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/pshufb-mask-comments.ll

91 lines
3.7 KiB
LLVM
Raw Normal View History

[X86][SSE] Regenerate PSHUFB shuffle mask comments tests llvm-svn: 260061
2016-02-08 06:22:09 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+ssse3 | FileCheck %s
Fix assert when decoding PSHUFB mask The PSHUFB mask decode routine used to assert if the mask index was out of range (<0 or greater than the size of the vector). The problem is, we can legitimately have a PSHUFB with a large index using intrinsics. The instruction only uses the least significant 4 bits. This change removes the assert and masks the index to match the instruction behaviour. llvm-svn: 218242
2014-09-22 19:54:38 +08:00
; Test that the pshufb mask comment is correct.
define <16 x i8> @test1(<16 x i8> %V) {
; CHECK-LABEL: test1:
[X86][SSE] Regenerate PSHUFB shuffle mask comments tests llvm-svn: 260061
2016-02-08 06:22:09 +08:00
; CHECK: # BB#0:
; CHECK-NEXT: pshufb {{.*#+}} xmm0 = xmm0[1,0,0,0,0,2,0,0,0,0,3,0,0,0,0,4]
; CHECK-NEXT: retq
Fix assert when decoding PSHUFB mask The PSHUFB mask decode routine used to assert if the mask index was out of range (<0 or greater than the size of the vector). The problem is, we can legitimately have a PSHUFB with a large index using intrinsics. The instruction only uses the least significant 4 bits. This change removes the assert and masks the index to match the instruction behaviour. llvm-svn: 218242
2014-09-22 19:54:38 +08:00
%1 = tail call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %V, <16 x i8> <i8 1, i8 0, i8 0, i8 0, i8 0, i8 2, i8 0, i8 0, i8 0, i8 0, i8 3, i8 0, i8 0, i8 0, i8 0, i8 4>)
ret <16 x i8> %1
}
; Test that indexes larger than the size of the vector are shown masked (bottom 4 bits).
define <16 x i8> @test2(<16 x i8> %V) {
; CHECK-LABEL: test2:
[X86][SSE] Regenerate PSHUFB shuffle mask comments tests llvm-svn: 260061
2016-02-08 06:22:09 +08:00
; CHECK: # BB#0:
; CHECK-NEXT: pshufb {{.*#+}} xmm0 = xmm0[15,0,0,0,0,0,0,0,0,0,1,0,0,0,0,2]
; CHECK-NEXT: retq
Fix assert when decoding PSHUFB mask The PSHUFB mask decode routine used to assert if the mask index was out of range (<0 or greater than the size of the vector). The problem is, we can legitimately have a PSHUFB with a large index using intrinsics. The instruction only uses the least significant 4 bits. This change removes the assert and masks the index to match the instruction behaviour. llvm-svn: 218242
2014-09-22 19:54:38 +08:00
%1 = tail call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %V, <16 x i8> <i8 15, i8 0, i8 0, i8 0, i8 0, i8 16, i8 0, i8 0, i8 0, i8 0, i8 17, i8 0, i8 0, i8 0, i8 0, i8 50>)
ret <16 x i8> %1
}
; Test that indexes with bit seven set are shown as zero.
define <16 x i8> @test3(<16 x i8> %V) {
; CHECK-LABEL: test3:
[X86][SSE] Regenerate PSHUFB shuffle mask comments tests llvm-svn: 260061
2016-02-08 06:22:09 +08:00
; CHECK: # BB#0:
; CHECK-NEXT: pshufb {{.*#+}} xmm0 = xmm0[1,0,0,15,0,2,0,0],zero,xmm0[0,3,0,0],zero,xmm0[0,4]
; CHECK-NEXT: retq
Fix assert when decoding PSHUFB mask The PSHUFB mask decode routine used to assert if the mask index was out of range (<0 or greater than the size of the vector). The problem is, we can legitimately have a PSHUFB with a large index using intrinsics. The instruction only uses the least significant 4 bits. This change removes the assert and masks the index to match the instruction behaviour. llvm-svn: 218242
2014-09-22 19:54:38 +08:00
%1 = tail call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %V, <16 x i8> <i8 1, i8 0, i8 0, i8 127, i8 0, i8 2, i8 0, i8 0, i8 128, i8 0, i8 3, i8 0, i8 0, i8 255, i8 0, i8 4>)
ret <16 x i8> %1
}
X86: Properly decode shuffle masks when the constant pool type is weird It's possible for the constant pool entry for the shuffle mask to come from a completely different operation. This occurs when Constants have the same bit pattern but have different types. Make DecodePSHUFBMask tolerant of types which, after a bitcast, are appropriately sized vector types. This fixes PR22188. llvm-svn: 225597
2015-01-11 13:08:57 +08:00
; Test that we won't crash when the constant was reused for another instruction.
