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/AArch64/spill-undef.mir

68 lines
4.3 KiB
Plaintext
Raw Normal View History

[InlineSpiller] Don't spill fully undef values Althought it is not wrong to spill undef values, it is useless and harms both code size and runtime. Before spilling a value, check that its content actually matters. http://www.llvm.org/PR33311 llvm-svn: 304752
2017-06-06 07:51:27 +08:00
# RUN: llc %s -run-pass greedy -o - | FileCheck %s
# Check that we don't insert spill code for undef values.
# Uninitialized memory for them is fine.
# PR33311
--- |
; ModuleID = 'stuff.ll'
target triple = "aarch64--"
MIR: Print the register class or bank in vreg defs This updates the MIRPrinter to include the regclass when printing virtual register defs, which is already valid syntax for the parser. That is, given 64 bit %0 and %1 in a "gpr" regbank, %1(s64) = COPY %0(s64) would now be written as %1:gpr(s64) = COPY %0(s64) While this change alone introduces a bit of redundancy with the registers block, it allows us to update the tests to be more concise and understandable and brings us closer to being able to remove the registers block completely. Note: We generally only print the class in defs, but there is one exception. If there are uses without any defs whatsoever, we'll print the class on all uses. I'm not completely convinced this comes up in meaningful machine IR, but for now the MIRParser and MachineVerifier both accept that kind of stuff, so we don't want to have a situation where we can print something we can't parse. llvm-svn: 316479
2017-10-25 02:04:54 +08:00
[InlineSpiller] Don't spill fully undef values Althought it is not wrong to spill undef values, it is useless and harms both code size and runtime. Before spilling a value, check that its content actually matters. http://www.llvm.org/PR33311 llvm-svn: 304752
2017-06-06 07:51:27 +08:00
@g = external global i32
MIR: Print the register class or bank in vreg defs This updates the MIRPrinter to include the regclass when printing virtual register defs, which is already valid syntax for the parser. That is, given 64 bit %0 and %1 in a "gpr" regbank, %1(s64) = COPY %0(s64) would now be written as %1:gpr(s64) = COPY %0(s64) While this change alone introduces a bit of redundancy with the registers block, it allows us to update the tests to be more concise and understandable and brings us closer to being able to remove the registers block completely. Note: We generally only print the class in defs, but there is one exception. If there are uses without any defs whatsoever, we'll print the class on all uses. I'm not completely convinced this comes up in meaningful machine IR, but for now the MIRParser and MachineVerifier both accept that kind of stuff, so we don't want to have a situation where we can print something we can't parse. llvm-svn: 316479
2017-10-25 02:04:54 +08:00
[InlineSpiller] Don't spill fully undef values Althought it is not wrong to spill undef values, it is useless and harms both code size and runtime. Before spilling a value, check that its content actually matters. http://www.llvm.org/PR33311 llvm-svn: 304752
2017-06-06 07:51:27 +08:00
define void @foobar() {
ret void
}
MIR: Print the register class or bank in vreg defs This updates the MIRPrinter to include the regclass when printing virtual register defs, which is already valid syntax for the parser. That is, given 64 bit %0 and %1 in a "gpr" regbank, %1(s64) = COPY %0(s64) would now be written as %1:gpr(s64) = COPY %0(s64) While this change alone introduces a bit of redundancy with the registers block, it allows us to update the tests to be more concise and understandable and brings us closer to being able to remove the registers block completely. Note: We generally only print the class in defs, but there is one exception. If there are uses without any defs whatsoever, we'll print the class on all uses. I'm not completely convinced this comes up in meaningful machine IR, but for now the MIRParser and MachineVerifier both accept that kind of stuff, so we don't want to have a situation where we can print something we can't parse. llvm-svn: 316479
2017-10-25 02:04:54 +08:00
[InlineSpiller] Don't spill fully undef values Althought it is not wrong to spill undef values, it is useless and harms both code size and runtime. Before spilling a value, check that its content actually matters. http://www.llvm.org/PR33311 llvm-svn: 304752
2017-06-06 07:51:27 +08:00
...
