maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/Mips/longbranch.ll

176 lines
6.5 KiB
LLVM
Raw Normal View History

[mips] Make Static a default relocation model for MIPS codegen This change follows up defaults for GCC and Clang, so LLVM does not differ from them. While number of the test files are touched with this change, they all keep the old (expected) behaviour with the explicit option: "-relocation-model=pic" The tests that have not been touched are insensitive to relocation model. Differential Revision: http://reviews.llvm.org/D17995 llvm-svn: 265949
2016-04-11 23:24:23 +08:00
; RUN: llc -march=mipsel -relocation-model=pic < %s | FileCheck %s
; RUN: llc -march=mipsel -force-mips-long-branch -O3 -relocation-model=pic < %s \
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
; RUN: | FileCheck %s -check-prefix=O32
[mips] Emit a JALR with $rd equal to $zero, instead of a JR in MIPS32R6. Summary: JR is an alias of JALR with $rd=0 in the R6 ISA. Also, this fixes recursive builds in MIPS32R6. Reviewers: dsanders, sdardis Subscribers: jfb, dschuff, dsanders, sdardis, llvm-commits Differential Revision: http://reviews.llvm.org/D21370 llvm-svn: 273085
2016-06-18 23:39:43 +08:00
; RUN: llc -march=mipsel -mcpu=mips32r6 -force-mips-long-branch -O3 \
; RUN: -relocation-model=pic -asm-show-inst < %s | FileCheck %s -check-prefix=O32-R6
[mips] Make Static a default relocation model for MIPS codegen This change follows up defaults for GCC and Clang, so LLVM does not differ from them. While number of the test files are touched with this change, they all keep the old (expected) behaviour with the explicit option: "-relocation-model=pic" The tests that have not been touched are insensitive to relocation model. Differential Revision: http://reviews.llvm.org/D17995 llvm-svn: 265949
2016-04-11 23:24:23 +08:00
; RUN: llc -march=mips64el -mcpu=mips4 -target-abi=n64 -force-mips-long-branch -O3 -relocation-model=pic \
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
; RUN: < %s | FileCheck %s -check-prefix=N64
[mips] Make Static a default relocation model for MIPS codegen This change follows up defaults for GCC and Clang, so LLVM does not differ from them. While number of the test files are touched with this change, they all keep the old (expected) behaviour with the explicit option: "-relocation-model=pic" The tests that have not been touched are insensitive to relocation model. Differential Revision: http://reviews.llvm.org/D17995 llvm-svn: 265949
2016-04-11 23:24:23 +08:00
; RUN: llc -march=mips64el -mcpu=mips64 -target-abi=n64 -force-mips-long-branch -O3 -relocation-model=pic \
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
; RUN: < %s | FileCheck %s -check-prefix=N64
[mips] Emit a JALR with $rd equal to $zero, instead of a JR in MIPS32R6. Summary: JR is an alias of JALR with $rd=0 in the R6 ISA. Also, this fixes recursive builds in MIPS32R6. Reviewers: dsanders, sdardis Subscribers: jfb, dschuff, dsanders, sdardis, llvm-commits Differential Revision: http://reviews.llvm.org/D21370 llvm-svn: 273085
2016-06-18 23:39:43 +08:00
; RUN: llc -march=mips64el -mcpu=mips64r6 -target-abi=n64 -force-mips-long-branch -O3 \
; RUN: -relocation-model=pic -asm-show-inst < %s | FileCheck %s -check-prefix=N64-R6
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
; RUN: llc -march=mipsel -mcpu=mips32r2 -mattr=micromips \
[mips] Make Static a default relocation model for MIPS codegen This change follows up defaults for GCC and Clang, so LLVM does not differ from them. While number of the test files are touched with this change, they all keep the old (expected) behaviour with the explicit option: "-relocation-model=pic" The tests that have not been touched are insensitive to relocation model. Differential Revision: http://reviews.llvm.org/D17995 llvm-svn: 265949