[X86][SSE] Update pshufb mask test to use a real input instead of undef We are getting better at combining constant pshufb masks - this test would've failed once we decode bitcasted masks as well. llvm-svn: 261095
2016-02-17 22:56:58 +08:00
define <16 x i8> @test4(<16 x i8> %V, <2 x i64>* %P) {
[X86][SSE] Regenerate PSHUFB shuffle mask comments tests llvm-svn: 260061
2016-02-08 06:22:09 +08:00
; CHECK-LABEL: test4:
; CHECK: # BB#0:
[X86][SSE] Added support for combining target shuffles to (V)PSHUFD/VPERMILPD/VPERMILPS immediate permutes This patch allows target shuffles to be combined to single input immediate permute instructions - (V)PSHUFD/VPERMILPD/VPERMILPS - allowing more general pattern matching than what we current do and improves the likelihood of memory folding compared to existing patterns which tend to reuse the input in multiple arguments. Further permute instructions (V)PSHUFLW/(V)PSHUFHW/(V)PERMQ/(V)PERMPD may be added in the future but its proven tricky to create tests cases for them so far. (V)PSHUFLW/(V)PSHUFHW is already handled quite well in combineTargetShuffle so it may be that removing some of that code may allow us to perform more of the combining in one place without duplication. Differential Revision: http://reviews.llvm.org/D21148 llvm-svn: 273999
2016-06-28 16:08:15 +08:00
; CHECK-NEXT: movaps {{.*#+}} xmm1 = [1084818905618843912,506097522914230528]
; CHECK-NEXT: movaps %xmm1, (%rdi)
; CHECK-NEXT: pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
[X86][SSE] Regenerate PSHUFB shuffle mask comments tests llvm-svn: 260061
2016-02-08 06:22:09 +08:00
; CHECK-NEXT: retq
%1 = insertelement <2 x i64> undef, i64 1084818905618843912, i32 0
%2 = insertelement <2 x i64> %1, i64 506097522914230528, i32 1
[X86][SSE] Update pshufb mask test to use a real input instead of undef We are getting better at combining constant pshufb masks - this test would've failed once we decode bitcasted masks as well. llvm-svn: 261095
2016-02-17 22:56:58 +08:00
store <2 x i64> %2, <2 x i64>* %P, align 16
[X86][SSE] Regenerate PSHUFB shuffle mask comments tests llvm-svn: 260061
2016-02-08 06:22:09 +08:00
%3 = bitcast <2 x i64> %2 to <16 x i8>
[X86][SSE] Update pshufb mask test to use a real input instead of undef We are getting better at combining constant pshufb masks - this test would've failed once we decode bitcasted masks as well. llvm-svn: 261095
2016-02-17 22:56:58 +08:00
%4 = tail call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %V, <16 x i8> %3)
[X86][SSE] Regenerate PSHUFB shuffle mask comments tests llvm-svn: 260061
2016-02-08 06:22:09 +08:00
ret <16 x i8> %4
X86: Properly decode shuffle masks when the constant pool type is weird It's possible for the constant pool entry for the shuffle mask to come from a completely different operation. This occurs when Constants have the same bit pattern but have different types. Make DecodePSHUFBMask tolerant of types which, after a bitcast, are appropriately sized vector types. This fixes PR22188. llvm-svn: 225597
2015-01-11 13:08:57 +08:00
}
[X86][SSE] Update pshufb mask tests. We are getting better at combining constant pshufb masks - use a real input instead of undef. Add test for decoding multi-use bitcasted masks as well (actual support will come soon). llvm-svn: 261101
2016-02-17 23:52:39 +08:00
define <16 x i8> @test5(<16 x i8> %V) {
[X86][SSE] Regenerate PSHUFB shuffle mask comments tests llvm-svn: 260061
2016-02-08 06:22:09 +08:00
; CHECK-LABEL: test5:
; CHECK: # BB#0:
; CHECK-NEXT: movl $1, %eax
[X86][SSE] Update pshufb mask tests. We are getting better at combining constant pshufb masks - use a real input instead of undef. Add test for decoding multi-use bitcasted masks as well (actual support will come soon). llvm-svn: 261101
2016-02-17 23:52:39 +08:00
; CHECK-NEXT: movd %rax, %xmm1
; CHECK-NEXT: movaps %xmm1, (%rax)
; CHECK-NEXT: movdqa {{.*#+}} xmm1 = [1,1]
; CHECK-NEXT: movdqa %xmm1, (%rax)
; CHECK-NEXT: pshufb %xmm1, %xmm0
[X86][SSE] Regenerate PSHUFB shuffle mask comments tests llvm-svn: 260061
