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/X86/avx-load-store.ll

313 lines
11 KiB
LLVM
Raw Normal View History

[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx,slow-unaligned-mem-32 | FileCheck %s
; RUN: llc -O0 < %s -mtriple=x86_64-unknown-unknown -mattr=avx,slow-unaligned-mem-32 | FileCheck %s -check-prefix=CHECK_O0
define void @test_256_load(double* nocapture %d, float* nocapture %f, <4 x i64>* nocapture %i) nounwind {
; CHECK-LABEL: test_256_load:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: # %bb.0: # %entry
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-NEXT: pushq %r15
; CHECK-NEXT: pushq %r14
; CHECK-NEXT: pushq %rbx
; CHECK-NEXT: subq $96, %rsp
; CHECK-NEXT: movq %rdx, %r14
; CHECK-NEXT: movq %rsi, %r15
; CHECK-NEXT: movq %rdi, %rbx
Re-enable "[MachineCopyPropagation] Extend pass to do COPY source forwarding" Re-enable commit r323991 now that r325931 has been committed to make MachineOperand::isRenamable() check more conservative w.r.t. code changes and opt-in on a per-target basis. llvm-svn: 326208
2018-02-28 00:59:10 +08:00
; CHECK-NEXT: vmovaps (%rdi), %ymm0
RegAllocFast: Leave unassigned virtreg entries in map Set `LiveReg::PhysReg` to zero when freeing a register instead of removing it from the entry from `LiveRegMap`. This way no iterators get invalidated and we can avoid passing around and updating iterators all over the place. This does not change any allocator decisions. It is not completely NFC because the arbitrary iteration order through `LiveRegMap` in `spillAll()` changes so we may get a different order in those spill sequences (the amount of spills does not change). This is in preparation of https://reviews.llvm.org/D52010. llvm-svn: 346298
2018-11-07 14:57:03 +08:00
; CHECK-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
Re-enable "[MachineCopyPropagation] Extend pass to do COPY source forwarding" Re-enable commit r323991 now that r325931 has been committed to make MachineOperand::isRenamable() check more conservative w.r.t. code changes and opt-in on a per-target basis. llvm-svn: 326208
2018-02-28 00:59:10 +08:00
; CHECK-NEXT: vmovaps (%rsi), %ymm1
RegAllocFast: Leave unassigned virtreg entries in map Set `LiveReg::PhysReg` to zero when freeing a register instead of removing it from the entry from `LiveRegMap`. This way no iterators get invalidated and we can avoid passing around and updating iterators all over the place. This does not change any allocator decisions. It is not completely NFC because the arbitrary iteration order through `LiveRegMap` in `spillAll()` changes so we may get a different order in those spill sequences (the amount of spills does not change). This is in preparation of https://reviews.llvm.org/D52010. llvm-svn: 346298
2018-11-07 14:57:03 +08:00
; CHECK-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
Re-enable "[MachineCopyPropagation] Extend pass to do COPY source forwarding" Re-enable commit r323991 now that r325931 has been committed to make MachineOperand::isRenamable() check more conservative w.r.t. code changes and opt-in on a per-target basis. llvm-svn: 326208
2018-02-28 00:59:10 +08:00
; CHECK-NEXT: vmovaps (%rdx), %ymm2
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-NEXT: vmovups %ymm2, (%rsp) # 32-byte Spill
; CHECK-NEXT: callq dummy
RegAllocFast: Leave unassigned virtreg entries in map Set `LiveReg::PhysReg` to zero when freeing a register instead of removing it from the entry from `LiveRegMap`. This way no iterators get invalidated and we can avoid passing around and updating iterators all over the place. This does not change any allocator decisions. It is not completely NFC because the arbitrary iteration order through `LiveRegMap` in `spillAll()` changes so we may get a different order in those spill sequences (the amount of spills does not change). This is in preparation of https://reviews.llvm.org/D52010. llvm-svn: 346298
2018-11-07 14:57:03 +08:00
; CHECK-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-NEXT: vmovaps %ymm0, (%rbx)