2016-04-11 23:24:23 +08:00
; RUN: -force-mips-long-branch -O3 -relocation-model=pic < %s | FileCheck %s -check-prefix=MICROMIPS
; RUN: llc -mtriple=mipsel-none-nacl -force-mips-long-branch -O3 -relocation-model=pic < %s \
[mips] Modify long branch for NaCl: * Move the instruction that changes sp outside of the branch delay slot. * Bundle-align the target of indirect branch. Differential Revision: http://llvm-reviews.chandlerc.com/D3928 llvm-svn: 210262
2014-06-05 21:52:08 +08:00
; RUN: | FileCheck %s -check-prefix=NACL
Test case for MIPS long branch pass. llvm-svn: 158438
2012-06-14 10:12:21 +08:00
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
@x = external global i32
[mips] Promote i32 arguments to i64 for the N32/N64 ABI and fix <64-bit structs... Summary: ... and after all that refactoring, it's possible to distinguish softfloat floating point values from integers so this patch no longer breaks softfloat to do it. Remove direct handling of i32's in the N32/N64 ABI by promoting them to i64. This more closely reflects the ABI documentation and also fixes problems with stack arguments on big-endian targets. We now rely on signext/zeroext annotations (already generated by clang) and the Assert[SZ]ext nodes to avoid the introduction of unnecessary sign/zero extends. It was not possible to convert three tests to use signext/zeroext. These tests are bswap.ll, ctlz-v.ll, ctlz-v.ll. It's not possible to put signext on a vector type so we just accept the sign extends here for now. These tests don't pass the vectors the same way clang does (clang puts multiple elements in the same argument, these map 1 element to 1 argument) so we don't need to worry too much about it. With this patch, all known N32/N64 bugs should be fixed and we now pass the first 10,000 tests generated by ABITest.py. Subscribers: llvm-commits Differential Revision: http://reviews.llvm.org/D6117 llvm-svn: 221534
2014-11-08 00:54:21 +08:00
define void @test1(i32 signext %s) {
Test case for MIPS long branch pass. llvm-svn: 158438
2012-06-14 10:12:21 +08:00
entry:
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
%cmp = icmp eq i32 %s, 0
br i1 %cmp, label %end, label %then
then:
store i32 1, i32* @x, align 4
br label %end
end:
Test case for MIPS long branch pass. llvm-svn: 158438
2012-06-14 10:12:21 +08:00
ret void
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
; First check the normal version (without long branch). beqz jumps to return,
; and fallthrough block stores 1 to global variable.
; CHECK: lui $[[R0:[0-9]+]], %hi(_gp_disp)
; CHECK: addiu $[[R0]], $[[R0]], %lo(_gp_disp)
Revert r237789 - [mips] The naming convention for private labels is ABI dependant. It works, but I've noticed that I missed several callers of createMCAsmInfo() and many don't have a TargetMachine to provide. llvm-svn: 237792
2015-05-20 22:18:59 +08:00
; CHECK: beqz $4, $[[BB0:BB[0-9_]+]]
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
; CHECK: addu $[[GP:[0-9]+]], $[[R0]], $25
; CHECK: lw $[[R1:[0-9]+]], %got(x)($[[GP]])
; CHECK: addiu $[[R2:[0-9]+]], $zero, 1
; CHECK: sw $[[R2]], 0($[[R1]])
Revert r237789 - [mips] The naming convention for private labels is ABI dependant. It works, but I've noticed that I missed several callers of createMCAsmInfo() and many don't have a TargetMachine to provide. llvm-svn: 237792
2015-05-20 22:18:59 +08:00
; CHECK: $[[BB0]]:
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
; CHECK: jr $ra
; CHECK: nop
; Check the MIPS32 version. Check that branch logic is inverted, so that the
; target of the new branch (bnez) is the fallthrough block of the original
; branch. Check that fallthrough block of the new branch contains long branch
; expansion which at the end indirectly jumps to the target of the original
; branch.