2016-02-08 06:22:09 +08:00
; CHECK-NEXT: retq
X86: Don't crash if we can't decode the pshufb mask Constant pool entries are uniqued by their contents regardless of their type. This means that a pshufb can have a shuffle mask which isn't a simple array of bytes. The code path which attempts to decode the mask didn't check for failure, causing PR22559. llvm-svn: 228979
2015-02-13 07:26:26 +08:00
store <2 x i64> <i64 1, i64 0>, <2 x i64>* undef, align 16
[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
%l = load <2 x i64>, <2 x i64>* undef, align 16
X86: Don't crash if we can't decode the pshufb mask Constant pool entries are uniqued by their contents regardless of their type. This means that a pshufb can have a shuffle mask which isn't a simple array of bytes. The code path which attempts to decode the mask didn't check for failure, causing PR22559. llvm-svn: 228979
2015-02-13 07:26:26 +08:00
%shuffle = shufflevector <2 x i64> %l, <2 x i64> undef, <2 x i32> zeroinitializer
store <2 x i64> %shuffle, <2 x i64>* undef, align 16
[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
%1 = load <16 x i8>, <16 x i8>* undef, align 16
[X86][SSE] Update pshufb mask tests. We are getting better at combining constant pshufb masks - use a real input instead of undef. Add test for decoding multi-use bitcasted masks as well (actual support will come soon). llvm-svn: 261101
2016-02-17 23:52:39 +08:00
%2 = call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %V, <16 x i8> %1)
X86: Don't crash if we can't decode the pshufb mask Constant pool entries are uniqued by their contents regardless of their type. This means that a pshufb can have a shuffle mask which isn't a simple array of bytes. The code path which attempts to decode the mask didn't check for failure, causing PR22559. llvm-svn: 228979
2015-02-13 07:26:26 +08:00
ret <16 x i8> %2
}
[X86][SSE] Update pshufb mask tests. We are getting better at combining constant pshufb masks - use a real input instead of undef. Add test for decoding multi-use bitcasted masks as well (actual support will come soon). llvm-svn: 261101
2016-02-17 23:52:39 +08:00
; Test for a reused constant that would allow the pshufb to combine to a simpler instruction.
define <16 x i8> @test6(<16 x i8> %V, <2 x i64>* %P) {
; CHECK-LABEL: test6:
; CHECK: # BB#0:
[X86][SSE] Improve PSHUFB shuffle mask decoding. In cases where the PSHUFB shuffle mask is shared it might not be bitcasted to a vXi8 byte vector. This patch adds support for decoding these wider shuffle masks from the ConstantPool. The test case in question makes use of this to recognise the shuffle mask is an unary UNPCKL pattern and simplifies accordingly. llvm-svn: 261201
2016-02-18 18:17:40 +08:00
; CHECK-NEXT: movaps {{.*#+}} xmm1 = [217019414673948672,506380106026255364]
; CHECK-NEXT: movaps %xmm1, (%rdi)
; CHECK-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
[X86][SSE] Update pshufb mask tests. We are getting better at combining constant pshufb masks - use a real input instead of undef. Add test for decoding multi-use bitcasted masks as well (actual support will come soon). llvm-svn: 261101
2016-02-17 23:52:39 +08:00
; CHECK-NEXT: retq
%1 = insertelement <2 x i64> undef, i64 217019414673948672, i32 0
%2 = insertelement <2 x i64> %1, i64 506380106026255364, i32 1
store <2 x i64> %2, <2 x i64>* %P, align 16
%3 = bitcast <2 x i64> %2 to <16 x i8>
%4 = tail call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %V, <16 x i8> %3)
ret <16 x i8> %4
}
Fix assert when decoding PSHUFB mask The PSHUFB mask decode routine used to assert if the mask index was out of range (<0 or greater than the size of the vector). The problem is, we can legitimately have a PSHUFB with a large index using intrinsics. The instruction only uses the least significant 4 bits. This change removes the assert and masks the index to match the instruction behaviour. llvm-svn: 218242
2014-09-22 19:54:38 +08:00
declare <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8>, <16 x i8>) nounwind readnone