RegAllocFast: Leave unassigned virtreg entries in map Set `LiveReg::PhysReg` to zero when freeing a register instead of removing it from the entry from `LiveRegMap`. This way no iterators get invalidated and we can avoid passing around and updating iterators all over the place. This does not change any allocator decisions. It is not completely NFC because the arbitrary iteration order through `LiveRegMap` in `spillAll()` changes so we may get a different order in those spill sequences (the amount of spills does not change). This is in preparation of https://reviews.llvm.org/D52010. llvm-svn: 346298
2018-11-07 14:57:03 +08:00
; CHECK-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-NEXT: vmovaps %ymm0, (%r15)
; CHECK-NEXT: vmovups (%rsp), %ymm0 # 32-byte Reload
; CHECK-NEXT: vmovaps %ymm0, (%r14)
; CHECK-NEXT: addq $96, %rsp
; CHECK-NEXT: popq %rbx
; CHECK-NEXT: popq %r14
; CHECK-NEXT: popq %r15
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
;
; CHECK_O0-LABEL: test_256_load:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK_O0: # %bb.0: # %entry
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK_O0-NEXT: subq $152, %rsp
; CHECK_O0-NEXT: vmovapd (%rdi), %ymm0
; CHECK_O0-NEXT: vmovaps (%rsi), %ymm1
; CHECK_O0-NEXT: vmovdqa (%rdx), %ymm2
RegAllocFast: Leave unassigned virtreg entries in map Set `LiveReg::PhysReg` to zero when freeing a register instead of removing it from the entry from `LiveRegMap`. This way no iterators get invalidated and we can avoid passing around and updating iterators all over the place. This does not change any allocator decisions. It is not completely NFC because the arbitrary iteration order through `LiveRegMap` in `spillAll()` changes so we may get a different order in those spill sequences (the amount of spills does not change). This is in preparation of https://reviews.llvm.org/D52010. llvm-svn: 346298
2018-11-07 14:57:03 +08:00
; CHECK_O0-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; CHECK_O0-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; CHECK_O0-NEXT: vmovups %ymm2, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; CHECK_O0-NEXT: movq %rdi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; CHECK_O0-NEXT: movq %rsi, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; CHECK_O0-NEXT: movq %rdx, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK_O0-NEXT: callq dummy
RegAllocFast: Remove early selection loop, the spill calculation will report cost 0 anyway for free regs The 2nd loop calculates spill costs but reports free registers as cost 0 anyway, so there is little benefit from having a separate early loop. Surprisingly this is not NFC, as many register are marked regDisabled so the first loop often picks up later registers unnecessarily instead of the first one available in the allocation order... Patch by Matthias Braun llvm-svn: 356499
2019-03-20 03:01:34 +08:00
; CHECK_O0-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload
RegAllocFast: Leave unassigned virtreg entries in map Set `LiveReg::PhysReg` to zero when freeing a register instead of removing it from the entry from `LiveRegMap`. This way no iterators get invalidated and we can avoid passing around and updating iterators all over the place. This does not change any allocator decisions. It is not completely NFC because the arbitrary iteration order through `LiveRegMap` in `spillAll()` changes so we may get a different order in those spill sequences (the amount of spills does not change). This is in preparation of https://reviews.llvm.org/D52010. llvm-svn: 346298
2018-11-07 14:57:03 +08:00
; CHECK_O0-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
RegAllocFast: Remove early selection loop, the spill calculation will report cost 0 anyway for free regs The 2nd loop calculates spill costs but reports free registers as cost 0 anyway, so there is little benefit from having a separate early loop. Surprisingly this is not NFC, as many register are marked regDisabled so the first loop often picks up later registers unnecessarily instead of the first one available in the allocation order... Patch by Matthias Braun llvm-svn: 356499