; O32: lui $[[R0:[0-9]+]], %hi(_gp_disp)
; O32: addiu $[[R0]], $[[R0]], %lo(_gp_disp)
Revert r237789 - [mips] The naming convention for private labels is ABI dependant. It works, but I've noticed that I missed several callers of createMCAsmInfo() and many don't have a TargetMachine to provide. llvm-svn: 237792
2015-05-20 22:18:59 +08:00
; O32: bnez $4, $[[BB0:BB[0-9_]+]]
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
; O32: addu $[[GP:[0-9]+]], $[[R0]], $25
; Check for long branch expansion:
; O32: addiu $sp, $sp, -8
; O32-NEXT: sw $ra, 0($sp)
Revert r237789 - [mips] The naming convention for private labels is ABI dependant. It works, but I've noticed that I missed several callers of createMCAsmInfo() and many don't have a TargetMachine to provide. llvm-svn: 237792
2015-05-20 22:18:59 +08:00
; O32-NEXT: lui $1, %hi(($[[BB2:BB[0-9_]+]])-($[[BB1:BB[0-9_]+]]))
; O32-NEXT: bal $[[BB1]]
; O32-NEXT: addiu $1, $1, %lo(($[[BB2]])-($[[BB1]]))
; O32-NEXT: $[[BB1]]:
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
; O32-NEXT: addu $1, $ra, $1
; O32-NEXT: lw $ra, 0($sp)
; O32-NEXT: jr $1
; O32-NEXT: addiu $sp, $sp, 8
Revert r237789 - [mips] The naming convention for private labels is ABI dependant. It works, but I've noticed that I missed several callers of createMCAsmInfo() and many don't have a TargetMachine to provide. llvm-svn: 237792
2015-05-20 22:18:59 +08:00
; O32: $[[BB0]]:
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
; O32: lw $[[R1:[0-9]+]], %got(x)($[[GP]])
; O32: addiu $[[R2:[0-9]+]], $zero, 1
; O32: sw $[[R2]], 0($[[R1]])
Revert r237789 - [mips] The naming convention for private labels is ABI dependant. It works, but I've noticed that I missed several callers of createMCAsmInfo() and many don't have a TargetMachine to provide. llvm-svn: 237792
2015-05-20 22:18:59 +08:00
; O32: $[[BB2]]:
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
; O32: jr $ra
; O32: nop
[mips] Emit a JALR with $rd equal to $zero, instead of a JR in MIPS32R6. Summary: JR is an alias of JALR with $rd=0 in the R6 ISA. Also, this fixes recursive builds in MIPS32R6. Reviewers: dsanders, sdardis Subscribers: jfb, dschuff, dsanders, sdardis, llvm-commits Differential Revision: http://reviews.llvm.org/D21370 llvm-svn: 273085
2016-06-18 23:39:43 +08:00
; In MIPS32R6 JR is an alias to JALR with $rd=0. As everything else remains the
; same with the O32 prefix, we use -asm-show-inst in order to make sure that
; the opcode of the MachineInst is a JALR.
; O32-R6: JALR
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
; Check the MIPS64 version.
