loop>;
[SystemZ] Add a definition of the CLC instruction llvm-svn: 188162
2013-08-12 18:17:33 +08:00
[SystemZ] Use CLST to implement strcmp llvm-svn: 188544
2013-08-16 19:21:54 +08:00
// String comparison.
[SystemZ] Rename 32-bit GPR registers I'm about to add support for high-word operations, so it seemed better for the low-word registers to have names like R0L rather than R0W. No behavioral change intended. llvm-svn: 191655
2013-09-30 16:48:38 +08:00
let mayLoad = 1, Defs = [CC], Uses = [R0L] in
[SystemZ] Use CLST to implement strcmp llvm-svn: 188544
2013-08-16 19:21:54 +08:00
defm CLST : StringRRE<"clst", 0xB25D, z_strcmp>;
[SystemZ] Add support for TMHH, TMHL, TMLH and TMLL For now just handles simple comparisons of an ANDed value with zero. The CC value provides enough information to do any comparison for a 2-bit mask, and some nonzero comparisons with more populated masks, but that's all future work. llvm-svn: 189469
2013-08-28 18:31:43 +08:00
// Test under mask.
let Defs = [CC] in {
[SystemZ] Extend test-under-mask support to high GR32s llvm-svn: 191773
2013-10-01 22:41:52 +08:00
// TMxMux expands to TM[LH]x, depending on the choice of register.
def TMLMux : CompareRIPseudo<z_tm_reg, GRX32, imm32ll16>,
Requires<[FeatureHighWord]>;
def TMHMux : CompareRIPseudo<z_tm_reg, GRX32, imm32lh16>,
Requires<[FeatureHighWord]>;
[SystemZ] Define the GR64 low-word logic instructions as pseudo aliases. Another patch to avoid duplication of encoding information. Things like NILF, NILL and NILH are used as both 32-bit and 64-bit instructions. Here the 64-bit versions are defined as aliases of the 32-bit ones. llvm-svn: 191369
2013-09-25 19:11:53 +08:00
def TMLL : CompareRI<"tmll", 0xA71, z_tm_reg, GR32, imm32ll16>;
def TMLH : CompareRI<"tmlh", 0xA70, z_tm_reg, GR32, imm32lh16>;
[SystemZ] Extend test-under-mask support to high GR32s llvm-svn: 191773
2013-10-01 22:41:52 +08:00
def TMHL : CompareRI<"tmhl", 0xA73, z_tm_reg, GRH32, imm32ll16>;
def TMHH : CompareRI<"tmhh", 0xA72, z_tm_reg, GRH32, imm32lh16>;
[SystemZ] Add TM and TMY The main complication here is that TM and TMY (the memory forms) set CC differently from the register forms. When the tested bits contain some 0s and some 1s, the register forms set CC to 1 or 2 based on the value the uppermost bit. The memory forms instead set CC to 1 regardless of the uppermost bit. Until now, I've tried to make it so that a branch never tests for an impossible CC value. E.g. NR only sets CC to 0 or 1, so branches on the result will only test for 0 or 1. Originally I'd tried to do the same thing for TM and TMY by using custom matching code in ISelDAGToDAG. That ended up being very ugly though, and would have meant duplicating some of the chain checks that the common isel code does. I've therefore gone for the simpler alternative of adding an extra operand to the TM DAG opcode to say whether a memory form would be OK. This means that the inverse of a "TM;JE" is "TM;JNE" rather than the more precise "TM;JNLE", just like the inverse of "TMLL;JE" is "TMLL;JNE". I suppose that's arguably less confusing though... llvm-svn: 190400
2013-09-10 18:20:32 +08:00
[SystemZ] Fix TMHH and TMHL usage for z10 with -O0 I've no idea why I decided to handle TMxx differently from all the other high/low logic operations, but it was a stupid thing to do. The high registers aren't available as separate 32-bit registers on z10, so subreg_h32 can't be used on a GR64 there. I've normally been testing with z196 and with -O3 and so hadn't noticed this until now. llvm-svn: 195473
2013-11-23 01:28:28 +08:00
def TMLL64 : CompareAliasRI<z_tm_reg, GR64, imm64ll16>;
def TMLH64 : CompareAliasRI<z_tm_reg, GR64, imm64lh16>;
def TMHL64 : CompareAliasRI<z_tm_reg, GR64, imm64hl16>;
def TMHH64 : CompareAliasRI<z_tm_reg, GR64, imm64hh16>;
[SystemZ] Add TM and TMY The main complication here is that TM and TMY (the memory forms) set CC differently from the register forms. When the tested bits contain some 0s and some 1s, the register forms set CC to 1 or 2 based on the value the uppermost bit. The memory forms instead set CC to 1 regardless of the uppermost bit. Until now, I've tried to make it so that a branch never tests for an impossible CC value. E.g. NR only sets CC to 0 or 1, so branches on the result will only test for 0 or 1. Originally I'd tried to do the same thing for TM and TMY by using custom matching code in ISelDAGToDAG. That ended up being very ugly though, and would have meant duplicating some of the chain checks that the common isel code does. I've therefore gone for the simpler alternative of adding an extra operand to the TM DAG opcode to say whether a memory form would be OK. This means that the inverse of a "TM;JE" is "TM;JNE" rather than the more precise "TM;JNLE", just like the inverse of "TMLL;JE" is "TMLL;JNE". I suppose that's arguably less confusing though... llvm-svn: 190400
2013-09-10 18:20:32 +08:00
defm TM : CompareSIPair<"tm", 0x91, 0xEB51, z_tm_mem, anyextloadi8, imm32zx8>;
[SystemZ] Add support for TMHH, TMHL, TMLH and TMLL For now just handles simple comparisons of an ANDed value with zero. The CC value provides enough information to do any comparison for a 2-bit mask, and some nonzero comparisons with more populated masks, but that's all future work. llvm-svn: 189469
2013-08-28 18:31:43 +08:00
}
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
//===----------------------------------------------------------------------===//
[SystemZ] Add basic prefetch support Just the instructions and intrinsics for now. llvm-svn: 189100
2013-08-23 19:36:42 +08:00
// Prefetch
//===----------------------------------------------------------------------===//
def PFD : PrefetchRXY<"pfd", 0xE336, z_prefetch>;
def PFDRL : PrefetchRILPC<"pfdrl", 0xC62, z_prefetch>;
//===----------------------------------------------------------------------===//
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Atomic operations
//===----------------------------------------------------------------------===//
Add TargetLowering::prepareVolatileOrAtomicLoad One unusual feature of the z architecture is that the result of a previous load can be reused indefinitely for subsequent loads, even if a cache-coherent store to that location is performed by another CPU. A special serializing instruction must be used if you want to force a load to be reattempted. Since volatile loads are not supposed to be omitted in this way, we should insert a serializing instruction before each such load. The same goes for atomic loads. The patch implements this at the IR->DAG boundary, in a similar way to atomic fences. It is a no-op for targets other than SystemZ. llvm-svn: 196905
2013-12-10 18:36:34 +08:00
def Serialize : Alias<2, (outs), (ins), [(z_serialize)]>;
[SystemZ] Add MC support for interlocked-access 1 instructions llvm-svn: 197984
2013-12-24 23:14:05 +08:00
let Predicates = [FeatureInterlockedAccess1], Defs = [CC] in {
[SystemZ] Use interlocked-access 1 instructions for CodeGen ...namely LOAD AND ADD, LOAD AND AND, LOAD AND OR and LOAD AND EXCLUSIVE OR. LOAD AND ADD LOGICAL isn't really separately useful for LLVM. I'll look at adding reusing the CC results in new year. llvm-svn: 197985
2013-12-24 23:18:04 +08:00
def LAA : LoadAndOpRSY<"laa", 0xEBF8, atomic_load_add_32, GR32>;
def LAAG : LoadAndOpRSY<"laag", 0xEBE8, atomic_load_add_64, GR64>;
[SystemZ] Add MC support for interlocked-access 1 instructions llvm-svn: 197984
2013-12-24 23:14:05 +08:00
def LAAL : LoadAndOpRSY<"laal", 0xEBFA, null_frag, GR32>;
def LAALG : LoadAndOpRSY<"laalg", 0xEBEA, null_frag, GR64>;
[SystemZ] Use interlocked-access 1 instructions for CodeGen ...namely LOAD AND ADD, LOAD AND AND, LOAD AND OR and LOAD AND EXCLUSIVE OR. LOAD AND ADD LOGICAL isn't really separately useful for LLVM. I'll look at adding reusing the CC results in new year. llvm-svn: 197985
2013-12-24 23:18:04 +08:00
def LAN : LoadAndOpRSY<"lan", 0xEBF4, atomic_load_and_32, GR32>;
def LANG : LoadAndOpRSY<"lang", 0xEBE4, atomic_load_and_64, GR64>;
def LAO : LoadAndOpRSY<"lao", 0xEBF6, atomic_load_or_32, GR32>;
def LAOG : LoadAndOpRSY<"laog", 0xEBE6, atomic_load_or_64, GR64>;
def LAX : LoadAndOpRSY<"lax", 0xEBF7, atomic_load_xor_32, GR32>;
def LAXG : LoadAndOpRSY<"laxg", 0xEBE7, atomic_load_xor_64, GR64>;
[SystemZ] Add MC support for interlocked-access 1 instructions llvm-svn: 197984
2013-12-24 23:14:05 +08:00
}
[SystemZ] Use interlocked-access 1 instructions for CodeGen ...namely LOAD AND ADD, LOAD AND AND, LOAD AND OR and LOAD AND EXCLUSIVE OR. LOAD AND ADD LOGICAL isn't really separately useful for LLVM. I'll look at adding reusing the CC results in new year. llvm-svn: 197985
2013-12-24 23:18:04 +08:00
def ATOMIC_SWAPW : AtomicLoadWBinaryReg<z_atomic_swapw>;
def ATOMIC_SWAP_32 : AtomicLoadBinaryReg32<atomic_swap_32>;
def ATOMIC_SWAP_64 : AtomicLoadBinaryReg64<atomic_swap_64>;
def ATOMIC_LOADW_AR : AtomicLoadWBinaryReg<z_atomic_loadw_add>;
def ATOMIC_LOADW_AFI : AtomicLoadWBinaryImm<z_atomic_loadw_add, simm32>;
let Predicates = [FeatureNoInterlockedAccess1] in {
def ATOMIC_LOAD_AR : AtomicLoadBinaryReg32<atomic_load_add_32>;
def ATOMIC_LOAD_AHI : AtomicLoadBinaryImm32<atomic_load_add_32, imm32sx16>;
def ATOMIC_LOAD_AFI : AtomicLoadBinaryImm32<atomic_load_add_32, simm32>;
def ATOMIC_LOAD_AGR : AtomicLoadBinaryReg64<atomic_load_add_64>;