2019-03-20 03:01:34 +08:00
; CHECK_O0-NEXT: vmovapd %ymm0, (%rax)
; CHECK_O0-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rcx # 8-byte Reload
RegAllocFast: Leave unassigned virtreg entries in map Set `LiveReg::PhysReg` to zero when freeing a register instead of removing it from the entry from `LiveRegMap`. This way no iterators get invalidated and we can avoid passing around and updating iterators all over the place. This does not change any allocator decisions. It is not completely NFC because the arbitrary iteration order through `LiveRegMap` in `spillAll()` changes so we may get a different order in those spill sequences (the amount of spills does not change). This is in preparation of https://reviews.llvm.org/D52010. llvm-svn: 346298
2018-11-07 14:57:03 +08:00
; CHECK_O0-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
RegAllocFast: Remove early selection loop, the spill calculation will report cost 0 anyway for free regs The 2nd loop calculates spill costs but reports free registers as cost 0 anyway, so there is little benefit from having a separate early loop. Surprisingly this is not NFC, as many register are marked regDisabled so the first loop often picks up later registers unnecessarily instead of the first one available in the allocation order... Patch by Matthias Braun llvm-svn: 356499
2019-03-20 03:01:34 +08:00
; CHECK_O0-NEXT: vmovaps %ymm1, (%rcx)
; CHECK_O0-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rdx # 8-byte Reload
RegAllocFast: Leave unassigned virtreg entries in map Set `LiveReg::PhysReg` to zero when freeing a register instead of removing it from the entry from `LiveRegMap`. This way no iterators get invalidated and we can avoid passing around and updating iterators all over the place. This does not change any allocator decisions. It is not completely NFC because the arbitrary iteration order through `LiveRegMap` in `spillAll()` changes so we may get a different order in those spill sequences (the amount of spills does not change). This is in preparation of https://reviews.llvm.org/D52010. llvm-svn: 346298
2018-11-07 14:57:03 +08:00
; CHECK_O0-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm2 # 32-byte Reload
RegAllocFast: Remove early selection loop, the spill calculation will report cost 0 anyway for free regs The 2nd loop calculates spill costs but reports free registers as cost 0 anyway, so there is little benefit from having a separate early loop. Surprisingly this is not NFC, as many register are marked regDisabled so the first loop often picks up later registers unnecessarily instead of the first one available in the allocation order... Patch by Matthias Braun llvm-svn: 356499
2019-03-20 03:01:34 +08:00
; CHECK_O0-NEXT: vmovdqa %ymm2, (%rdx)
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK_O0-NEXT: addq $152, %rsp
; CHECK_O0-NEXT: vzeroupper
; CHECK_O0-NEXT: retq
Add 256-bit load/store recognition and matching in several places. llvm-svn: 135171
2011-07-15 02:50:58 +08:00
entry:
%0 = bitcast double* %d to <4 x double>*
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%tmp1.i = load <4 x double>, <4 x double>* %0, align 32
Add 256-bit load/store recognition and matching in several places. llvm-svn: 135171
2011-07-15 02:50:58 +08:00
%1 = bitcast float* %f to <8 x float>*
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%tmp1.i17 = load <8 x float>, <8 x float>* %1, align 32
%tmp1.i16 = load <4 x i64>, <4 x i64>* %i, align 32
Add 256-bit load/store recognition and matching in several places. llvm-svn: 135171
2011-07-15 02:50:58 +08:00
tail call void @dummy(<4 x double> %tmp1.i, <8 x float> %tmp1.i17, <4 x i64> %tmp1.i16) nounwind
store <4 x double> %tmp1.i, <4 x double>* %0, align 32
store <8 x float> %tmp1.i17, <8 x float>* %1, align 32
store <4 x i64> %tmp1.i16, <4 x i64>* %i, align 32
ret void
}
declare void @dummy(<4 x double>, <8 x float>, <4 x i64>)
Add two patterns to match special vmovss and vmovsd cases. Also fix the patterns already there to be more strict regarding the predicate. This fixes PR10558 llvm-svn: 137100