; N64: lui $[[R0:[0-9]+]], %hi(%neg(%gp_rel(test1)))
[mips] Correct label prefixes for N32 and N64. Summary: N32 and N64 follow the standard ELF conventions (.L) whereas O32 uses its own ($). This fixes the majority of object differences between -fintegrated-as and -fno-integrated-as. Reviewers: sdardis Subscribers: dsanders, sdardis, llvm-commits Differential Revision: https://reviews.llvm.org/D22412 llvm-svn: 275967
2016-07-19 18:49:03 +08:00
; N64: bnez $4, [[BB0:\.LBB[0-9_]+]]
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
; N64: daddu $[[R1:[0-9]+]], $[[R0]], $25
; Check for long branch expansion:
; N64: daddiu $sp, $sp, -16
; N64-NEXT: sd $ra, 0($sp)
[mips] Correct label prefixes for N32 and N64. Summary: N32 and N64 follow the standard ELF conventions (.L) whereas O32 uses its own ($). This fixes the majority of object differences between -fintegrated-as and -fno-integrated-as. Reviewers: sdardis Subscribers: dsanders, sdardis, llvm-commits Differential Revision: https://reviews.llvm.org/D22412 llvm-svn: 275967
2016-07-19 18:49:03 +08:00
; N64-NEXT: daddiu $1, $zero, %hi([[BB2:\.LBB[0-9_]+]]-[[BB1:\.LBB[0-9_]+]])
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
; N64-NEXT: dsll $1, $1, 16
[mips] Correct label prefixes for N32 and N64. Summary: N32 and N64 follow the standard ELF conventions (.L) whereas O32 uses its own ($). This fixes the majority of object differences between -fintegrated-as and -fno-integrated-as. Reviewers: sdardis Subscribers: dsanders, sdardis, llvm-commits Differential Revision: https://reviews.llvm.org/D22412 llvm-svn: 275967
2016-07-19 18:49:03 +08:00
; N64-NEXT: bal [[BB1]]
; N64-NEXT: daddiu $1, $1, %lo([[BB2]]-[[BB1]])
; N64-NEXT: [[BB1]]:
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
; N64-NEXT: daddu $1, $ra, $1
; N64-NEXT: ld $ra, 0($sp)
; N64-NEXT: jr $1
; N64-NEXT: daddiu $sp, $sp, 16
[mips] Correct label prefixes for N32 and N64. Summary: N32 and N64 follow the standard ELF conventions (.L) whereas O32 uses its own ($). This fixes the majority of object differences between -fintegrated-as and -fno-integrated-as. Reviewers: sdardis Subscribers: dsanders, sdardis, llvm-commits Differential Revision: https://reviews.llvm.org/D22412 llvm-svn: 275967
2016-07-19 18:49:03 +08:00
; N64: [[BB0]]:
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
; N64: daddiu $[[GP:[0-9]+]], $[[R1]], %lo(%neg(%gp_rel(test1)))
; N64: addiu $[[R3:[0-9]+]], $zero, 1
[mips] interAptiv based generic schedule model This scheduler describes a processor which covers all MIPS ISAs based around the interAptiv and P5600 timings. Reviewers: vkalintiris, dsanders Differential Revision: https://reviews.llvm.org/D23551 llvm-svn: 280374
2016-09-01 22:53:53 +08:00
; N64: ld $[[R2:[0-9]+]], %got_disp(x)($[[GP]])
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
; N64: sw $[[R3]], 0($[[R2]])
[mips] Correct label prefixes for N32 and N64. Summary: N32 and N64 follow the standard ELF conventions (.L) whereas O32 uses its own ($). This fixes the majority of object differences between -fintegrated-as and -fno-integrated-as. Reviewers: sdardis Subscribers: dsanders, sdardis, llvm-commits Differential Revision: https://reviews.llvm.org/D22412 llvm-svn: 275967
2016-07-19 18:49:03 +08:00
; N64: [[BB2]]:
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
; N64: jr $ra
; N64: nop
[mips] Emit a JALR with $rd equal to $zero, instead of a JR in MIPS32R6. Summary: JR is an alias of JALR with $rd=0 in the R6 ISA. Also, this fixes recursive builds in MIPS32R6. Reviewers: dsanders, sdardis Subscribers: jfb, dschuff, dsanders, sdardis, llvm-commits Differential Revision: http://reviews.llvm.org/D21370 llvm-svn: 273085
2016-06-18 23:39:43 +08:00
; In MIPS64R6 JR is an alias to JALR with $rd=0. As everything else remains the
; same with the N64 prefix, we use -asm-show-inst in order to make sure that
; the opcode of the MachineInst is a JALR.
; N64-R6: JALR64
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
; Check the microMIPS version.