def ATOMIC_LOAD_AGHI : AtomicLoadBinaryImm64<atomic_load_add_64, imm64sx16>;
def ATOMIC_LOAD_AGFI : AtomicLoadBinaryImm64<atomic_load_add_64, imm64sx32>;
}
def ATOMIC_LOADW_SR : AtomicLoadWBinaryReg<z_atomic_loadw_sub>;
def ATOMIC_LOAD_SR : AtomicLoadBinaryReg32<atomic_load_sub_32>;
def ATOMIC_LOAD_SGR : AtomicLoadBinaryReg64<atomic_load_sub_64>;
def ATOMIC_LOADW_NR : AtomicLoadWBinaryReg<z_atomic_loadw_and>;
def ATOMIC_LOADW_NILH : AtomicLoadWBinaryImm<z_atomic_loadw_and, imm32lh16c>;
let Predicates = [FeatureNoInterlockedAccess1] in {
def ATOMIC_LOAD_NR : AtomicLoadBinaryReg32<atomic_load_and_32>;
def ATOMIC_LOAD_NILL : AtomicLoadBinaryImm32<atomic_load_and_32,
imm32ll16c>;
def ATOMIC_LOAD_NILH : AtomicLoadBinaryImm32<atomic_load_and_32,
imm32lh16c>;
def ATOMIC_LOAD_NILF : AtomicLoadBinaryImm32<atomic_load_and_32, uimm32>;
def ATOMIC_LOAD_NGR : AtomicLoadBinaryReg64<atomic_load_and_64>;
def ATOMIC_LOAD_NILL64 : AtomicLoadBinaryImm64<atomic_load_and_64,
imm64ll16c>;
def ATOMIC_LOAD_NILH64 : AtomicLoadBinaryImm64<atomic_load_and_64,
imm64lh16c>;
def ATOMIC_LOAD_NIHL64 : AtomicLoadBinaryImm64<atomic_load_and_64,
imm64hl16c>;
def ATOMIC_LOAD_NIHH64 : AtomicLoadBinaryImm64<atomic_load_and_64,
imm64hh16c>;
def ATOMIC_LOAD_NILF64 : AtomicLoadBinaryImm64<atomic_load_and_64,
imm64lf32c>;
def ATOMIC_LOAD_NIHF64 : AtomicLoadBinaryImm64<atomic_load_and_64,
imm64hf32c>;
}
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
def ATOMIC_LOADW_OR : AtomicLoadWBinaryReg<z_atomic_loadw_or>;
def ATOMIC_LOADW_OILH : AtomicLoadWBinaryImm<z_atomic_loadw_or, imm32lh16>;
[SystemZ] Use interlocked-access 1 instructions for CodeGen ...namely LOAD AND ADD, LOAD AND AND, LOAD AND OR and LOAD AND EXCLUSIVE OR. LOAD AND ADD LOGICAL isn't really separately useful for LLVM. I'll look at adding reusing the CC results in new year. llvm-svn: 197985
2013-12-24 23:18:04 +08:00
let Predicates = [FeatureNoInterlockedAccess1] in {
def ATOMIC_LOAD_OR : AtomicLoadBinaryReg32<atomic_load_or_32>;
def ATOMIC_LOAD_OILL : AtomicLoadBinaryImm32<atomic_load_or_32, imm32ll16>;
def ATOMIC_LOAD_OILH : AtomicLoadBinaryImm32<atomic_load_or_32, imm32lh16>;
def ATOMIC_LOAD_OILF : AtomicLoadBinaryImm32<atomic_load_or_32, uimm32>;
def ATOMIC_LOAD_OGR : AtomicLoadBinaryReg64<atomic_load_or_64>;
def ATOMIC_LOAD_OILL64 : AtomicLoadBinaryImm64<atomic_load_or_64, imm64ll16>;
def ATOMIC_LOAD_OILH64 : AtomicLoadBinaryImm64<atomic_load_or_64, imm64lh16>;
def ATOMIC_LOAD_OIHL64 : AtomicLoadBinaryImm64<atomic_load_or_64, imm64hl16>;
def ATOMIC_LOAD_OIHH64 : AtomicLoadBinaryImm64<atomic_load_or_64, imm64hh16>;
def ATOMIC_LOAD_OILF64 : AtomicLoadBinaryImm64<atomic_load_or_64, imm64lf32>;
def ATOMIC_LOAD_OIHF64 : AtomicLoadBinaryImm64<atomic_load_or_64, imm64hf32>;
}
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
def ATOMIC_LOADW_XR : AtomicLoadWBinaryReg<z_atomic_loadw_xor>;
def ATOMIC_LOADW_XILF : AtomicLoadWBinaryImm<z_atomic_loadw_xor, uimm32>;
[SystemZ] Use interlocked-access 1 instructions for CodeGen ...namely LOAD AND ADD, LOAD AND AND, LOAD AND OR and LOAD AND EXCLUSIVE OR. LOAD AND ADD LOGICAL isn't really separately useful for LLVM. I'll look at adding reusing the CC results in new year. llvm-svn: 197985
2013-12-24 23:18:04 +08:00
let Predicates = [FeatureNoInterlockedAccess1] in {
def ATOMIC_LOAD_XR : AtomicLoadBinaryReg32<atomic_load_xor_32>;
def ATOMIC_LOAD_XILF : AtomicLoadBinaryImm32<atomic_load_xor_32, uimm32>;
def ATOMIC_LOAD_XGR : AtomicLoadBinaryReg64<atomic_load_xor_64>;
def ATOMIC_LOAD_XILF64 : AtomicLoadBinaryImm64<atomic_load_xor_64, imm64lf32>;
def ATOMIC_LOAD_XIHF64 : AtomicLoadBinaryImm64<atomic_load_xor_64, imm64hf32>;
}
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
def ATOMIC_LOADW_NRi : AtomicLoadWBinaryReg<z_atomic_loadw_nand>;
def ATOMIC_LOADW_NILHi : AtomicLoadWBinaryImm<z_atomic_loadw_nand,
imm32lh16c>;
def ATOMIC_LOAD_NRi : AtomicLoadBinaryReg32<atomic_load_nand_32>;
[SystemZ] Define the GR64 low-word logic instructions as pseudo aliases. Another patch to avoid duplication of encoding information. Things like NILF, NILL and NILH are used as both 32-bit and 64-bit instructions. Here the 64-bit versions are defined as aliases of the 32-bit ones. llvm-svn: 191369
2013-09-25 19:11:53 +08:00
def ATOMIC_LOAD_NILLi : AtomicLoadBinaryImm32<atomic_load_nand_32,
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
imm32ll16c>;
[SystemZ] Define the GR64 low-word logic instructions as pseudo aliases. Another patch to avoid duplication of encoding information. Things like NILF, NILL and NILH are used as both 32-bit and 64-bit instructions. Here the 64-bit versions are defined as aliases of the 32-bit ones. llvm-svn: 191369
2013-09-25 19:11:53 +08:00
def ATOMIC_LOAD_NILHi : AtomicLoadBinaryImm32<atomic_load_nand_32,
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
imm32lh16c>;
[SystemZ] Define the GR64 low-word logic instructions as pseudo aliases. Another patch to avoid duplication of encoding information. Things like NILF, NILL and NILH are used as both 32-bit and 64-bit instructions. Here the 64-bit versions are defined as aliases of the 32-bit ones. llvm-svn: 191369
2013-09-25 19:11:53 +08:00
def ATOMIC_LOAD_NILFi : AtomicLoadBinaryImm32<atomic_load_nand_32, uimm32>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
def ATOMIC_LOAD_NGRi : AtomicLoadBinaryReg64<atomic_load_nand_64>;
[SystemZ] Define the GR64 low-word logic instructions as pseudo aliases. Another patch to avoid duplication of encoding information. Things like NILF, NILL and NILH are used as both 32-bit and 64-bit instructions. Here the 64-bit versions are defined as aliases of the 32-bit ones. llvm-svn: 191369
2013-09-25 19:11:53 +08:00
def ATOMIC_LOAD_NILL64i : AtomicLoadBinaryImm64<atomic_load_nand_64,
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
imm64ll16c>;
[SystemZ] Define the GR64 low-word logic instructions as pseudo aliases. Another patch to avoid duplication of encoding information. Things like NILF, NILL and NILH are used as both 32-bit and 64-bit instructions. Here the 64-bit versions are defined as aliases of the 32-bit ones. llvm-svn: 191369
2013-09-25 19:11:53 +08:00
def ATOMIC_LOAD_NILH64i : AtomicLoadBinaryImm64<atomic_load_nand_64,
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
imm64lh16c>;
[SystemZ] Allow integer AND involving high words llvm-svn: 191762
2013-10-01 22:20:41 +08:00
def ATOMIC_LOAD_NIHL64i : AtomicLoadBinaryImm64<atomic_load_nand_64,
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
imm64hl16c>;
[SystemZ] Allow integer AND involving high words llvm-svn: 191762
2013-10-01 22:20:41 +08:00
def ATOMIC_LOAD_NIHH64i : AtomicLoadBinaryImm64<atomic_load_nand_64,
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
imm64hh16c>;
[SystemZ] Define the GR64 low-word logic instructions as pseudo aliases. Another patch to avoid duplication of encoding information. Things like NILF, NILL and NILH are used as both 32-bit and 64-bit instructions. Here the 64-bit versions are defined as aliases of the 32-bit ones. llvm-svn: 191369
2013-09-25 19:11:53 +08:00
def ATOMIC_LOAD_NILF64i : AtomicLoadBinaryImm64<atomic_load_nand_64,
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
imm64lf32c>;
[SystemZ] Allow integer AND involving high words llvm-svn: 191762
2013-10-01 22:20:41 +08:00
def ATOMIC_LOAD_NIHF64i : AtomicLoadBinaryImm64<atomic_load_nand_64,
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
imm64hf32c>;
def ATOMIC_LOADW_MIN : AtomicLoadWBinaryReg<z_atomic_loadw_min>;
def ATOMIC_LOAD_MIN_32 : AtomicLoadBinaryReg32<atomic_load_min_32>;
def ATOMIC_LOAD_MIN_64 : AtomicLoadBinaryReg64<atomic_load_min_64>;
def ATOMIC_LOADW_MAX : AtomicLoadWBinaryReg<z_atomic_loadw_max>;
def ATOMIC_LOAD_MAX_32 : AtomicLoadBinaryReg32<atomic_load_max_32>;
def ATOMIC_LOAD_MAX_64 : AtomicLoadBinaryReg64<atomic_load_max_64>;
def ATOMIC_LOADW_UMIN : AtomicLoadWBinaryReg<z_atomic_loadw_umin>;
def ATOMIC_LOAD_UMIN_32 : AtomicLoadBinaryReg32<atomic_load_umin_32>;
def ATOMIC_LOAD_UMIN_64 : AtomicLoadBinaryReg64<atomic_load_umin_64>;
def ATOMIC_LOADW_UMAX : AtomicLoadWBinaryReg<z_atomic_loadw_umax>;
def ATOMIC_LOAD_UMAX_32 : AtomicLoadBinaryReg32<atomic_load_umax_32>;
def ATOMIC_LOAD_UMAX_64 : AtomicLoadBinaryReg64<atomic_load_umax_64>;
def ATOMIC_CMP_SWAPW
: Pseudo<(outs GR32:$dst), (ins bdaddr20only:$addr, GR32:$cmp, GR32:$swap,
ADDR32:$bitshift, ADDR32:$negbitshift,
uimm32:$bitsize),
[(set GR32:$dst,
(z_atomic_cmp_swapw bdaddr20only:$addr, GR32:$cmp, GR32:$swap,
ADDR32:$bitshift, ADDR32:$negbitshift,
uimm32:$bitsize))]> {
[SystemZ] Rename PSW to CC Addresses a review comment from Ulrich Weigand. No functional change intended. I'm not sure whether the old TODO that this patch touches still holds, but that's something we'd get to when adding a targetted scheduling description. llvm-svn: 182474
2013-05-22 21:38:45 +08:00
let Defs = [CC];
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
let mayLoad = 1;
let mayStore = 1;
let usesCustomInserter = 1;
}
[SystemZ] Rename PSW to CC Addresses a review comment from Ulrich Weigand. No functional change intended. I'm not sure whether the old TODO that this patch touches still holds, but that's something we'd get to when adding a targetted scheduling description. llvm-svn: 182474
2013-05-22 21:38:45 +08:00
let Defs = [CC] in {
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