2011-08-09 09:43:09 +08:00
;;
;; The two tests below check that we must fold load + scalar_to_vector
Fix a bug in the lowering of BUILD_VECTOR for AVX. SCALAR_TO_VECTOR does not zero untouched elements. Use INSERT_VECTOR_ELT instead. llvm-svn: 147948
2012-01-11 22:07:51 +08:00
;; + ins_subvec+ zext into only a single vmovss or vmovsd or vinsertps from memory
Add two patterns to match special vmovss and vmovsd cases. Also fix the patterns already there to be more strict regarding the predicate. This fixes PR10558 llvm-svn: 137100
2011-08-09 09:43:09 +08:00
define <8 x float> @mov00(<8 x float> %v, float * %ptr) nounwind {
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-LABEL: mov00:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: # %bb.0:
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT: retq
;
; CHECK_O0-LABEL: mov00:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK_O0: # %bb.0:
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK_O0-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
[X86] Use 128-bit ops for 256-bit vzmovl patterns. 128-bit ops implicitly zero the upper bits. This should address the comment about domain crossing for the integer version without AVX2 since we can use a 128-bit VBLENDW without AVX2. The only bad thing I see here is that we failed to reuse an vxorps in some of the tests, but I think that's already known issue. llvm-svn: 337134
2018-07-16 02:51:07 +08:00
; CHECK_O0-NEXT: # kill: def $ymm0 killed $xmm0
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK_O0-NEXT: retq
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%val = load float, float* %ptr
Add two patterns to match special vmovss and vmovsd cases. Also fix the patterns already there to be more strict regarding the predicate. This fixes PR10558 llvm-svn: 137100
2011-08-09 09:43:09 +08:00
%i0 = insertelement <8 x float> zeroinitializer, float %val, i32 0
ret <8 x float> %i0
}
define <4 x double> @mov01(<4 x double> %v, double * %ptr) nounwind {
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-LABEL: mov01:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: # %bb.0:
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT: retq
;
; CHECK_O0-LABEL: mov01:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK_O0: # %bb.0:
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK_O0-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
[X86] Use 128-bit ops for 256-bit vzmovl patterns. 128-bit ops implicitly zero the upper bits. This should address the comment about domain crossing for the integer version without AVX2 since we can use a 128-bit VBLENDW without AVX2. The only bad thing I see here is that we failed to reuse an vxorps in some of the tests, but I think that's already known issue. llvm-svn: 337134
2018-07-16 02:51:07 +08:00
; CHECK_O0-NEXT: # kill: def $ymm0 killed $xmm0
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK_O0-NEXT: retq
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%val = load double, double* %ptr
Add two patterns to match special vmovss and vmovsd cases. Also fix the patterns already there to be more strict regarding the predicate. This fixes PR10558 llvm-svn: 137100
2011-08-09 09:43:09 +08:00
%i0 = insertelement <4 x double> zeroinitializer, double %val, i32 0
ret <4 x double> %i0
}
Add v16i16 and v32i8 store patterns llvm-svn: 137166
2011-08-10 06:39:53 +08:00
define void @storev16i16(<16 x i16> %a) nounwind {
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-LABEL: storev16i16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: # %bb.0:
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-NEXT: vmovaps %ymm0, (%rax)
;
; CHECK_O0-LABEL: storev16i16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK_O0: # %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
; CHECK_O0-NEXT: # implicit-def: $rax
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK_O0-NEXT: vmovdqa %ymm0, (%rax)
Add v16i16 and v32i8 store patterns llvm-svn: 137166
2011-08-10 06:39:53 +08:00
store <16 x i16> %a, <16 x i16>* undef, align 32
unreachable
}
define void @storev16i16_01(<16 x i16> %a) nounwind {