; MICROMIPS: lui $[[R0:[0-9]+]], %hi(_gp_disp)
; MICROMIPS: addiu $[[R0]], $[[R0]], %lo(_gp_disp)
Revert r237789 - [mips] The naming convention for private labels is ABI dependant. It works, but I've noticed that I missed several callers of createMCAsmInfo() and many don't have a TargetMachine to provide. llvm-svn: 237792
2015-05-20 22:18:59 +08:00
; MICROMIPS: bnez $4, $[[BB0:BB[0-9_]+]]
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
; MICROMIPS: addu $[[GP:[0-9]+]], $[[R0]], $25
; Check for long branch expansion:
; MICROMIPS: addiu $sp, $sp, -8
; MICROMIPS-NEXT: sw $ra, 0($sp)
Revert r237789 - [mips] The naming convention for private labels is ABI dependant. It works, but I've noticed that I missed several callers of createMCAsmInfo() and many don't have a TargetMachine to provide. llvm-svn: 237792
2015-05-20 22:18:59 +08:00
; MICROMIPS-NEXT: lui $1, %hi(($[[BB2:BB[0-9_]+]])-($[[BB1:BB[0-9_]+]]))
; MICROMIPS-NEXT: bal $[[BB1]]
; MICROMIPS-NEXT: addiu $1, $1, %lo(($[[BB2]])-($[[BB1]]))
; MICROMIPS-NEXT: $[[BB1]]:
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
; MICROMIPS-NEXT: addu $1, $ra, $1
; MICROMIPS-NEXT: lw $ra, 0($sp)
; MICROMIPS-NEXT: jr $1
; MICROMIPS-NEXT: addiu $sp, $sp, 8
Revert r237789 - [mips] The naming convention for private labels is ABI dependant. It works, but I've noticed that I missed several callers of createMCAsmInfo() and many don't have a TargetMachine to provide. llvm-svn: 237792
2015-05-20 22:18:59 +08:00
; MICROMIPS: $[[BB0]]:
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
; MICROMIPS: lw $[[R1:[0-9]+]], %got(x)($[[GP]])
[mips][microMIPS] Implement CodeGen support for LI16 instruction. Differential Revision: http://reviews.llvm.org/D5840 llvm-svn: 224017
2014-12-11 21:56:23 +08:00
; MICROMIPS: li16 $[[R2:[0-9]+]], 1
[mips][microMIPS] Implement CodeGen support for SW16 and LW16 instructions Differential Revision: http://reviews.llvm.org/D6581 llvm-svn: 228149
2015-02-04 23:43:17 +08:00
; MICROMIPS: sw16 $[[R2]], 0($[[R1]])
Revert r237789 - [mips] The naming convention for private labels is ABI dependant. It works, but I've noticed that I missed several callers of createMCAsmInfo() and many don't have a TargetMachine to provide. llvm-svn: 237792
2015-05-20 22:18:59 +08:00
; MICROMIPS: $[[BB2]]:
[mips][microMIPS] Delay slot filler: Replace the microMIPS JR with the JRC This patch adds functionality in MIPS delay slot filler such as if delay slot filler have to put NOP instruction into the delay slot of microMIPS JR instruction, then instead of emitting NOP this instruction is replaced by compact jump instruction JRC. Differential Revision: http://reviews.llvm.org/D7522 llvm-svn: 229128
2015-02-14 01:51:27 +08:00
; MICROMIPS: jrc $ra
[mips] Modify long branch for NaCl: * Move the instruction that changes sp outside of the branch delay slot. * Bundle-align the target of indirect branch. Differential Revision: http://llvm-reviews.chandlerc.com/D3928 llvm-svn: 210262
2014-06-05 21:52:08 +08:00
; Check the NaCl version. Check that sp change is not in the branch delay slot
; of "jr $1" instruction. Check that target of indirect branch "jr $1" is
; bundle aligned.