defm CS : CmpSwapRSPair<"cs", 0xBA, 0xEB14, atomic_cmp_swap_32, GR32>;
def CSG : CmpSwapRSY<"csg", 0xEB30, atomic_cmp_swap_64, GR64>;
}
[SystemZ] Support transactional execution on zEC12 The zEC12 provides the transactional-execution facility. This is exposed to users via a set of builtin routines on other compilers. This patch adds LLVM support to enable those builtins. In partciular, the patch: - adds the transactional-execution and processor-assist facilities - adds MC support for all instructions provided by those facilities - adds LLVM intrinsics for those instructions and hooks them up for CodeGen - adds CodeGen support to optimize CC return value checking Since this is first use of target-specific intrinsics on the platform, the patch creates the include/llvm/IR/IntrinsicsSystemZ.td file and hooks it up in Intrinsics.td. I've also changed Triple::getArchTypePrefix to return "s390" instead of "systemz", since the naming convention for GCC intrinsics uses "s390" on the platform, and it neemed more straight- forward to use the same convention for LLVM IR intrinsics. An associated clang patch makes the intrinsics (and command line switches) available at the source-language level. For reference, the transactional-execution instructions are documented in the z/Architecture Principles of Operation for the zEC12: http://publibfp.boulder.ibm.com/cgi-bin/bookmgr/download/DZ9ZR009.pdf The associated builtins are documented in the GCC manual: http://gcc.gnu.org/onlinedocs/gcc/S_002f390-System-z-Built-in-Functions.html Index: llvm-head/lib/Target/SystemZ/SystemZOperators.td =================================================================== --- llvm-head.orig/lib/Target/SystemZ/SystemZOperators.td +++ llvm-head/lib/Target/SystemZ/SystemZOperators.td @@ -79,6 +79,9 @@ def SDT_ZI32Intrinsic : SDTypeProf def SDT_ZPrefetch : SDTypeProfile<0, 2, [SDTCisVT<0, i32>, SDTCisPtrTy<1>]>; +def SDT_ZTBegin : SDTypeProfile<0, 2, + [SDTCisPtrTy<0>, + SDTCisVT<1, i32>]>; //===----------------------------------------------------------------------===// // Node definitions @@ -180,6 +183,15 @@ def z_prefetch : SDNode<"System [SDNPHasChain, SDNPMayLoad, SDNPMayStore, SDNPMemOperand]>; +def z_tbegin : SDNode<"SystemZISD::TBEGIN", SDT_ZTBegin, + [SDNPHasChain, SDNPOutGlue, SDNPMayStore, + SDNPSideEffect]>; +def z_tbegin_nofloat : SDNode<"SystemZISD::TBEGIN_NOFLOAT", SDT_ZTBegin, + [SDNPHasChain, SDNPOutGlue, SDNPMayStore, + SDNPSideEffect]>; +def z_tend : SDNode<"SystemZISD::TEND", SDTNone, + [SDNPHasChain, SDNPOutGlue, SDNPSideEffect]>; + //===----------------------------------------------------------------------===// // Pattern fragments //===----------------------------------------------------------------------===// Index: llvm-head/lib/Target/SystemZ/SystemZInstrFormats.td =================================================================== --- llvm-head.orig/lib/Target/SystemZ/SystemZInstrFormats.td +++ llvm-head/lib/Target/SystemZ/SystemZInstrFormats.td @@ -473,6 +473,17 @@ class InstSS<bits<8> op, dag outs, dag i let Inst{15-0} = BD2; } +class InstS<bits<16> op, dag outs, dag ins, string asmstr, list<dag> pattern> + : InstSystemZ<4, outs, ins, asmstr, pattern> { + field bits<32> Inst; + field bits<32> SoftFail = 0; + + bits<16> BD2; + + let Inst{31-16} = op; + let Inst{15-0} = BD2; +} + //===----------------------------------------------------------------------===// // Instruction definitions with semantics //===----------------------------------------------------------------------===// Index: llvm-head/lib/Target/SystemZ/SystemZInstrInfo.td =================================================================== --- llvm-head.orig/lib/Target/SystemZ/SystemZInstrInfo.td +++ llvm-head/lib/Target/SystemZ/SystemZInstrInfo.td @@ -1362,6 +1362,60 @@ let Defs = [CC] in { } //===----------------------------------------------------------------------===// +// Transactional execution +//===----------------------------------------------------------------------===// + +let Predicates = [FeatureTransactionalExecution] in { + // Transaction Begin + let hasSideEffects = 1, mayStore = 1, + usesCustomInserter = 1, Defs = [CC] in { + def TBEGIN : InstSIL<0xE560, + (outs), (ins bdaddr12only:$BD1, imm32zx16:$I2), + "tbegin\t$BD1, $I2", + [(z_tbegin bdaddr12only:$BD1, imm32zx16:$I2)]>; + def TBEGIN_nofloat : Pseudo<(outs), (ins bdaddr12only:$BD1, imm32zx16:$I2), + [(z_tbegin_nofloat bdaddr12only:$BD1, + imm32zx16:$I2)]>; + def TBEGINC : InstSIL<0xE561, + (outs), (ins bdaddr12only:$BD1, imm32zx16:$I2), + "tbeginc\t$BD1, $I2", + [(int_s390_tbeginc bdaddr12only:$BD1, + imm32zx16:$I2)]>; + } + + // Transaction End + let hasSideEffects = 1, Defs = [CC], BD2 = 0 in + def TEND : InstS<0xB2F8, (outs), (ins), "tend", [(z_tend)]>; + + // Transaction Abort + let hasSideEffects = 1, isTerminator = 1, isBarrier = 1 in + def TABORT : InstS<0xB2FC, (outs), (ins bdaddr12only:$BD2), + "tabort\t$BD2", + [(int_s390_tabort bdaddr12only:$BD2)]>; + + // Nontransactional Store + let hasSideEffects = 1 in + def NTSTG : StoreRXY<"ntstg", 0xE325, int_s390_ntstg, GR64, 8>; + + // Extract Transaction Nesting Depth + let hasSideEffects = 1 in + def ETND : InherentRRE<"etnd", 0xB2EC, GR32, (int_s390_etnd)>; +} + +//===----------------------------------------------------------------------===// +// Processor assist +//===----------------------------------------------------------------------===// + +let Predicates = [FeatureProcessorAssist] in { + let hasSideEffects = 1, R4 = 0 in + def PPA : InstRRF<0xB2E8, (outs), (ins GR64:$R1, GR64:$R2, imm32zx4:$R3), + "ppa\t$R1, $R2, $R3", []>; + def : Pat<(int_s390_ppa_txassist GR32:$src), + (PPA (INSERT_SUBREG (i64 (IMPLICIT_DEF)), GR32:$src, subreg_l32), + 0, 1)>; +} + +//===----------------------------------------------------------------------===// // Miscellaneous Instructions. //===----------------------------------------------------------------------===// Index: llvm-head/lib/Target/SystemZ/SystemZProcessors.td =================================================================== --- llvm-head.orig/lib/Target/SystemZ/SystemZProcessors.td +++ llvm-head/lib/Target/SystemZ/SystemZProcessors.td @@ -60,6 +60,16 @@ def FeatureMiscellaneousExtensions : Sys "Assume that the miscellaneous-extensions facility is installed" >; +def FeatureTransactionalExecution : SystemZFeature< + "transactional-execution", "TransactionalExecution", + "Assume that the transactional-execution facility is installed" +>; + +def FeatureProcessorAssist : SystemZFeature< + "processor-assist", "ProcessorAssist", + "Assume that the processor-assist facility is installed" +>; + def : Processor<"generic", NoItineraries, []>; def : Processor<"z10", NoItineraries, []>; def : Processor<"z196", NoItineraries, @@ -70,4 +80,5 @@ def : Processor<"zEC12", NoItineraries, [FeatureDistinctOps, FeatureLoadStoreOnCond, FeatureHighWord, FeatureFPExtension, FeaturePopulationCount, FeatureFastSerialization, FeatureInterlockedAccess1, - FeatureMiscellaneousExtensions]>; + FeatureMiscellaneousExtensions, + FeatureTransactionalExecution, FeatureProcessorAssist]>; Index: llvm-head/lib/Target/SystemZ/SystemZSubtarget.cpp =================================================================== --- llvm-head.orig/lib/Target/SystemZ/SystemZSubtarget.cpp +++ llvm-head/lib/Target/SystemZ/SystemZSubtarget.cpp @@ -40,6 +40,7 @@ SystemZSubtarget::SystemZSubtarget(const HasLoadStoreOnCond(false), HasHighWord(false), HasFPExtension(false), HasPopulationCount(false), HasFastSerialization(false), HasInterlockedAccess1(false), HasMiscellaneousExtensions(false), + HasTransactionalExecution(false), HasProcessorAssist(false), TargetTriple(TT), InstrInfo(initializeSubtargetDependencies(CPU, FS)), TLInfo(TM, *this), TSInfo(*TM.getDataLayout()), FrameLowering() {} Index: llvm-head/lib/Target/SystemZ/SystemZSubtarget.h =================================================================== --- llvm-head.orig/lib/Target/SystemZ/SystemZSubtarget.h +++ llvm-head/lib/Target/SystemZ/SystemZSubtarget.h @@ -42,6 +42,8 @@ protected: bool HasFastSerialization; bool HasInterlockedAccess1; bool HasMiscellaneousExtensions; + bool HasTransactionalExecution; + bool HasProcessorAssist; private: Triple TargetTriple; @@ -102,6 +104,12 @@ public: return HasMiscellaneousExtensions; } + // Return true if the target has the transactional-execution facility. + bool hasTransactionalExecution() const { return HasTransactionalExecution; } + + // Return true if the target has the processor-assist facility. + bool hasProcessorAssist() const { return HasProcessorAssist; } + // Return true if GV can be accessed using LARL for reloc model RM // and code model CM. bool isPC32DBLSymbol(const GlobalValue *GV, Reloc::Model RM, Index: llvm-head/lib/Support/Triple.cpp =================================================================== --- llvm-head.orig/lib/Support/Triple.cpp +++ llvm-head/lib/Support/Triple.cpp @@ -92,7 +92,7 @@ const char *Triple::getArchTypePrefix(Ar case sparcv9: case sparc: return "sparc"; - case systemz: return "systemz"; + case systemz: return "s390"; case x86: case x86_64: return "x86"; Index: llvm-head/include/llvm/IR/Intrinsics.td =================================================================== --- llvm-head.orig/include/llvm/IR/Intrinsics.td +++ llvm-head/include/llvm/IR/Intrinsics.td @@ -634,3 +634,4 @@ include "llvm/IR/IntrinsicsNVVM.td" include "llvm/IR/IntrinsicsMips.td" include "llvm/IR/IntrinsicsR600.td" include "llvm/IR/IntrinsicsBPF.td" +include "llvm/IR/IntrinsicsSystemZ.td" Index: llvm-head/include/llvm/IR/IntrinsicsSystemZ.td =================================================================== --- /dev/null +++ llvm-head/include/llvm/IR/IntrinsicsSystemZ.td @@ -0,0 +1,46 @@ +//===- IntrinsicsSystemZ.td - Defines SystemZ intrinsics ---*- tablegen -*-===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +// +// This file defines all of the SystemZ-specific intrinsics. +// +//===----------------------------------------------------------------------===// + +//===----------------------------------------------------------------------===// +// +// Transactional-execution intrinsics +// +//===----------------------------------------------------------------------===// + +let TargetPrefix = "s390" in { + def int_s390_tbegin : Intrinsic<[llvm_i32_ty], [llvm_ptr_ty, llvm_i32_ty], + [IntrNoDuplicate]>; + + def int_s390_tbegin_nofloat : Intrinsic<[llvm_i32_ty], + [llvm_ptr_ty, llvm_i32_ty], + [IntrNoDuplicate]>; + + def int_s390_tbeginc : Intrinsic<[], [llvm_ptr_ty, llvm_i32_ty], + [IntrNoDuplicate]>; + + def int_s390_tabort : Intrinsic<[], [llvm_i64_ty], + [IntrNoReturn, Throws]>; + + def int_s390_tend : GCCBuiltin<"__builtin_tend">, + Intrinsic<[llvm_i32_ty], []>; + + def int_s390_etnd : GCCBuiltin<"__builtin_tx_nesting_depth">, + Intrinsic<[llvm_i32_ty], [], [IntrNoMem]>; + + def int_s390_ntstg : Intrinsic<[], [llvm_i64_ty, llvm_ptr64_ty], + [IntrReadWriteArgMem]>; + + def int_s390_ppa_txassist : GCCBuiltin<"__builtin_tx_assist">, + Intrinsic<[], [llvm_i32_ty]>; +} + Index: llvm-head/lib/Target/SystemZ/SystemZ.h =================================================================== --- llvm-head.orig/lib/Target/SystemZ/SystemZ.h +++ llvm-head/lib/Target/SystemZ/SystemZ.h @@ -68,6 +68,18 @@ const unsigned CCMASK_TM_MSB_0 = C const unsigned CCMASK_TM_MSB_1 = CCMASK_2 | CCMASK_3; const unsigned CCMASK_TM = CCMASK_ANY; +// Condition-code mask assignments for TRANSACTION_BEGIN. +const unsigned CCMASK_TBEGIN_STARTED = CCMASK_0; +const unsigned CCMASK_TBEGIN_INDETERMINATE = CCMASK_1; +const unsigned CCMASK_TBEGIN_TRANSIENT = CCMASK_2; +const unsigned CCMASK_TBEGIN_PERSISTENT = CCMASK_3; +const unsigned CCMASK_TBEGIN = CCMASK_ANY; + +// Condition-code mask assignments for TRANSACTION_END. +const unsigned CCMASK_TEND_TX = CCMASK_0; +const unsigned CCMASK_TEND_NOTX = CCMASK_2; +const unsigned CCMASK_TEND = CCMASK_TEND_TX | CCMASK_TEND_NOTX; + // The position of the low CC bit in an IPM result. const unsigned IPM_CC = 28; Index: llvm-head/lib/Target/SystemZ/SystemZISelLowering.h =================================================================== --- llvm-head.orig/lib/Target/SystemZ/SystemZISelLowering.h +++ llvm-head/lib/Target/SystemZ/SystemZISelLowering.h @@ -146,6 +146,15 @@ enum { // Perform a serialization operation. (BCR 15,0 or BCR 14,0.) SERIALIZE, + // Transaction begin. The first operand is the chain, the second + // the TDB pointer, and the third the immediate control field. + // Returns chain and glue. + TBEGIN, + TBEGIN_NOFLOAT, + + // Transaction end. Just the chain operand. Returns chain and glue. + TEND, + // Wrappers around the inner loop of an 8- or 16-bit ATOMIC_SWAP or // ATOMIC_LOAD_<op>. // @@ -318,6 +327,7 @@ private: SDValue lowerSTACKSAVE(SDValue Op, SelectionDAG &DAG) const; SDValue lowerSTACKRESTORE(SDValue Op, SelectionDAG &DAG) const; SDValue lowerPREFETCH(SDValue Op, SelectionDAG &DAG) const; + SDValue lowerINTRINSIC_W_CHAIN(SDValue Op, SelectionDAG &DAG) const; // If the last instruction before MBBI in MBB was some form of COMPARE, // try to replace it with a COMPARE AND BRANCH just before MBBI. @@ -355,6 +365,10 @@ private: MachineBasicBlock *emitStringWrapper(MachineInstr *MI, MachineBasicBlock *BB, unsigned Opcode) const; + MachineBasicBlock *emitTransactionBegin(MachineInstr *MI, + MachineBasicBlock *MBB, + unsigned Opcode, + bool NoFloat) const; }; } // end namespace llvm Index: llvm-head/lib/Target/SystemZ/SystemZISelLowering.cpp =================================================================== --- llvm-head.orig/lib/Target/SystemZ/SystemZISelLowering.cpp +++ llvm-head/lib/Target/SystemZ/SystemZISelLowering.cpp @@ -20,6 +20,7 @@ #include "llvm/CodeGen/MachineInstrBuilder.h" #include "llvm/CodeGen/MachineRegisterInfo.h" #include "llvm/CodeGen/TargetLoweringObjectFileImpl.h" +#include "llvm/IR/Intrinsics.h" #include <cctype> using namespace llvm; @@ -304,6 +305,9 @@ SystemZTargetLowering::SystemZTargetLowe // Codes for which we want to perform some z-specific combinations. setTargetDAGCombine(ISD::SIGN_EXTEND); + // Handle intrinsics. + setOperationAction(ISD::INTRINSIC_W_CHAIN, MVT::Other, Custom); + // We want to use MVC in preference to even a single load/store pair. MaxStoresPerMemcpy = 0; MaxStoresPerMemcpyOptSize = 0; @@ -1031,6 +1035,53 @@ prepareVolatileOrAtomicLoad(SDValue Chai return DAG.getNode(SystemZISD::SERIALIZE, DL, MVT::Other, Chain); } +// Return true if Op is an intrinsic node with chain that returns the CC value +// as its only (other) argument. Provide the associated SystemZISD opcode and +// the mask of valid CC values if so. +static bool isIntrinsicWithCCAndChain(SDValue Op, unsigned &Opcode, + unsigned &CCValid) { + unsigned Id = cast<ConstantSDNode>(Op.getOperand(1))->getZExtValue(); + switch (Id) { + case Intrinsic::s390_tbegin: + Opcode = SystemZISD::TBEGIN; + CCValid = SystemZ::CCMASK_TBEGIN; + return true; + + case Intrinsic::s390_tbegin_nofloat: + Opcode = SystemZISD::TBEGIN_NOFLOAT; + CCValid = SystemZ::CCMASK_TBEGIN; + return true; + + case Intrinsic::s390_tend: + Opcode = SystemZISD::TEND; + CCValid = SystemZ::CCMASK_TEND; + return true; + + default: + return false; + } +} + +// Emit an intrinsic with chain with a glued value instead of its CC result. +static SDValue emitIntrinsicWithChainAndGlue(SelectionDAG &DAG, SDValue Op, + unsigned Opcode) { + // Copy all operands except the intrinsic ID. + unsigned NumOps = Op.getNumOperands(); + SmallVector<SDValue, 6> Ops; + Ops.reserve(NumOps - 1); + Ops.push_back(Op.getOperand(0)); + for (unsigned I = 2; I < NumOps; ++I) + Ops.push_back(Op.getOperand(I)); + + assert(Op->getNumValues() == 2 && "Expected only CC result and chain"); + SDVTList RawVTs = DAG.getVTList(MVT::Other, MVT::Glue); + SDValue Intr = DAG.getNode(Opcode, SDLoc(Op), RawVTs, Ops); + SDValue OldChain = SDValue(Op.getNode(), 1); + SDValue NewChain = SDValue(Intr.getNode(), 0); + DAG.ReplaceAllUsesOfValueWith(OldChain, NewChain); + return Intr; +} + // CC is a comparison that will be implemented using an integer or // floating-point comparison. Return the condition code mask for // a branch on true. In the integer case, CCMASK_CMP_UO is set for @@ -1588,9 +1639,53 @@ static void adjustForTestUnderMask(Selec C.CCMask = NewCCMask; } +// Return a Comparison that tests the condition-code result of intrinsic +// node Call against constant integer CC using comparison code Cond. +// Opcode is the opcode of the SystemZISD operation for the intrinsic +// and CCValid is the set of possible condition-code results. +static Comparison getIntrinsicCmp(SelectionDAG &DAG, unsigned Opcode, + SDValue Call, unsigned CCValid, uint64_t CC, + ISD::CondCode Cond) { + Comparison C(Call, SDValue()); + C.Opcode = Opcode; + C.CCValid = CCValid; + if (Cond == ISD::SETEQ) + // bit 3 for CC==0, bit 0 for CC==3, always false for CC>3. + C.CCMask = CC < 4 ? 1 << (3 - CC) : 0; + else if (Cond == ISD::SETNE) + // ...and the inverse of that. + C.CCMask = CC < 4 ? ~(1 << (3 - CC)) : -1; + else if (Cond == ISD::SETLT || Cond == ISD::SETULT) + // bits above bit 3 for CC==0 (always false), bits above bit 0 for CC==3, + // always true for CC>3. + C.CCMask = CC < 4 ? -1 << (4 - CC) : -1; + else if (Cond == ISD::SETGE || Cond == ISD::SETUGE) + // ...and the inverse of that. + C.CCMask = CC < 4 ? ~(-1 << (4 - CC)) : 0; + else if (Cond == ISD::SETLE || Cond == ISD::SETULE) + // bit 3 and above for CC==0, bit 0 and above for CC==3 (always true), + // always true for CC>3. + C.CCMask = CC < 4 ? -1 << (3 - CC) : -1; + else if (Cond == ISD::SETGT || Cond == ISD::SETUGT) + // ...and the inverse of that. + C.CCMask = CC < 4 ? ~(-1 << (3 - CC)) : 0; + else + llvm_unreachable("Unexpected integer comparison type"); + C.CCMask &= CCValid; + return C; +} + // Decide how to implement a comparison of type Cond between CmpOp0 with CmpOp1. static Comparison getCmp(SelectionDAG &DAG, SDValue CmpOp0, SDValue CmpOp1, ISD::CondCode Cond) { + if (CmpOp1.getOpcode() == ISD::Constant) { + uint64_t Constant = cast<ConstantSDNode>(CmpOp1)->getZExtValue(); + unsigned Opcode, CCValid; + if (CmpOp0.getOpcode() == ISD::INTRINSIC_W_CHAIN && + CmpOp0.getResNo() == 0 && CmpOp0->hasNUsesOfValue(1, 0) && + isIntrinsicWithCCAndChain(CmpOp0, Opcode, CCValid)) + return getIntrinsicCmp(DAG, Opcode, CmpOp0, CCValid, Constant, Cond); + } Comparison C(CmpOp0, CmpOp1); C.CCMask = CCMaskForCondCode(Cond); if (C.Op0.getValueType().isFloatingPoint()) { @@ -1632,6 +1727,17 @@ static Comparison getCmp(SelectionDAG &D // Emit the comparison instruction described by C. static SDValue emitCmp(SelectionDAG &DAG, SDLoc DL, Comparison &C) { + if (!C.Op1.getNode()) { + SDValue Op; + switch (C.Op0.getOpcode()) { + case ISD::INTRINSIC_W_CHAIN: + Op = emitIntrinsicWithChainAndGlue(DAG, C.Op0, C.Opcode); + break; + default: + llvm_unreachable("Invalid comparison operands"); + } + return SDValue(Op.getNode(), Op->getNumValues() - 1); + } if (C.Opcode == SystemZISD::ICMP) return DAG.getNode(SystemZISD::ICMP, DL, MVT::Glue, C.Op0, C.Op1, DAG.getConstant(C.ICmpType, MVT::i32)); @@ -1713,7 +1819,6 @@ SDValue SystemZTargetLowering::lowerSETC } SDValue SystemZTargetLowering::lowerBR_CC(SDValue Op, SelectionDAG &DAG) const { - SDValue Chain = Op.getOperand(0); ISD::CondCode CC = cast<CondCodeSDNode>(Op.getOperand(1))->get(); SDValue CmpOp0 = Op.getOperand(2); SDValue CmpOp1 = Op.getOperand(3); @@ -1723,7 +1828,7 @@ SDValue SystemZTargetLowering::lowerBR_C Comparison C(getCmp(DAG, CmpOp0, CmpOp1, CC)); SDValue Glue = emitCmp(DAG, DL, C); return DAG.getNode(SystemZISD::BR_CCMASK, DL, Op.getValueType(), - Chain, DAG.getConstant(C.CCValid, MVT::i32), + Op.getOperand(0), DAG.getConstant(C.CCValid, MVT::i32), DAG.getConstant(C.CCMask, MVT::i32), Dest, Glue); } @@ -2561,6 +2666,30 @@ SDValue SystemZTargetLowering::lowerPREF Node->getMemoryVT(), Node->getMemOperand()); } +// Return an i32 that contains the value of CC immediately after After, +// whose final operand must be MVT::Glue. +static SDValue getCCResult(SelectionDAG &DAG, SDNode *After) { + SDValue Glue = SDValue(After, After->getNumValues() - 1); + SDValue IPM = DAG.getNode(SystemZISD::IPM, SDLoc(After), MVT::i32, Glue); + return DAG.getNode(ISD::SRL, SDLoc(After), MVT::i32, IPM, + DAG.getConstant(SystemZ::IPM_CC, MVT::i32)); +} + +SDValue +SystemZTargetLowering::lowerINTRINSIC_W_CHAIN(SDValue Op, + SelectionDAG &DAG) const { + unsigned Opcode, CCValid; + if (isIntrinsicWithCCAndChain(Op, Opcode, CCValid)) { + assert(Op->getNumValues() == 2 && "Expected only CC result and chain"); + SDValue Glued = emitIntrinsicWithChainAndGlue(DAG, Op, Opcode); + SDValue CC = getCCResult(DAG, Glued.getNode()); + DAG.ReplaceAllUsesOfValueWith(SDValue(Op.getNode(), 0), CC); + return SDValue(); + } + + return SDValue(); +} + SDValue SystemZTargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const { switch (Op.getOpcode()) { @@ -2634,6 +2763,8 @@ SDValue SystemZTargetLowering::LowerOper return lowerSTACKRESTORE(Op, DAG); case ISD::PREFETCH: return lowerPREFETCH(Op, DAG); + case ISD::INTRINSIC_W_CHAIN: + return lowerINTRINSIC_W_CHAIN(Op, DAG); default: llvm_unreachable("Unexpected node to lower"); } @@ -2674,6 +2805,9 @@ const char *SystemZTargetLowering::getTa OPCODE(SEARCH_STRING); OPCODE(IPM); OPCODE(SERIALIZE); + OPCODE(TBEGIN); + OPCODE(TBEGIN_NOFLOAT); + OPCODE(TEND); OPCODE(ATOMIC_SWAPW); OPCODE(ATOMIC_LOADW_ADD); OPCODE(ATOMIC_LOADW_SUB); @@ -3501,6 +3635,50 @@ SystemZTargetLowering::emitStringWrapper return DoneMBB; } +// Update TBEGIN instruction with final opcode and register clobbers. +MachineBasicBlock * +SystemZTargetLowering::emitTransactionBegin(MachineInstr *MI, + MachineBasicBlock *MBB, + unsigned Opcode, + bool NoFloat) const { + MachineFunction &MF = *MBB->getParent(); + const TargetFrameLowering *TFI = Subtarget.getFrameLowering(); + const SystemZInstrInfo *TII = Subtarget.getInstrInfo(); + + // Update opcode. + MI->setDesc(TII->get(Opcode)); + + // We cannot handle a TBEGIN that clobbers the stack or frame pointer. + // Make sure to add the corresponding GRSM bits if they are missing. + uint64_t Control = MI->getOperand(2).getImm(); + static const unsigned GPRControlBit[16] = { + 0x8000, 0x8000, 0x4000, 0x4000, 0x2000, 0x2000, 0x1000, 0x1000, + 0x0800, 0x0800, 0x0400, 0x0400, 0x0200, 0x0200, 0x0100, 0x0100 + }; + Control |= GPRControlBit[15]; + if (TFI->hasFP(MF)) + Control |= GPRControlBit[11]; + MI->getOperand(2).setImm(Control); + + // Add GPR clobbers. + for (int I = 0; I < 16; I++) { + if ((Control & GPRControlBit[I]) == 0) { + unsigned Reg = SystemZMC::GR64Regs[I]; + MI->addOperand(MachineOperand::CreateReg(Reg, true, true)); + } + } + + // Add FPR clobbers. + if (!NoFloat && (Control & 4) != 0) { + for (int I = 0; I < 16; I++) { + unsigned Reg = SystemZMC::FP64Regs[I]; + MI->addOperand(MachineOperand::CreateReg(Reg, true, true)); + } + } + + return MBB; +} + MachineBasicBlock *SystemZTargetLowering:: EmitInstrWithCustomInserter(MachineInstr *MI, MachineBasicBlock *MBB) const { switch (MI->getOpcode()) { @@ -3742,6 +3920,12 @@ EmitInstrWithCustomInserter(MachineInstr return emitStringWrapper(MI, MBB, SystemZ::MVST); case SystemZ::SRSTLoop: return emitStringWrapper(MI, MBB, SystemZ::SRST); + case SystemZ::TBEGIN: + return emitTransactionBegin(MI, MBB, SystemZ::TBEGIN, false); + case SystemZ::TBEGIN_nofloat: + return emitTransactionBegin(MI, MBB, SystemZ::TBEGIN, true); + case SystemZ::TBEGINC: + return emitTransactionBegin(MI, MBB, SystemZ::TBEGINC, true); default: llvm_unreachable("Unexpected instr type to insert"); } Index: llvm-head/test/CodeGen/SystemZ/htm-intrinsics.ll =================================================================== --- /dev/null +++ llvm-head/test/CodeGen/SystemZ/htm-intrinsics.ll @@ -0,0 +1,352 @@ +; Test transactional-execution intrinsics. +; +; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=zEC12 | FileCheck %s + +declare i32 @llvm.s390.tbegin(i8 *, i32) +declare i32 @llvm.s390.tbegin.nofloat(i8 *, i32) +declare void @llvm.s390.tbeginc(i8 *, i32) +declare i32 @llvm.s390.tend() +declare void @llvm.s390.tabort(i64) +declare void @llvm.s390.ntstg(i64, i64 *) +declare i32 @llvm.s390.etnd() +declare void @llvm.s390.ppa.txassist(i32) + +; TBEGIN. +define void @test_tbegin() { +; CHECK-LABEL: test_tbegin: +; CHECK-NOT: stmg +; CHECK: std %f8, +; CHECK: std %f9, +; CHECK: std %f10, +; CHECK: std %f11, +; CHECK: std %f12, +; CHECK: std %f13, +; CHECK: std %f14, +; CHECK: std %f15, +; CHECK: tbegin 0, 65292 +; CHECK: ld %f8, +; CHECK: ld %f9, +; CHECK: ld %f10, +; CHECK: ld %f11, +; CHECK: ld %f12, +; CHECK: ld %f13, +; CHECK: ld %f14, +; CHECK: ld %f15, +; CHECK: br %r14 + call i32 @llvm.s390.tbegin(i8 *null, i32 65292) + ret void +} + +; TBEGIN (nofloat). +define void @test_tbegin_nofloat1() { +; CHECK-LABEL: test_tbegin_nofloat1: +; CHECK-NOT: stmg +; CHECK-NOT: std +; CHECK: tbegin 0, 65292 +; CHECK: br %r14 + call i32 @llvm.s390.tbegin.nofloat(i8 *null, i32 65292) + ret void +} + +; TBEGIN (nofloat) with integer CC return value. +define i32 @test_tbegin_nofloat2() { +; CHECK-LABEL: test_tbegin_nofloat2: +; CHECK-NOT: stmg +; CHECK-NOT: std +; CHECK: tbegin 0, 65292 +; CHECK: ipm %r2 +; CHECK: srl %r2, 28 +; CHECK: br %r14 + %res = call i32 @llvm.s390.tbegin.nofloat(i8 *null, i32 65292) + ret i32 %res +} + +; TBEGIN (nofloat) with implicit CC check. +define void @test_tbegin_nofloat3(i32 *%ptr) { +; CHECK-LABEL: test_tbegin_nofloat3: +; CHECK-NOT: stmg +; CHECK-NOT: std +; CHECK: tbegin 0, 65292 +; CHECK: jnh {{\.L*}} +; CHECK: mvhi 0(%r2), 0 +; CHECK: br %r14 + %res = call i32 @llvm.s390.tbegin.nofloat(i8 *null, i32 65292) + %cmp = icmp eq i32 %res, 2 + br i1 %cmp, label %if.then, label %if.end + +if.then: ; preds = %entry + store i32 0, i32* %ptr, align 4 + br label %if.end + +if.end: ; preds = %if.then, %entry + ret void +} + +; TBEGIN (nofloat) with dual CC use. +define i32 @test_tbegin_nofloat4(i32 %pad, i32 *%ptr) { +; CHECK-LABEL: test_tbegin_nofloat4: +; CHECK-NOT: stmg +; CHECK-NOT: std +; CHECK: tbegin 0, 65292 +; CHECK: ipm %r2 +; CHECK: srl %r2, 28 +; CHECK: cijlh %r2, 2, {{\.L*}} +; CHECK: mvhi 0(%r3), 0 +; CHECK: br %r14 + %res = call i32 @llvm.s390.tbegin.nofloat(i8 *null, i32 65292) + %cmp = icmp eq i32 %res, 2 + br i1 %cmp, label %if.then, label %if.end + +if.then: ; preds = %entry + store i32 0, i32* %ptr, align 4 + br label %if.end + +if.end: ; preds = %if.then, %entry + ret i32 %res +} + +; TBEGIN (nofloat) with register. +define void @test_tbegin_nofloat5(i8 *%ptr) { +; CHECK-LABEL: test_tbegin_nofloat5: +; CHECK-NOT: stmg +; CHECK-NOT: std +; CHECK: tbegin 0(%r2), 65292 +; CHECK: br %r14 + call i32 @llvm.s390.tbegin.nofloat(i8 *%ptr, i32 65292) + ret void +} + +; TBEGIN (nofloat) with GRSM 0x0f00. +define void @test_tbegin_nofloat6() { +; CHECK-LABEL: test_tbegin_nofloat6: +; CHECK: stmg %r6, %r15, +; CHECK-NOT: std +; CHECK: tbegin 0, 3840 +; CHECK: br %r14 + call i32 @llvm.s390.tbegin.nofloat(i8 *null, i32 3840) + ret void +} + +; TBEGIN (nofloat) with GRSM 0xf100. +define void @test_tbegin_nofloat7() { +; CHECK-LABEL: test_tbegin_nofloat7: +; CHECK: stmg %r8, %r15, +; CHECK-NOT: std +; CHECK: tbegin 0, 61696 +; CHECK: br %r14 + call i32 @llvm.s390.tbegin.nofloat(i8 *null, i32 61696) + ret void +} + +; TBEGIN (nofloat) with GRSM 0xfe00 -- stack pointer added automatically. +define void @test_tbegin_nofloat8() { +; CHECK-LABEL: test_tbegin_nofloat8: +; CHECK-NOT: stmg +; CHECK-NOT: std +; CHECK: tbegin 0, 65280 +; CHECK: br %r14 + call i32 @llvm.s390.tbegin.nofloat(i8 *null, i32 65024) + ret void +} + +; TBEGIN (nofloat) with GRSM 0xfb00 -- no frame pointer needed. +define void @test_tbegin_nofloat9() { +; CHECK-LABEL: test_tbegin_nofloat9: +; CHECK: stmg %r10, %r15, +; CHECK-NOT: std +; CHECK: tbegin 0, 64256 +; CHECK: br %r14 + call i32 @llvm.s390.tbegin.nofloat(i8 *null, i32 64256) + ret void +} + +; TBEGIN (nofloat) with GRSM 0xfb00 -- frame pointer added automatically. +define void @test_tbegin_nofloat10(i64 %n) { +; CHECK-LABEL: test_tbegin_nofloat10: +; CHECK: stmg %r11, %r15, +; CHECK-NOT: std +; CHECK: tbegin 0, 65280 +; CHECK: br %r14 + %buf = alloca i8, i64 %n + call i32 @llvm.s390.tbegin.nofloat(i8 *null, i32 64256) + ret void +} + +; TBEGINC. +define void @test_tbeginc() { +; CHECK-LABEL: test_tbeginc: +; CHECK-NOT: stmg +; CHECK-NOT: std +; CHECK: tbeginc 0, 65288 +; CHECK: br %r14 + call void @llvm.s390.tbeginc(i8 *null, i32 65288) + ret void +} + +; TEND with integer CC return value. +define i32 @test_tend1() { +; CHECK-LABEL: test_tend1: +; CHECK: tend +; CHECK: ipm %r2 +; CHECK: srl %r2, 28 +; CHECK: br %r14 + %res = call i32 @llvm.s390.tend() + ret i32 %res +} + +; TEND with implicit CC check. +define void @test_tend3(i32 *%ptr) { +; CHECK-LABEL: test_tend3: +; CHECK: tend +; CHECK: je {{\.L*}} +; CHECK: mvhi 0(%r2), 0 +; CHECK: br %r14 + %res = call i32 @llvm.s390.tend() + %cmp = icmp eq i32 %res, 2 + br i1 %cmp, label %if.then, label %if.end + +if.then: ; preds = %entry + store i32 0, i32* %ptr, align 4 + br label %if.end + +if.end: ; preds = %if.then, %entry + ret void +} + +; TEND with dual CC use. +define i32 @test_tend2(i32 %pad, i32 *%ptr) { +; CHECK-LABEL: test_tend2: +; CHECK: tend +; CHECK: ipm %r2 +; CHECK: srl %r2, 28 +; CHECK: cijlh %r2, 2, {{\.L*}} +; CHECK: mvhi 0(%r3), 0 +; CHECK: br %r14 + %res = call i32 @llvm.s390.tend() + %cmp = icmp eq i32 %res, 2 + br i1 %cmp, label %if.then, label %if.end + +if.then: ; preds = %entry + store i32 0, i32* %ptr, align 4 + br label %if.end + +if.end: ; preds = %if.then, %entry + ret i32 %res +} + +; TABORT with register only. +define void @test_tabort1(i64 %val) { +; CHECK-LABEL: test_tabort1: +; CHECK: tabort 0(%r2) +; CHECK: br %r14 + call void @llvm.s390.tabort(i64 %val) + ret void +} + +; TABORT with immediate only. +define void @test_tabort2(i64 %val) { +; CHECK-LABEL: test_tabort2: +; CHECK: tabort 1234 +; CHECK: br %r14 + call void @llvm.s390.tabort(i64 1234) + ret void +} + +; TABORT with register + immediate. +define void @test_tabort3(i64 %val) { +; CHECK-LABEL: test_tabort3: +; CHECK: tabort 1234(%r2) +; CHECK: br %r14 + %sum = add i64 %val, 1234 + call void @llvm.s390.tabort(i64 %sum) + ret void +} + +; TABORT with out-of-range immediate. +define void @test_tabort4(i64 %val) { +; CHECK-LABEL: test_tabort4: +; CHECK: tabort 0({{%r[1-5]}}) +; CHECK: br %r14 + call void @llvm.s390.tabort(i64 4096) + ret void +} + +; NTSTG with base pointer only. +define void @test_ntstg1(i64 *%ptr, i64 %val) { +; CHECK-LABEL: test_ntstg1: +; CHECK: ntstg %r3, 0(%r2) +; CHECK: br %r14 + call void @llvm.s390.ntstg(i64 %val, i64 *%ptr) + ret void +} + +; NTSTG with base and index. +; Check that VSTL doesn't allow an index. +define void @test_ntstg2(i64 *%base, i64 %index, i64 %val) { +; CHECK-LABEL: test_ntstg2: +; CHECK: sllg [[REG:%r[1-5]]], %r3, 3 +; CHECK: ntstg %r4, 0([[REG]],%r2) +; CHECK: br %r14 + %ptr = getelementptr i64, i64 *%base, i64 %index + call void @llvm.s390.ntstg(i64 %val, i64 *%ptr) + ret void +} + +; NTSTG with the highest in-range displacement. +define void @test_ntstg3(i64 *%base, i64 %val) { +; CHECK-LABEL: test_ntstg3: +; CHECK: ntstg %r3, 524280(%r2) +; CHECK: br %r14 + %ptr = getelementptr i64, i64 *%base, i64 65535 + call void @llvm.s390.ntstg(i64 %val, i64 *%ptr) + ret void +} + +; NTSTG with an out-of-range positive displacement. +define void @test_ntstg4(i64 *%base, i64 %val) { +; CHECK-LABEL: test_ntstg4: +; CHECK: ntstg %r3, 0({{%r[1-5]}}) +; CHECK: br %r14 + %ptr = getelementptr i64, i64 *%base, i64 65536 + call void @llvm.s390.ntstg(i64 %val, i64 *%ptr) + ret void +} + +; NTSTG with the lowest in-range displacement. +define void @test_ntstg5(i64 *%base, i64 %val) { +; CHECK-LABEL: test_ntstg5: +; CHECK: ntstg %r3, -524288(%r2) +; CHECK: br %r14 + %ptr = getelementptr i64, i64 *%base, i64 -65536 + call void @llvm.s390.ntstg(i64 %val, i64 *%ptr) + ret void +} + +; NTSTG with an out-of-range negative displacement. +define void @test_ntstg6(i64 *%base, i64 %val) { +; CHECK-LABEL: test_ntstg6: +; CHECK: ntstg %r3, 0({{%r[1-5]}}) +; CHECK: br %r14 + %ptr = getelementptr i64, i64 *%base, i64 -65537 + call void @llvm.s390.ntstg(i64 %val, i64 *%ptr) + ret void +} + +; ETND. +define i32 @test_etnd() { +; CHECK-LABEL: test_etnd: +; CHECK: etnd %r2 +; CHECK: br %r14 + %res = call i32 @llvm.s390.etnd() + ret i32 %res +} + +; PPA (Transaction-Abort Assist) +define void @test_ppa_txassist(i32 %val) { +; CHECK-LABEL: test_ppa_txassist: +; CHECK: ppa %r2, 0, 1 +; CHECK: br %r14 + call void @llvm.s390.ppa.txassist(i32 %val) + ret void +} + Index: llvm-head/test/MC/SystemZ/insn-bad-zEC12.s =================================================================== --- llvm-head.orig/test/MC/SystemZ/insn-bad-zEC12.s +++ llvm-head/test/MC/SystemZ/insn-bad-zEC12.s @@ -3,6 +3,22 @@ # RUN: FileCheck < %t %s #CHECK: error: invalid operand +#CHECK: ntstg %r0, -524289 +#CHECK: error: invalid operand +#CHECK: ntstg %r0, 524288 + + ntstg %r0, -524289 + ntstg %r0, 524288 + +#CHECK: error: invalid operand +#CHECK: ppa %r0, %r0, -1 +#CHECK: error: invalid operand +#CHECK: ppa %r0, %r0, 16 + + ppa %r0, %r0, -1 + ppa %r0, %r0, 16 + +#CHECK: error: invalid operand #CHECK: risbgn %r0,%r0,0,0,-1 #CHECK: error: invalid operand #CHECK: risbgn %r0,%r0,0,0,64 @@ -22,3 +38,47 @@ risbgn %r0,%r0,-1,0,0 risbgn %r0,%r0,256,0,0 +#CHECK: error: invalid operand +#CHECK: tabort -1 +#CHECK: error: invalid operand +#CHECK: tabort 4096 +#CHECK: error: invalid use of indexed addressing +#CHECK: tabort 0(%r1,%r2) + + tabort -1 + tabort 4096 + tabort 0(%r1,%r2) + +#CHECK: error: invalid operand +#CHECK: tbegin -1, 0 +#CHECK: error: invalid operand +#CHECK: tbegin 4096, 0 +#CHECK: error: invalid use of indexed addressing +#CHECK: tbegin 0(%r1,%r2), 0 +#CHECK: error: invalid operand +#CHECK: tbegin 0, -1 +#CHECK: error: invalid operand +#CHECK: tbegin 0, 65536 + + tbegin -1, 0 + tbegin 4096, 0 + tbegin 0(%r1,%r2), 0 + tbegin 0, -1 + tbegin 0, 65536 + +#CHECK: error: invalid operand +#CHECK: tbeginc -1, 0 +#CHECK: error: invalid operand +#CHECK: tbeginc 4096, 0 +#CHECK: error: invalid use of indexed addressing +#CHECK: tbeginc 0(%r1,%r2), 0 +#CHECK: error: invalid operand +#CHECK: tbeginc 0, -1 +#CHECK: error: invalid operand +#CHECK: tbeginc 0, 65536 + + tbeginc -1, 0 + tbeginc 4096, 0 + tbeginc 0(%r1,%r2), 0 + tbeginc 0, -1 + tbeginc 0, 65536 Index: llvm-head/test/MC/SystemZ/insn-good-zEC12.s =================================================================== --- llvm-head.orig/test/MC/SystemZ/insn-good-zEC12.s +++ llvm-head/test/MC/SystemZ/insn-good-zEC12.s @@ -1,6 +1,48 @@ # For zEC12 and above. # RUN: llvm-mc -triple s390x-linux-gnu -mcpu=zEC12 -show-encoding %s | FileCheck %s +#CHECK: etnd %r0 # encoding: [0xb2,0xec,0x00,0x00] +#CHECK: etnd %r15 # encoding: [0xb2,0xec,0x00,0xf0] +#CHECK: etnd %r7 # encoding: [0xb2,0xec,0x00,0x70] + + etnd %r0 + etnd %r15 + etnd %r7 + +#CHECK: ntstg %r0, -524288 # encoding: [0xe3,0x00,0x00,0x00,0x80,0x25] +#CHECK: ntstg %r0, -1 # encoding: [0xe3,0x00,0x0f,0xff,0xff,0x25] +#CHECK: ntstg %r0, 0 # encoding: [0xe3,0x00,0x00,0x00,0x00,0x25] +#CHECK: ntstg %r0, 1 # encoding: [0xe3,0x00,0x00,0x01,0x00,0x25] +#CHECK: ntstg %r0, 524287 # encoding: [0xe3,0x00,0x0f,0xff,0x7f,0x25] +#CHECK: ntstg %r0, 0(%r1) # encoding: [0xe3,0x00,0x10,0x00,0x00,0x25] +#CHECK: ntstg %r0, 0(%r15) # encoding: [0xe3,0x00,0xf0,0x00,0x00,0x25] +#CHECK: ntstg %r0, 524287(%r1,%r15) # encoding: [0xe3,0x01,0xff,0xff,0x7f,0x25] +#CHECK: ntstg %r0, 524287(%r15,%r1) # encoding: [0xe3,0x0f,0x1f,0xff,0x7f,0x25] +#CHECK: ntstg %r15, 0 # encoding: [0xe3,0xf0,0x00,0x00,0x00,0x25] + + ntstg %r0, -524288 + ntstg %r0, -1 + ntstg %r0, 0 + ntstg %r0, 1 + ntstg %r0, 524287 + ntstg %r0, 0(%r1) + ntstg %r0, 0(%r15) + ntstg %r0, 524287(%r1,%r15) + ntstg %r0, 524287(%r15,%r1) + ntstg %r15, 0 + +#CHECK: ppa %r0, %r0, 0 # encoding: [0xb2,0xe8,0x00,0x00] +#CHECK: ppa %r0, %r0, 15 # encoding: [0xb2,0xe8,0xf0,0x00] +#CHECK: ppa %r0, %r15, 0 # encoding: [0xb2,0xe8,0x00,0x0f] +#CHECK: ppa %r4, %r6, 7 # encoding: [0xb2,0xe8,0x70,0x46] +#CHECK: ppa %r15, %r0, 0 # encoding: [0xb2,0xe8,0x00,0xf0] + + ppa %r0, %r0, 0 + ppa %r0, %r0, 15 + ppa %r0, %r15, 0 + ppa %r4, %r6, 7 + ppa %r15, %r0, 0 + #CHECK: risbgn %r0, %r0, 0, 0, 0 # encoding: [0xec,0x00,0x00,0x00,0x00,0x59] #CHECK: risbgn %r0, %r0, 0, 0, 63 # encoding: [0xec,0x00,0x00,0x00,0x3f,0x59] #CHECK: risbgn %r0, %r0, 0, 255, 0 # encoding: [0xec,0x00,0x00,0xff,0x00,0x59] @@ -17,3 +59,68 @@ risbgn %r15,%r0,0,0,0 risbgn %r4,%r5,6,7,8 +#CHECK: tabort 0 # encoding: [0xb2,0xfc,0x00,0x00] +#CHECK: tabort 0(%r1) # encoding: [0xb2,0xfc,0x10,0x00] +#CHECK: tabort 0(%r15) # encoding: [0xb2,0xfc,0xf0,0x00] +#CHECK: tabort 4095 # encoding: [0xb2,0xfc,0x0f,0xff] +#CHECK: tabort 4095(%r1) # encoding: [0xb2,0xfc,0x1f,0xff] +#CHECK: tabort 4095(%r15) # encoding: [0xb2,0xfc,0xff,0xff] + + tabort 0 + tabort 0(%r1) + tabort 0(%r15) + tabort 4095 + tabort 4095(%r1) + tabort 4095(%r15) + +#CHECK: tbegin 0, 0 # encoding: [0xe5,0x60,0x00,0x00,0x00,0x00] +#CHECK: tbegin 4095, 0 # encoding: [0xe5,0x60,0x0f,0xff,0x00,0x00] +#CHECK: tbegin 0, 0 # encoding: [0xe5,0x60,0x00,0x00,0x00,0x00] +#CHECK: tbegin 0, 1 # encoding: [0xe5,0x60,0x00,0x00,0x00,0x01] +#CHECK: tbegin 0, 32767 # encoding: [0xe5,0x60,0x00,0x00,0x7f,0xff] +#CHECK: tbegin 0, 