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-LABEL: storev16i16_01:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: # %bb.0:
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-NEXT: vextractf128 $1, %ymm0, (%rax)
; CHECK-NEXT: vmovups %xmm0, (%rax)
;
; CHECK_O0-LABEL: storev16i16_01:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK_O0: # %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
; CHECK_O0-NEXT: # implicit-def: $rax
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK_O0-NEXT: vmovdqu %ymm0, (%rax)
Add v16i16 and v32i8 store patterns llvm-svn: 137166
2011-08-10 06:39:53 +08:00
store <16 x i16> %a, <16 x i16>* undef, align 4
unreachable
}
define void @storev32i8(<32 x i8> %a) nounwind {
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-LABEL: storev32i8:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: # %bb.0:
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-NEXT: vmovaps %ymm0, (%rax)
;
; CHECK_O0-LABEL: storev32i8:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK_O0: # %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
; CHECK_O0-NEXT: # implicit-def: $rax
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK_O0-NEXT: vmovdqa %ymm0, (%rax)
Add v16i16 and v32i8 store patterns llvm-svn: 137166
2011-08-10 06:39:53 +08:00
store <32 x i8> %a, <32 x i8>* undef, align 32
unreachable
}
define void @storev32i8_01(<32 x i8> %a) nounwind {
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-LABEL: storev32i8_01:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: # %bb.0:
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-NEXT: vextractf128 $1, %ymm0, (%rax)
; CHECK-NEXT: vmovups %xmm0, (%rax)
;
; CHECK_O0-LABEL: storev32i8_01:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK_O0: # %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
; CHECK_O0-NEXT: # implicit-def: $rax
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK_O0-NEXT: vmovdqu %ymm0, (%rax)
Add v16i16 and v32i8 store patterns llvm-svn: 137166
2011-08-10 06:39:53 +08:00
store <32 x i8> %a, <32 x i8>* undef, align 4
unreachable
}
[CodeGen] Print register names in lowercase in both MIR and debug output As part of the unification of the debug format and the MIR format, always print registers as lowercase. * Only debug printing is affected. It now follows MIR. Differential Revision: https://reviews.llvm.org/D40417 llvm-svn: 319187
2017-11-29 01:15:09 +08:00
; It is faster to make two saves, if the data is already in xmm registers. For
Fix the test added by Nadav in r137308. Make it more strict: 1) check for the "v" version of movaps 2) add a couple of CHECK-NOT to guarantee the behavior 3) move to a more appropriate test file llvm-svn: 137361
2011-08-12 05:50:35 +08:00
; example, after making an integer operation.
define void @double_save(<4 x i32> %A, <4 x i32> %B, <8 x i32>* %P) nounwind ssp {
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-LABEL: double_save:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: # %bb.0:
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-NEXT: vmovaps %xmm1, 16(%rdi)
; CHECK-NEXT: vmovaps %xmm0, (%rdi)
; CHECK-NEXT: retq
;
; CHECK_O0-LABEL: double_save:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK_O0: # %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
; CHECK_O0-NEXT: # implicit-def: $ymm2
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK_O0-NEXT: vmovaps %xmm0, %xmm2
; CHECK_O0-NEXT: vinsertf128 $1, %xmm1, %ymm2, %ymm2
; CHECK_O0-NEXT: vmovdqu %ymm2, (%rdi)
; CHECK_O0-NEXT: vzeroupper
; CHECK_O0-NEXT: retq
Fix the test added by Nadav in r137308. Make it more strict: 1) check for the "v" version of movaps 2) add a couple of CHECK-NOT to guarantee the behavior 3) move to a more appropriate test file llvm-svn: 137361
2011-08-12 05:50:35 +08:00
%Z = shufflevector <4 x i32>%A, <4 x i32>%B, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
store <8 x i32> %Z, <8 x i32>* %P, align 16
ret void
}