---
name: foobar
alignment: 2
tracksRegLiveness: true
MIR: Print the register class or bank in vreg defs This updates the MIRPrinter to include the regclass when printing virtual register defs, which is already valid syntax for the parser. That is, given 64 bit %0 and %1 in a "gpr" regbank, %1(s64) = COPY %0(s64) would now be written as %1:gpr(s64) = COPY %0(s64) While this change alone introduces a bit of redundancy with the registers block, it allows us to update the tests to be more concise and understandable and brings us closer to being able to remove the registers block completely. Note: We generally only print the class in defs, but there is one exception. If there are uses without any defs whatsoever, we'll print the class on all uses. I'm not completely convinced this comes up in meaningful machine IR, but for now the MIRParser and MachineVerifier both accept that kind of stuff, so we don't want to have a situation where we can print something we can't parse. llvm-svn: 316479
2017-10-25 02:04:54 +08:00
registers:
[InlineSpiller] Don't spill fully undef values Althought it is not wrong to spill undef values, it is useless and harms both code size and runtime. Before spilling a value, check that its content actually matters. http://www.llvm.org/PR33311 llvm-svn: 304752
2017-06-06 07:51:27 +08:00
- { id: 0, class: gpr32 }
- { id: 1, class: gpr32 }
- { id: 2, class: gpr32all }
- { id: 3, class: gpr32 }
- { id: 4, class: gpr64common }
- { id: 5, class: gpr32 }
- { id: 6, class: gpr64common }
- { id: 7, class: gpr32 }
- { id: 8, class: gpr32 }
- { id: 9, class: gpr64 }
body: |
bb.0:
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
liveins: $x0
[InlineSpiller] Don't spill fully undef values Althought it is not wrong to spill undef values, it is useless and harms both code size and runtime. Before spilling a value, check that its content actually matters. http://www.llvm.org/PR33311 llvm-svn: 304752
2017-06-06 07:51:27 +08:00
successors: %bb.1, %bb.2
; %8 is going to be spilled.
; But on that path, we don't care about its value.
; Emit a simple KILL instruction instead of an
; actual spill.
MIR: Print the register class or bank in vreg defs This updates the MIRPrinter to include the regclass when printing virtual register defs, which is already valid syntax for the parser. That is, given 64 bit %0 and %1 in a "gpr" regbank, %1(s64) = COPY %0(s64) would now be written as %1:gpr(s64) = COPY %0(s64) While this change alone introduces a bit of redundancy with the registers block, it allows us to update the tests to be more concise and understandable and brings us closer to being able to remove the registers block completely. Note: We generally only print the class in defs, but there is one exception. If there are uses without any defs whatsoever, we'll print the class on all uses. I'm not completely convinced this comes up in meaningful machine IR, but for now the MIRParser and MachineVerifier both accept that kind of stuff, so we don't want to have a situation where we can print something we can't parse. llvm-svn: 316479
2017-10-25 02:04:54 +08:00
; CHECK: [[UNDEF:%[0-9]+]]:gpr32 = IMPLICIT_DEF
[InlineSpiller] Don't spill fully undef values Althought it is not wrong to spill undef values, it is useless and harms both code size and runtime. Before spilling a value, check that its content actually matters. http://www.llvm.org/PR33311 llvm-svn: 304752
2017-06-06 07:51:27 +08:00
; CHECK-NEXT: KILL [[UNDEF]]
%8 = IMPLICIT_DEF
; %9 us going to be spilled.
; But it is only partially undef.