32768 # encoding: [0xe5,0x60,0x00,0x00,0x80,0x00] +#CHECK: tbegin 0, 65535 # encoding: [0xe5,0x60,0x00,0x00,0xff,0xff] +#CHECK: tbegin 0(%r1), 42 # encoding: [0xe5,0x60,0x10,0x00,0x00,0x2a] +#CHECK: tbegin 0(%r15), 42 # encoding: [0xe5,0x60,0xf0,0x00,0x00,0x2a] +#CHECK: tbegin 4095(%r1), 42 # encoding: [0xe5,0x60,0x1f,0xff,0x00,0x2a] +#CHECK: tbegin 4095(%r15), 42 # encoding: [0xe5,0x60,0xff,0xff,0x00,0x2a] + + tbegin 0, 0 + tbegin 4095, 0 + tbegin 0, 0 + tbegin 0, 1 + tbegin 0, 32767 + tbegin 0, 32768 + tbegin 0, 65535 + tbegin 0(%r1), 42 + tbegin 0(%r15), 42 + tbegin 4095(%r1), 42 + tbegin 4095(%r15), 42 + +#CHECK: tbeginc 0, 0 # encoding: [0xe5,0x61,0x00,0x00,0x00,0x00] +#CHECK: tbeginc 4095, 0 # encoding: [0xe5,0x61,0x0f,0xff,0x00,0x00] +#CHECK: tbeginc 0, 0 # encoding: [0xe5,0x61,0x00,0x00,0x00,0x00] +#CHECK: tbeginc 0, 1 # encoding: [0xe5,0x61,0x00,0x00,0x00,0x01] +#CHECK: tbeginc 0, 32767 # encoding: [0xe5,0x61,0x00,0x00,0x7f,0xff] +#CHECK: tbeginc 0, 32768 # encoding: [0xe5,0x61,0x00,0x00,0x80,0x00] +#CHECK: tbeginc 0, 65535 # encoding: [0xe5,0x61,0x00,0x00,0xff,0xff] +#CHECK: tbeginc 0(%r1), 42 # encoding: [0xe5,0x61,0x10,0x00,0x00,0x2a] +#CHECK: tbeginc 0(%r15), 42 # encoding: [0xe5,0x61,0xf0,0x00,0x00,0x2a] +#CHECK: tbeginc 4095(%r1), 42 # encoding: [0xe5,0x61,0x1f,0xff,0x00,0x2a] +#CHECK: tbeginc 4095(%r15), 42 # encoding: [0xe5,0x61,0xff,0xff,0x00,0x2a] + + tbeginc 0, 0 + tbeginc 4095, 0 + tbeginc 0, 0 + tbeginc 0, 1 + tbeginc 0, 32767 + tbeginc 0, 32768 + tbeginc 0, 65535 + tbeginc 0(%r1), 42 + tbeginc 0(%r15), 42 + tbeginc 4095(%r1), 42 + tbeginc 4095(%r15), 42 + +#CHECK: tend # encoding: [0xb2,0xf8,0x00,0x00] + + tend Index: llvm-head/test/MC/SystemZ/insn-bad-z196.s =================================================================== --- llvm-head.orig/test/MC/SystemZ/insn-bad-z196.s +++ llvm-head/test/MC/SystemZ/insn-bad-z196.s @@ -244,6 +244,11 @@ cxlgbr %f0, 16, %r0, 0 cxlgbr %f2, 0, %r0, 0 +#CHECK: error: {{(instruction requires: transactional-execution)?}} +#CHECK: etnd %r7 + + etnd %r7 + #CHECK: error: invalid operand #CHECK: fidbra %f0, 0, %f0, -1 #CHECK: error: invalid operand @@ -546,6 +551,16 @@ locr %r0,%r0,-1 locr %r0,%r0,16 +#CHECK: error: {{(instruction requires: transactional-execution)?}} +#CHECK: ntstg %r0, 524287(%r1,%r15) + + ntstg %r0, 524287(%r1,%r15) + +#CHECK: error: {{(instruction requires: processor-assist)?}} +#CHECK: ppa %r4, %r6, 7 + + ppa %r4, %r6, 7 + #CHECK: error: {{(instruction requires: miscellaneous-extensions)?}} #CHECK: risbgn %r1, %r2, 0, 0, 0 @@ -690,3 +705,24 @@ stocg %r0,-524289,1 stocg %r0,524288,1 stocg %r0,0(%r1,%r2),1 + +#CHECK: error: {{(instruction requires: transactional-execution)?}} +#CHECK: tabort 4095(%r1) + + tabort 4095(%r1) + +#CHECK: error: {{(instruction requires: transactional-execution)?}} +#CHECK: tbegin 4095(%r1), 42 + + tbegin 4095(%r1), 42 + +#CHECK: error: {{(instruction requires: transactional-execution)?}} +#CHECK: tbeginc 4095(%r1), 42 + + tbeginc 4095(%r1), 42 + +#CHECK: error: {{(instruction requires: transactional-execution)?}} +#CHECK: tend + + tend + Index: llvm-head/test/MC/Disassembler/SystemZ/insns.txt =================================================================== --- llvm-head.orig/test/MC/Disassembler/SystemZ/insns.txt +++ llvm-head/test/MC/Disassembler/SystemZ/insns.txt @@ -2503,6 +2503,15 @@ # CHECK: ear %r15, %a15 0xb2 0x4f 0x00 0xff +# CHECK: etnd %r0 +0xb2 0xec 0x00 0x00 + +# CHECK: etnd %r15 +0xb2 0xec 0x00 0xf0 + +# CHECK: etnd %r7 +0xb2 0xec 0x00 0x70 + # CHECK: fidbr %f0, 0, %f0 0xb3 0x5f 0x00 0x00 @@ -6034,6 +6043,36 @@ # CHECK: ny %r15, 0 0xe3 0xf0 0x00 0x00 0x00 0x54 +# CHECK: ntstg %r0, -524288 +0xe3 0x00 0x00 0x00 0x80 0x25 + +# CHECK: ntstg %r0, -1 +0xe3 0x00 0x0f 0xff 0xff 0x25 + +# CHECK: ntstg %r0, 0 +0xe3 0x00 0x00 0x00 0x00 0x25 + +# CHECK: ntstg %r0, 1 +0xe3 0x00 0x00 0x01 0x00 0x25 + +# CHECK: ntstg %r0, 524287 +0xe3 0x00 0x0f 0xff 0x7f 0x25 + +# CHECK: ntstg %r0, 0(%r1) +0xe3 0x00 0x10 0x00 0x00 0x25 + +# CHECK: ntstg %r0, 0(%r15) +0xe3 0x00 0xf0 0x00 0x00 0x25 + +# CHECK: ntstg %r0, 524287(%r1,%r15) +0xe3 0x01 0xff 0xff 0x7f 0x25 + +# CHECK: ntstg %r0, 524287(%r15,%r1) +0xe3 0x0f 0x1f 0xff 0x7f 0x25 + +# CHECK: ntstg %r15, 0 +0xe3 0xf0 0x00 0x00 0x00 0x25 + # CHECK: oc 0(1), 0 0xd6 0x00 0x00 0x00 0x00 0x00 @@ -6346,6 +6385,21 @@ # CHECK: popcnt %r7, %r8 0xb9 0xe1 0x00 0x78 +# CHECK: ppa %r0, %r0, 0 +0xb2 0xe8 0x00 0x00 + +# CHECK: ppa %r0, %r0, 15 +0xb2 0xe8 0xf0 0x00 + +# CHECK: ppa %r0, %r15, 0 +0xb2 0xe8 0x00 0x0f + +# CHECK: ppa %r4, %r6, 7 +0xb2 0xe8 0x70 0x46 + +# CHECK: ppa %r15, %r0, 0 +0xb2 0xe8 0x00 0xf0 + # CHECK: risbg %r0, %r0, 0, 0, 0 0xec 0x00 0x00 0x00 0x00 0x55 @@ -8062,6 +8116,93 @@ # CHECK: sy %r15, 0 0xe3 0xf0 0x00 0x00 0x00 0x5b +# CHECK: tabort 0 +0xb2 0xfc 0x00 0x00 + +# CHECK: tabort 0(%r1) +0xb2 0xfc 0x10 0x00 + +# CHECK: tabort 0(%r15) +0xb2 0xfc 0xf0 0x00 + +# CHECK: tabort 4095 +0xb2 0xfc 0x0f 0xff + +# CHECK: tabort 4095(%r1) +0xb2 0xfc 0x1f 0xff + +# CHECK: tabort 4095(%r15) +0xb2 0xfc 0xff 0xff + +# CHECK: tbegin 0, 0 +0xe5 0x60 0x00 0x00 0x00 0x00 + +# CHECK: tbegin 4095, 0 +0xe5 0x60 0x0f 0xff 0x00 0x00 + +# CHECK: tbegin 0, 0 +0xe5 0x60 0x00 0x00 0x00 0x00 + +# CHECK: tbegin 0, 1 +0xe5 0x60 0x00 0x00 0x00 0x01 + +# CHECK: tbegin 0, 32767 +0xe5 0x60 0x00 0x00 0x7f 0xff + +# CHECK: tbegin 0, 32768 +0xe5 0x60 0x00 0x00 0x80 0x00 + +# CHECK: tbegin 0, 65535 +0xe5 0x60 0x00 0x00 0xff 0xff + +# CHECK: tbegin 0(%r1), 42 +0xe5 0x60 0x10 0x00 0x00 0x2a + +# CHECK: tbegin 0(%r15), 42 +0xe5 0x60 0xf0 0x00 0x00 0x2a + +# CHECK: tbegin 4095(%r1), 42 +0xe5 0x60 0x1f 0xff 0x00 0x2a + +# CHECK: tbegin 4095(%r15), 42 +0xe5 0x60 0xff 0xff 0x00 0x2a + +# CHECK: tbeginc 0, 0 +0xe5 0x61 0x00 0x00 0x00 0x00 + +# CHECK: tbeginc 4095, 0 +0xe5 0x61 0x0f 0xff 0x00 0x00 + +# CHECK: tbeginc 0, 0 +0xe5 0x61 0x00 0x00 0x00 0x00 + +# CHECK: tbeginc 0, 1 +0xe5 0x61 0x00 0x00 0x00 0x01 + +# CHECK: tbeginc 0, 32767 +0xe5 0x61 0x00 0x00 0x7f 0xff + +# CHECK: tbeginc 0, 32768 +0xe5 0x61 0x00 0x00 0x80 0x00 + +# CHECK: tbeginc 0, 65535 +0xe5 0x61 0x00 0x00 0xff 0xff + +# CHECK: tbeginc 0(%r1), 42 +0xe5 0x61 0x10 0x00 0x00 0x2a + +# CHECK: tbeginc 0(%r15), 42 +0xe5 0x61 0xf0 0x00 0x00 0x2a + +# CHECK: tbeginc 4095(%r1), 42 +0xe5 0x61 0x1f 0xff 0x00 0x2a + +# CHECK: tbeginc 4095(%r15), 42 +0xe5 0x61 0xff 0xff 0x00 0x2a + +# CHECK: tend +0xb2 0xf8 0x00 0x00 + # CHECK: tm 0, 0 0x91 0x00 0x00 0x00 llvm-svn: 233803
2015-04-01 20:51:43 +08:00
//===----------------------------------------------------------------------===//
// Transactional execution
//===----------------------------------------------------------------------===//
let Predicates = [FeatureTransactionalExecution] in {
// Transaction Begin
let hasSideEffects = 1, mayStore = 1,
usesCustomInserter = 1, Defs = [CC] in {
def TBEGIN : InstSIL<0xE560,
(outs), (ins bdaddr12only:$BD1, imm32zx16:$I2),
"tbegin\t$BD1, $I2",
[(z_tbegin bdaddr12only:$BD1, imm32zx16:$I2)]>;
def TBEGIN_nofloat : Pseudo<(outs), (ins bdaddr12only:$BD1, imm32zx16:$I2),
[(z_tbegin_nofloat bdaddr12only:$BD1,
imm32zx16:$I2)]>;
def TBEGINC : InstSIL<0xE561,
(outs), (ins bdaddr12only:$BD1, imm32zx16:$I2),
"tbeginc\t$BD1, $I2",
[(int_s390_tbeginc bdaddr12only:$BD1,
imm32zx16:$I2)]>;
}
// Transaction End
let hasSideEffects = 1, Defs = [CC], BD2 = 0 in
def TEND : InstS<0xB2F8, (outs), (ins), "tend", [(z_tend)]>;
// Transaction Abort
let hasSideEffects = 1, isTerminator = 1, isBarrier = 1 in
def TABORT : InstS<0xB2FC, (outs), (ins bdaddr12only:$BD2),
"tabort\t$BD2",
[(int_s390_tabort bdaddr12only:$BD2)]>;
// Nontransactional Store
let hasSideEffects = 1 in
def NTSTG : StoreRXY<"ntstg", 0xE325, int_s390_ntstg, GR64, 8>;
// Extract Transaction Nesting Depth
let hasSideEffects = 1 in
def ETND : InherentRRE<"etnd", 0xB2EC, GR32, (int_s390_etnd)>;
}
//===----------------------------------------------------------------------===//
// Processor assist
//===----------------------------------------------------------------------===//
let Predicates = [FeatureProcessorAssist] in {
let hasSideEffects = 1, R4 = 0 in
def PPA : InstRRF<0xB2E8, (outs), (ins GR64:$R1, GR64:$R2, imm32zx4:$R3),
"ppa\t$R1, $R2, $R3", []>;
def : Pat<(int_s390_ppa_txassist GR32:$src),
(PPA (INSERT_SUBREG (i64 (IMPLICIT_DEF)), GR32:$src, subreg_l32),
0, 1)>;
}
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
//===----------------------------------------------------------------------===//
// Miscellaneous Instructions.
//===----------------------------------------------------------------------===//
[SystemZ] Add a definition of the IPM instruction llvm-svn: 188161
2013-08-12 18:05:58 +08:00
// Extract CC into bits 29 and 28 of a register.
let Uses = [CC] in
[SystemZ] Use CLC and IPM to implement memcmp For now this is restricted to fixed-length comparisons with a length in the range [1, 256], as for memcpy() and MVC. llvm-svn: 188163
2013-08-12 18:28:10 +08:00
def IPM : InherentRRE<"ipm", 0xB222, GR32, (z_ipm)>;
[SystemZ] Add a definition of the IPM instruction llvm-svn: 188161
2013-08-12 18:05:58 +08:00
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Read a 32-bit access register into a GR32. As with all GR32 operations,
// the upper 32 bits of the enclosing GR64 remain unchanged, which is useful
// when a 64-bit address is stored in a pair of access registers.