[x86] Fix AVX maskload/store intrinsic prototypes. The mask value type for maskload/maskstore GCC builtins is never a vector of packed floats/doubles. This patch fixes the following issues: 1. The mask argument for builtin_ia32_maskloadpd and builtin_ia32_maskstorepd should be of type llvm_v2i64_ty and not llvm_v2f64_ty. 2. The mask argument for builtin_ia32_maskloadpd256 and builtin_ia32_maskstorepd256 should be of type llvm_v4i64_ty and not llvm_v4f64_ty. 3. The mask argument for builtin_ia32_maskloadps and builtin_ia32_maskstoreps should be of type llvm_v4i32_ty and not llvm_v4f32_ty. 4. The mask argument for builtin_ia32_maskloadps256 and builtin_ia32_maskstoreps256 should be of type llvm_v8i32_ty and not llvm_v8f32_ty. Differential Revision: http://reviews.llvm.org/D13776 llvm-svn: 250817
2015-10-20 19:20:13 +08:00
declare void @llvm.x86.avx.maskstore.ps.256(i8*, <8 x i32>, <8 x float>) nounwind
Fix PR10844: Add patterns to cover non foldable versions of X86vzmovl. Triggered using llc -O0. Also fix some SET0PS patterns to their AVX forms and test it on the testcase. llvm-svn: 139304
2011-09-09 02:05:02 +08:00
define void @f_f() nounwind {
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-LABEL: f_f:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: # %bb.0: # %allocas
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: testb %al, %al
; CHECK-NEXT: jne .LBB8_2
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK-NEXT: # %bb.1: # %cif_mask_all
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-NEXT: .LBB8_2: # %cif_mask_mixed
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: testb %al, %al
; CHECK-NEXT: jne .LBB8_4
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK-NEXT: # %bb.3: # %cif_mixed_test_all
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-NEXT: movl $-1, %eax
; CHECK-NEXT: vmovd %eax, %xmm0
; CHECK-NEXT: vmaskmovps %ymm0, %ymm0, (%rax)
; CHECK-NEXT: .LBB8_4: # %cif_mixed_test_any_check
;
; CHECK_O0-LABEL: f_f:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK_O0: # %bb.0: # %allocas
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_O0-NEXT: # implicit-def: $al
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK_O0-NEXT: testb $1, %al
; CHECK_O0-NEXT: jne .LBB8_1
; CHECK_O0-NEXT: jmp .LBB8_2
; CHECK_O0-NEXT: .LBB8_1: # %cif_mask_all
; CHECK_O0-NEXT: .LBB8_2: # %cif_mask_mixed
Followup on Proposal to move MIR physical register namespace to '$' 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_O0-NEXT: # implicit-def: $al
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK_O0-NEXT: testb $1, %al
; CHECK_O0-NEXT: jne .LBB8_3
; CHECK_O0-NEXT: jmp .LBB8_4
; CHECK_O0-NEXT: .LBB8_3: # %cif_mixed_test_all
; CHECK_O0-NEXT: movl $-1, %eax
; CHECK_O0-NEXT: vmovd %eax, %xmm0
; CHECK_O0-NEXT: vmovaps %xmm0, %xmm1
Followup on Proposal to move MIR physical register namespace to '$' 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_O0-NEXT: # implicit-def: $rcx
; CHECK_O0-NEXT: # implicit-def: $ymm2
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK_O0-NEXT: vmaskmovps %ymm2, %ymm1, (%rcx)
; CHECK_O0-NEXT: .LBB8_4: # %cif_mixed_test_any_check
Fix PR10844: Add patterns to cover non foldable versions of X86vzmovl. Triggered using llc -O0. Also fix some SET0PS patterns to their AVX forms and test it on the testcase. llvm-svn: 139304
2011-09-09 02:05:02 +08:00
allocas:
br i1 undef, label %cif_mask_all, label %cif_mask_mixed
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
cif_mask_all:
Fix PR10844: Add patterns to cover non foldable versions of X86vzmovl. Triggered using llc -O0. Also fix some SET0PS patterns to their AVX forms and test it on the testcase. llvm-svn: 139304
2011-09-09 02:05:02 +08:00
unreachable
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
cif_mask_mixed:
Fix PR10844: Add patterns to cover non foldable versions of X86vzmovl. Triggered using llc -O0. Also fix some SET0PS patterns to their AVX forms and test it on the testcase. llvm-svn: 139304
2011-09-09 02:05:02 +08:00
br i1 undef, label %cif_mixed_test_all, label %cif_mixed_test_any_check
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
cif_mixed_test_all:
[x86] Fix AVX maskload/store intrinsic prototypes. The mask value type for maskload/maskstore GCC builtins is never a vector of packed floats/doubles. This patch fixes the following issues: 1. The mask argument for builtin_ia32_maskloadpd and builtin_ia32_maskstorepd should be of type llvm_v2i64_ty and not llvm_v2f64_ty. 2. The mask argument for builtin_ia32_maskloadpd256 and builtin_ia32_maskstorepd256 should be of type llvm_v4i64_ty and not llvm_v4f64_ty. 3. The mask argument for builtin_ia32_maskloadps and builtin_ia32_maskstoreps should be of type llvm_v4i32_ty and not llvm_v4f32_ty. 4. The mask argument for builtin_ia32_maskloadps256 and builtin_ia32_maskstoreps256 should be of type llvm_v8i32_ty and not llvm_v8f32_ty. Differential Revision: http://reviews.llvm.org/D13776 llvm-svn: 250817
2015-10-20 19:20:13 +08:00
call void @llvm.x86.avx.maskstore.ps.256(i8* undef, <8 x i32> <i32 -1, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>, <8 x float> undef) nounwind
Fix PR10844: Add patterns to cover non foldable versions of X86vzmovl. Triggered using llc -O0. Also fix some SET0PS patterns to their AVX forms and test it on the testcase. llvm-svn: 139304
2011-09-09 02:05:02 +08:00
unreachable
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
cif_mixed_test_any_check:
Fix PR10844: Add patterns to cover non foldable versions of X86vzmovl. Triggered using llc -O0. Also fix some SET0PS patterns to their AVX forms and test it on the testcase. llvm-svn: 139304
2011-09-09 02:05:02 +08:00
unreachable
}
Enhance folding of (extract_subvec (insert_subvec V1, V2, IIdx), EIdx) - Handle the case where the result of 'insert_subvect' is bitcasted before 'extract_subvec'. This removes the redundant insertf128/extractf128 pair on unaligned 256-bit vector load/store on vectors of non 64-bit integer. llvm-svn: 177945
2013-03-26 07:47:35 +08:00
define void @add8i32(<8 x i32>* %ret, <8 x i32>* %bp) nounwind {
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-LABEL: add8i32:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: # %bb.0:
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-NEXT: vmovups (%rsi), %xmm0
; CHECK-NEXT: vmovups 16(%rsi), %xmm1
[DAG] Avoid smart constructor-based dangling nodes. Various SelectionDAG non-combine operations (e.g. the getNode smart constructor and legalization) may leave dangling nodes by applying optimizations or not fully pruning unused result values. This can result in nodes that are never added to the worklist and therefore can not be pruned. Add a node inserter as the current node deleter to make sure such nodes have the chance of being pruned. Many minor changes, mostly positive. llvm-svn: 356996
2019-03-26 23:08:14 +08:00
; CHECK-NEXT: vmovups %xmm1, 16(%rdi)
Revert r356996 "[DAG] Avoid smart constructor-based dangling nodes." This patch appears to trigger very large compile time increases in halide builds. llvm-svn: 357116
2019-03-28 03:54:41 +08:00
; CHECK-NEXT: vmovups %xmm0, (%rdi)
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-NEXT: retq
;
; CHECK_O0-LABEL: add8i32:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK_O0: # %bb.0:
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK_O0-NEXT: vmovdqu (%rsi), %xmm0
; CHECK_O0-NEXT: vmovdqu 16(%rsi), %xmm1
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_O0-NEXT: # implicit-def: $ymm2
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK_O0-NEXT: vmovaps %xmm0, %xmm2
; CHECK_O0-NEXT: vinsertf128 $1, %xmm1, %ymm2, %ymm2
; CHECK_O0-NEXT: vmovdqu %ymm2, (%rdi)
; CHECK_O0-NEXT: vzeroupper
; CHECK_O0-NEXT: retq
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%b = load <8 x i32>, <8 x i32>* %bp, align 1
Enhance folding of (extract_subvec (insert_subvec V1, V2, IIdx), EIdx) - Handle the case where the result of 'insert_subvect' is bitcasted before 'extract_subvec'. This removes the redundant insertf128/extractf128 pair on unaligned 256-bit vector load/store on vectors of non 64-bit integer. llvm-svn: 177945
2013-03-26 07:47:35 +08:00
%x = add <8 x i32> zeroinitializer, %b
store <8 x i32> %x, <8 x i32>* %ret, align 1
ret void
}