; Make sure we spill it properly
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
; CHECK: [[NINE:%[0-9]+]]:gpr64 = COPY $x0
MIR: Print the register class or bank in vreg defs This updates the MIRPrinter to include the regclass when printing virtual register defs, which is already valid syntax for the parser. That is, given 64 bit %0 and %1 in a "gpr" regbank, %1(s64) = COPY %0(s64) would now be written as %1:gpr(s64) = COPY %0(s64) While this change alone introduces a bit of redundancy with the registers block, it allows us to update the tests to be more concise and understandable and brings us closer to being able to remove the registers block completely. Note: We generally only print the class in defs, but there is one exception. If there are uses without any defs whatsoever, we'll print the class on all uses. I'm not completely convinced this comes up in meaningful machine IR, but for now the MIRParser and MachineVerifier both accept that kind of stuff, so we don't want to have a situation where we can print something we can't parse. llvm-svn: 316479
2017-10-25 02:04:54 +08:00
; CHECK: [[NINE]].sub_32:gpr64 = IMPLICIT_DEF
[InlineSpiller] Don't spill fully undef values Althought it is not wrong to spill undef values, it is useless and harms both code size and runtime. Before spilling a value, check that its content actually matters. http://www.llvm.org/PR33311 llvm-svn: 304752
2017-06-06 07:51:27 +08:00
; CHECK-NEXT: STRXui [[NINE]]
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
%9 = COPY $x0
[InlineSpiller] Don't spill fully undef values Althought it is not wrong to spill undef values, it is useless and harms both code size and runtime. Before spilling a value, check that its content actually matters. http://www.llvm.org/PR33311 llvm-svn: 304752
2017-06-06 07:51:27 +08:00
%9.sub_32 = IMPLICIT_DEF
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
CBNZW $wzr, %bb.2
[InlineSpiller] Don't spill fully undef values Althought it is not wrong to spill undef values, it is useless and harms both code size and runtime. Before spilling a value, check that its content actually matters. http://www.llvm.org/PR33311 llvm-svn: 304752
2017-06-06 07:51:27 +08:00
B %bb.1
MIR: Print the register class or bank in vreg defs This updates the MIRPrinter to include the regclass when printing virtual register defs, which is already valid syntax for the parser. That is, given 64 bit %0 and %1 in a "gpr" regbank, %1(s64) = COPY %0(s64) would now be written as %1:gpr(s64) = COPY %0(s64) While this change alone introduces a bit of redundancy with the registers block, it allows us to update the tests to be more concise and understandable and brings us closer to being able to remove the registers block completely. Note: We generally only print the class in defs, but there is one exception. If there are uses without any defs whatsoever, we'll print the class on all uses. I'm not completely convinced this comes up in meaningful machine IR, but for now the MIRParser and MachineVerifier both accept that kind of stuff, so we don't want to have a situation where we can print something we can't parse. llvm-svn: 316479
2017-10-25 02:04:54 +08:00
[InlineSpiller] Don't spill fully undef values Althought it is not wrong to spill undef values, it is useless and harms both code size and runtime. Before spilling a value, check that its content actually matters. http://www.llvm.org/PR33311 llvm-svn: 304752
2017-06-06 07:51:27 +08:00
bb.1:
%4 = ADRP target-flags(aarch64-page) @g
%8 = LDRWui %4, target-flags(aarch64-pageoff, aarch64-nc) @g :: (volatile dereferenceable load 4 from @g)
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
INLINEASM &nop, 1, 12, implicit-def dead early-clobber $x0, 12, implicit-def dead early-clobber $x1, 12, implicit-def dead early-clobber $x2, 12, implicit-def dead early-clobber $x3, 12, implicit-def dead early-clobber $x4, 12, implicit-def dead early-clobber $x5, 12, implicit-def dead early-clobber $x6, 12, implicit-def dead early-clobber $x7, 12, implicit-def dead early-clobber $x8, 12, implicit-def dead early-clobber $x9, 12, implicit-def dead early-clobber $x10, 12, implicit-def dead early-clobber $x11, 12, implicit-def dead early-clobber $x12, 12, implicit-def dead early-clobber $x13, 12, implicit-def dead early-clobber $x14, 12, implicit-def dead early-clobber $x15, 12, implicit-def dead early-clobber $x16, 12, implicit-def dead early-clobber $x17, 12, implicit-def dead early-clobber $x18, 12, implicit-def dead early-clobber $x19, 12, implicit-def dead early-clobber $x20, 12, implicit-def dead early-clobber $x21, 12, implicit-def dead early-clobber $x22, 12, implicit-def dead early-clobber $x23, 12, implicit-def dead early-clobber $x24, 12, implicit-def dead early-clobber $x25, 12, implicit-def dead early-clobber $x26, 12, implicit-def dead early-clobber $x27, 12, implicit-def dead early-clobber $x28, 12, implicit-def dead early-clobber $fp, 12, implicit-def dead early-clobber $lr