; NACL: lui $[[R0:[0-9]+]], %hi(_gp_disp)
; NACL: addiu $[[R0]], $[[R0]], %lo(_gp_disp)
Revert r237789 - [mips] The naming convention for private labels is ABI dependant. It works, but I've noticed that I missed several callers of createMCAsmInfo() and many don't have a TargetMachine to provide. llvm-svn: 237792
2015-05-20 22:18:59 +08:00
; NACL: bnez $4, $[[BB0:BB[0-9_]+]]
[mips] Modify long branch for NaCl: * Move the instruction that changes sp outside of the branch delay slot. * Bundle-align the target of indirect branch. Differential Revision: http://llvm-reviews.chandlerc.com/D3928 llvm-svn: 210262
2014-06-05 21:52:08 +08:00
; NACL: addu $[[GP:[0-9]+]], $[[R0]], $25
; Check for long branch expansion:
; NACL: addiu $sp, $sp, -8
; NACL-NEXT: sw $ra, 0($sp)
Revert r237789 - [mips] The naming convention for private labels is ABI dependant. It works, but I've noticed that I missed several callers of createMCAsmInfo() and many don't have a TargetMachine to provide. llvm-svn: 237792
2015-05-20 22:18:59 +08:00
; NACL-NEXT: lui $1, %hi(($[[BB2:BB[0-9_]+]])-($[[BB1:BB[0-9_]+]]))
; NACL-NEXT: bal $[[BB1]]
; NACL-NEXT: addiu $1, $1, %lo(($[[BB2]])-($[[BB1]]))
; NACL-NEXT: $[[BB1]]:
[mips] Modify long branch for NaCl: * Move the instruction that changes sp outside of the branch delay slot. * Bundle-align the target of indirect branch. Differential Revision: http://llvm-reviews.chandlerc.com/D3928 llvm-svn: 210262
2014-06-05 21:52:08 +08:00
; NACL-NEXT: addu $1, $ra, $1
; NACL-NEXT: lw $ra, 0($sp)
; NACL-NEXT: addiu $sp, $sp, 8
; NACL-NEXT: jr $1
; NACL-NEXT: nop
Revert r237789 - [mips] The naming convention for private labels is ABI dependant. It works, but I've noticed that I missed several callers of createMCAsmInfo() and many don't have a TargetMachine to provide. llvm-svn: 237792
2015-05-20 22:18:59 +08:00
; NACL: $[[BB0]]:
[mips] Modify long branch for NaCl: * Move the instruction that changes sp outside of the branch delay slot. * Bundle-align the target of indirect branch. Differential Revision: http://llvm-reviews.chandlerc.com/D3928 llvm-svn: 210262
2014-06-05 21:52:08 +08:00
; NACL: lw $[[R1:[0-9]+]], %got(x)($[[GP]])
; NACL: addiu $[[R2:[0-9]+]], $zero, 1
; NACL: sw $[[R2]], 0($[[R1]])
[MC] Use .p2align instead of .align For historic reasons, the behavior of .align differs between targets. Fortunately, there are alternatives, .p2align and .balign, which make the interpretation of the parameter explicit, and which behave consistently across targets. This patch teaches MC to use .p2align instead of .align, so that people reading code for multiple architectures don't have to remember which way each platform does its .align directive. Differential Revision: http://reviews.llvm.org/D16549 llvm-svn: 258750
2016-01-26 08:03:25 +08:00
; NACL: .p2align 4
Revert r237789 - [mips] The naming convention for private labels is ABI dependant. It works, but I've noticed that I missed several callers of createMCAsmInfo() and many don't have a TargetMachine to provide. llvm-svn: 237792
2015-05-20 22:18:59 +08:00
; NACL-NEXT: $[[BB2]]:
[mips] Modify long branch for NaCl: * Move the instruction that changes sp outside of the branch delay slot. * Bundle-align the target of indirect branch. Differential Revision: http://llvm-reviews.chandlerc.com/D3928 llvm-svn: 210262
2014-06-05 21:52:08 +08:00
; NACL: jr $ra
; NACL: nop
[mips] Fix MipsLongBranch pass to work when the offset from the branch to the target cannot be determined accurately. This is the case for NaCl where the sandboxing instructions are added in MC layer, after the MipsLongBranch pass. It is also the case when the code has inline assembly. Instead of calculating offset in the MipsLongBranch pass, use %hi(sym1 - sym2) and %lo(sym1 - sym2) expressions that are resolved during the fixup. This patch also deletes microMIPS test file test/CodeGen/Mips/micromips-long-branch.ll and implements microMIPS CHECKs in a much simpler way in a file test/CodeGen/Mips/longbranch.ll, together with MIPS32 and MIPS64. llvm-svn: 207656
2014-04-30 23:06:25 +08:00
}