Revise alignment checking/calculation on 256-bit unaligned memory access - It's still considered aligned when the specified alignment is larger than the natural alignment; - The new alignment for the high 128-bit vector should be min(16, alignment) as the pointer is advanced by 16, a power-of-2 offset. llvm-svn: 177947
2013-03-26 07:50:10 +08:00
define void @add4i64a64(<4 x i64>* %ret, <4 x i64>* %bp) nounwind {
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-LABEL: add4i64a64:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: # %bb.0:
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-NEXT: vmovaps (%rsi), %ymm0
; CHECK-NEXT: vmovaps %ymm0, (%rdi)
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
;
; CHECK_O0-LABEL: add4i64a64:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK_O0: # %bb.0:
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK_O0-NEXT: vmovaps (%rsi), %ymm0
; CHECK_O0-NEXT: vmovdqa %ymm0, (%rdi)
; CHECK_O0-NEXT: vzeroupper
; CHECK_O0-NEXT: retq
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%b = load <4 x i64>, <4 x i64>* %bp, align 64
Revise alignment checking/calculation on 256-bit unaligned memory access - It's still considered aligned when the specified alignment is larger than the natural alignment; - The new alignment for the high 128-bit vector should be min(16, alignment) as the pointer is advanced by 16, a power-of-2 offset. llvm-svn: 177947
2013-03-26 07:50:10 +08:00
%x = add <4 x i64> zeroinitializer, %b
store <4 x i64> %x, <4 x i64>* %ret, align 64
ret void
}
define void @add4i64a16(<4 x i64>* %ret, <4 x i64>* %bp) nounwind {
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-LABEL: add4i64a16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK: # %bb.0:
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-NEXT: vmovaps (%rsi), %xmm0
; CHECK-NEXT: vmovaps 16(%rsi), %xmm1
[DAG] Avoid smart constructor-based dangling nodes. Various SelectionDAG non-combine operations (e.g. the getNode smart constructor and legalization) may leave dangling nodes by applying optimizations or not fully pruning unused result values. This can result in nodes that are never added to the worklist and therefore can not be pruned. Add a node inserter as the current node deleter to make sure such nodes have the chance of being pruned. Many minor changes, mostly positive. llvm-svn: 356996
2019-03-26 23:08:14 +08:00
; CHECK-NEXT: vmovaps %xmm1, 16(%rdi)
Revert r356996 "[DAG] Avoid smart constructor-based dangling nodes." This patch appears to trigger very large compile time increases in halide builds. llvm-svn: 357116
2019-03-28 03:54:41 +08:00
; CHECK-NEXT: vmovaps %xmm0, (%rdi)
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK-NEXT: retq
;
; CHECK_O0-LABEL: add4i64a16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; CHECK_O0: # %bb.0:
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK_O0-NEXT: vmovdqa (%rsi), %xmm0
; CHECK_O0-NEXT: vmovdqa 16(%rsi), %xmm1
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_O0-NEXT: # implicit-def: $ymm2
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00
; CHECK_O0-NEXT: vmovaps %xmm0, %xmm2
; CHECK_O0-NEXT: vinsertf128 $1, %xmm1, %ymm2, %ymm2
; CHECK_O0-NEXT: vmovdqu %ymm2, (%rdi)
; CHECK_O0-NEXT: vzeroupper
; CHECK_O0-NEXT: retq
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%b = load <4 x i64>, <4 x i64>* %bp, align 16
Revise alignment checking/calculation on 256-bit unaligned memory access - It's still considered aligned when the specified alignment is larger than the natural alignment; - The new alignment for the high 128-bit vector should be min(16, alignment) as the pointer is advanced by 16, a power-of-2 offset. llvm-svn: 177947
2013-03-26 07:50:10 +08:00
%x = add <4 x i64> zeroinitializer, %b
store <4 x i64> %x, <4 x i64>* %ret, align 16
ret void
}
[x86] auto-generate complete checks for tests; NFC These all used 'CHECK-NOT' which isn't necessary if we have complete checks. There were also several over-specifications in the RUN params such as CPU model or OS requirement llvm-svn: 307028
2017-07-03 23:04:05 +08:00