MIR: Print the register class or bank in vreg defs This updates the MIRPrinter to include the regclass when printing virtual register defs, which is already valid syntax for the parser. That is, given 64 bit %0 and %1 in a "gpr" regbank, %1(s64) = COPY %0(s64) would now be written as %1:gpr(s64) = COPY %0(s64) While this change alone introduces a bit of redundancy with the registers block, it allows us to update the tests to be more concise and understandable and brings us closer to being able to remove the registers block completely. Note: We generally only print the class in defs, but there is one exception. If there are uses without any defs whatsoever, we'll print the class on all uses. I'm not completely convinced this comes up in meaningful machine IR, but for now the MIRParser and MachineVerifier both accept that kind of stuff, so we don't want to have a situation where we can print something we can't parse. llvm-svn: 316479
2017-10-25 02:04:54 +08:00
[InlineSpiller] Don't spill fully undef values Althought it is not wrong to spill undef values, it is useless and harms both code size and runtime. Before spilling a value, check that its content actually matters. http://www.llvm.org/PR33311 llvm-svn: 304752
2017-06-06 07:51:27 +08:00
bb.2:
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
INLINEASM &nop, 1, 12, implicit-def dead early-clobber $x0, 12, implicit-def dead early-clobber $x1, 12, implicit-def dead early-clobber $x2, 12, implicit-def dead early-clobber $x3, 12, implicit-def dead early-clobber $x4, 12, implicit-def dead early-clobber $x5, 12, implicit-def dead early-clobber $x6, 12, implicit-def dead early-clobber $x7, 12, implicit-def dead early-clobber $x8, 12, implicit-def dead early-clobber $x9, 12, implicit-def dead early-clobber $x10, 12, implicit-def dead early-clobber $x11, 12, implicit-def dead early-clobber $x12, 12, implicit-def dead early-clobber $x13, 12, implicit-def dead early-clobber $x14, 12, implicit-def dead early-clobber $x15, 12, implicit-def dead early-clobber $x16, 12, implicit-def dead early-clobber $x17, 12, implicit-def dead early-clobber $x18, 12, implicit-def dead early-clobber $x19, 12, implicit-def dead early-clobber $x20, 12, implicit-def dead early-clobber $x21, 12, implicit-def dead early-clobber $x22, 12, implicit-def dead early-clobber $x23, 12, implicit-def dead early-clobber $x24, 12, implicit-def dead early-clobber $x25, 12, implicit-def dead early-clobber $x26, 12, implicit-def dead early-clobber $x27, 12, implicit-def dead early-clobber $x28, 12, implicit-def dead early-clobber $fp, 12, implicit-def dead early-clobber $lr
[InlineSpiller] Don't spill fully undef values Althought it is not wrong to spill undef values, it is useless and harms both code size and runtime. Before spilling a value, check that its content actually matters. http://www.llvm.org/PR33311 llvm-svn: 304752
2017-06-06 07:51:27 +08:00
%6 = ADRP target-flags(aarch64-page) @g
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
$w0 = MOVi32imm 42
[InlineSpiller] Don't spill fully undef values Althought it is not wrong to spill undef values, it is useless and harms both code size and runtime. Before spilling a value, check that its content actually matters. http://www.llvm.org/PR33311 llvm-svn: 304752
2017-06-06 07:51:27 +08:00
STRWui %8, %6, target-flags(aarch64-pageoff, aarch64-nc) @g :: (volatile store 4 into @g)
STRXui %9, %6, target-flags(aarch64-pageoff, aarch64-nc) @g :: (volatile store 8 into @g)
Followup on Proposal to move MIR physical register namespace to '$' sigil. Discussed here: http://lists.llvm.org/pipermail/llvm-dev/2018-January/120320.html In preparation for adding support for named vregs we are changing the sigil for physical registers in MIR to '$' from '%'. This will prevent name clashes of named physical register with named vregs. llvm-svn: 323922
2018-02-01 06:04:26 +08:00
RET_ReallyLR implicit killed $w0
[InlineSpiller] Don't spill fully undef values Althought it is not wrong to spill undef values, it is useless and harms both code size and runtime. Before spilling a value, check that its content actually matters. http://www.llvm.org/PR33311 llvm-svn: 304752
2017-06-06 07:51:27 +08:00
...