[SystemZ] Match operands to fields by name rather than by order The SystemZ port currently relies on the order of the instruction operands matching the order of the instruction field lists. This isn't desirable for disassembly, where the two are matched only by name. E.g. the R1 and R2 fields of an RR instruction should have corresponding R1 and R2 operands. The main complication is that addresses are compound operands, and as far as I know there is no mechanism to allow individual suboperands to be selected by name in "let Inst{...} = ..." assignments. Luckily it doesn't really matter though. The SystemZ instruction encoding groups all address fields together in a predictable order, so it's just as valid to see the entire compound address operand as a single field. That's the approach taken in this patch. Matching by name in turn means that the operands to COPY SIGN and CONVERT TO FIXED instructions can be given in natural order. (It was easier to do this at the same time as the rename, since otherwise the intermediate step was too confusing.) No functional change intended. llvm-svn: 181769
2013-05-14 17:28:21 +08:00
def EAR : InstRRE<0xB24F, (outs GR32:$R1), (ins access_reg:$R2),
"ear\t$R1, $R2",
[(set GR32:$R1, (z_extract_access access_reg:$R2))]>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Find leftmost one, AKA count leading zeros. The instruction actually
// returns a pair of GR64s, the first giving the number of leading zeros
// and the second giving a copy of the source with the leftmost one bit
// cleared. We only use the first result here.
[SystemZ] Rename PSW to CC Addresses a review comment from Ulrich Weigand. No functional change intended. I'm not sure whether the old TODO that this patch touches still holds, but that's something we'd get to when adding a targetted scheduling description. llvm-svn: 182474
2013-05-22 21:38:45 +08:00
let Defs = [CC] in {
[SystemZ] Fold more spills Add a mapping from register-based <INSN>R instructions to the corresponding memory-based <INSN>. Use it to cut down on the number of spill loads. Some instructions extend their operands from smaller fields, so this required a new TSFlags field to say how big the unextended operand is. This optimisation doesn't trigger for C(G)R and CL(G)R because in practice we always combine those instructions with a branch. Adding a test for every other case probably seems excessive, but it did catch a missed optimisation for DSGF (fixed in r185435). llvm-svn: 185529
2013-07-03 18:10:02 +08:00
def FLOGR : UnaryRRE<"flog", 0xB983, null_frag, GR128, GR64>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
}
def : Pat<(ctlz GR64:$src),
[SystemZ] Rename subregs and add subreg_h32 Use subreg_hNN and subreg_lNN for the high and low NN bits of a register. List the low registers first, so that subreg_l32 also means the low 32 bits of a 128-bit register. Floats are stored in the upper 32 bits of a 64-bit register, so they should use subreg_h32 rather than subreg_l32. No behavioral change intended. llvm-svn: 191659
2013-09-30 18:28:35 +08:00
(EXTRACT_SUBREG (FLOGR GR64:$src), subreg_h64)>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
[SystemZ] Use POPCNT instruction on z196 We already exploit a number of instructions specific to z196, but not yet POPCNT. Add support for the population-count facility, MC support for the POPCNT instruction, CodeGen support for using POPCNT, and implement the getPopcntSupport TargetTransformInfo hook. llvm-svn: 233689
2015-03-31 20:56:33 +08:00
// Population count. Counts bits set per byte.
let Predicates = [FeaturePopulationCount], Defs = [CC] in {
def POPCNT : InstRRE<0xB9E1, (outs GR64:$R1), (ins GR64:$R2),
"popcnt\t$R1, $R2",
[(set GR64:$R1, (z_popcnt GR64:$R2))]>;
}
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Use subregs to populate the "don't care" bits in a 32-bit to 64-bit anyext.
def : Pat<(i64 (anyext GR32:$src)),
[SystemZ] Rename subregs and add subreg_h32 Use subreg_hNN and subreg_lNN for the high and low NN bits of a register. List the low registers first, so that subreg_l32 also means the low 32 bits of a 128-bit register. Floats are stored in the upper 32 bits of a 64-bit register, so they should use subreg_h32 rather than subreg_l32. No behavioral change intended. llvm-svn: 191659
2013-09-30 18:28:35 +08:00
(INSERT_SUBREG (i64 (IMPLICIT_DEF)), GR32:$src, subreg_l32)>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
// Extend GR32s and GR64s to GR128s.
let usesCustomInserter = 1 in {
def AEXT128_64 : Pseudo<(outs GR128:$dst), (ins GR64:$src), []>;
def ZEXT128_32 : Pseudo<(outs GR128:$dst), (ins GR32:$src), []>;
def ZEXT128_64 : Pseudo<(outs GR128:$dst), (ins GR64:$src), []>;
}
[SystemZ] Use SRST to implement strlen and strnlen It would also make sense to use it for memchr; I'm working on that now. llvm-svn: 188547
2013-08-16 19:41:43 +08:00
// Search a block of memory for a character.
[SystemZ] Rename 32-bit GPR registers I'm about to add support for high-word operations, so it seemed better for the low-word registers to have names like R0L rather than R0W. No behavioral change intended. llvm-svn: 191655
2013-09-30 16:48:38 +08:00
let mayLoad = 1, Defs = [CC], Uses = [R0L] in
[SystemZ] Use SRST to implement strlen and strnlen It would also make sense to use it for memchr; I'm working on that now. llvm-svn: 188547
2013-08-16 19:41:43 +08:00
defm SRST : StringRRE<"srst", 0xb25e, z_search_string>;
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
//===----------------------------------------------------------------------===//
// Peepholes.
//===----------------------------------------------------------------------===//
// Use AL* for GR64 additions of unsigned 32-bit values.
defm : ZXB<add, GR64, ALGFR>;
def : Pat<(add GR64:$src1, imm64zx32:$src2),
(ALGFI GR64:$src1, imm64zx32:$src2)>;
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
def : Pat<(add GR64:$src1, (azextloadi32 bdxaddr20only:$addr)),
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
(ALGF GR64:$src1, bdxaddr20only:$addr)>;
// Use SL* for GR64 subtractions of unsigned 32-bit values.
defm : ZXB<sub, GR64, SLGFR>;
def : Pat<(add GR64:$src1, imm64zx32n:$src2),
(SLGFI GR64:$src1, imm64zx32n:$src2)>;
[SystemZ] Improve extload handling The port originally had special patterns for extload, mapping them to the same instructions as sextload. It seemed neater to have patterns that match "an extension that is allowed to be signed" and "an extension that is allowed to be unsigned". This was originally meant to be a clean-up, but it does improve the handling of promoted integers a little, as shown by args-06.ll. llvm-svn: 190777
2013-09-16 17:03:10 +08:00
def : Pat<(sub GR64:$src1, (azextloadi32 bdxaddr20only:$addr)),
[SystemZ] Add back end This adds the actual lib/Target/SystemZ target files necessary to implement the SystemZ target. Note that at this point, the target cannot yet be built since the configure bits are missing. Those will be provided shortly by a follow-on patch. This version of the patch incorporates feedback from reviews by Chris Lattner and Anton Korobeynikov. Thanks to all reviewers! Patch by Richard Sandiford. llvm-svn: 181203
2013-05-07 00:15:19 +08:00
(SLGF GR64:$src1, bdxaddr20only:$addr)>;
[SystemZ] Optimize sign-extends of vector setccs Normal (sext (setcc ...)) sequences are optimised into (select_cc ..., -1, 0) by DAGCombiner::visitSIGN_EXTEND. However, this is deliberately not done for vectors, and after vector type legalization we have (sext_inreg (setcc ...)) instead. I wondered about trying to extend DAGCombiner to handle this case too, but it seemed to be a loss on some other targets I tried, even those for which SETCC isn't "legal" and SELECT_CC is. llvm-svn: 186149
2013-07-12 17:17:10 +08:00
// Optimize sign-extended 1/0 selects to -1/0 selects. This is important
// for vector legalization.
[SystemZ] Avoid using i8 constants for immediate fields Immediate fields that have no natural MVT type tended to use i8 if the field was small enough. This was a bit confusing since i8 isn't a legal type for the target. Fields for short immediates in a 32-bit or 64-bit operation use i32 or i64 instead, so it would be better to do the same for all fields. No behavioral change intended. llvm-svn: 212702
2014-07-10 18:52:51 +08:00
def : Pat<(sra (shl (i32 (z_select_ccmask 1, 0, imm32zx4:$valid, imm32zx4:$cc)),
[SystemZ] Be more careful about inverting CC masks System z branches have a mask to select which of the 4 CC values should cause the branch to be taken. We can invert a branch by inverting the mask. However, not all instructions can produce all 4 CC values, so inverting the branch like this can lead to some oddities. For example, integer comparisons only produce a CC of 0 (equal), 1 (less) or 2 (greater). If an integer EQ is reversed to NE before instruction selection, the branch will test for 1 or 2. If instead the branch is reversed after instruction selection (by inverting the mask), it will test for 1, 2 or 3. Both are correct, but the second isn't really canonical. This patch therefore keeps track of which CC values are possible and uses this when inverting a mask. Although this is mostly cosmestic, it fixes undefined behavior for the CIJNLH in branch-08.ll. Another fix would have been to mask out bit 0 when generating the fused compare and branch, but the point of this patch is that we shouldn't need to do that in the first place. The patch also makes it easier to reuse CC results from other instructions. llvm-svn: 187495
2013-07-31 20:30:20 +08:00
(i32 31)),
(i32 31)),
[SystemZ] Avoid using i8 constants for immediate fields Immediate fields that have no natural MVT type tended to use i8 if the field was small enough. This was a bit confusing since i8 isn't a legal type for the target. Fields for short immediates in a 32-bit or 64-bit operation use i32 or i64 instead, so it would be better to do the same for all fields. No behavioral change intended. llvm-svn: 212702
2014-07-10 18:52:51 +08:00
(Select32 (LHI -1), (LHI 0), imm32zx4:$valid, imm32zx4:$cc)>;
def : Pat<(sra (shl (i64 (anyext (i32 (z_select_ccmask 1, 0, imm32zx4:$valid,
imm32zx4:$cc)))),
[SystemZ] Optimize sign-extends of vector setccs Normal (sext (setcc ...)) sequences are optimised into (select_cc ..., -1, 0) by DAGCombiner::visitSIGN_EXTEND. However, this is deliberately not done for vectors, and after vector type legalization we have (sext_inreg (setcc ...)) instead. I wondered about trying to extend DAGCombiner to handle this case too, but it seemed to be a loss on some other targets I tried, even those for which SETCC isn't "legal" and SELECT_CC is. llvm-svn: 186149
2013-07-12 17:17:10 +08:00
(i32 63)),
(i32 63)),
[SystemZ] Avoid using i8 constants for immediate fields Immediate fields that have no natural MVT type tended to use i8 if the field was small enough. This was a bit confusing since i8 isn't a legal type for the target. Fields for short immediates in a 32-bit or 64-bit operation use i32 or i64 instead, so it would be better to do the same for all fields. No behavioral change intended. llvm-svn: 212702
2014-07-10 18:52:51 +08:00
(Select64 (LGHI -1), (LGHI 0), imm32zx4:$valid, imm32zx4:$cc)>;
[SystemZ] Add NC, OC and XC For now these are just used to handle scalar ANDs, ORs and XORs in which all operands are memory. llvm-svn: 190041
2013-09-05 18:36:45 +08:00
// Peepholes for turning scalar operations into block operations.
defm : BlockLoadStore<anyextloadi8, i32, MVCSequence, NCSequence, OCSequence,
XCSequence, 1>;
defm : BlockLoadStore<anyextloadi16, i32, MVCSequence, NCSequence, OCSequence,
XCSequence, 2>;
defm : BlockLoadStore<load, i32, MVCSequence, NCSequence, OCSequence,
XCSequence, 4>;
defm : BlockLoadStore<anyextloadi8, i64, MVCSequence, NCSequence,
OCSequence, XCSequence, 1>;
defm : BlockLoadStore<anyextloadi16, i64, MVCSequence, NCSequence, OCSequence,
XCSequence, 2>;
defm : BlockLoadStore<anyextloadi32, i64, MVCSequence, NCSequence, OCSequence,
XCSequence, 4>;
defm : BlockLoadStore<load, i64, MVCSequence, NCSequence, OCSequence,
XCSequence, 8>;