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/vselect-avx.ll

93 lines
4.3 KiB
LLVM
Raw Normal View History

[X86] Fix a bug in the lowering of the mask of VSELECT. X86 code to lower VSELECT messed a bit with the bits set in the mask of VSELECT when it knows it can be lowered into BLEND. Indeed, only the high bits need to be set for those and it optimizes those accordingly. However, when the mask is a compile time constant, the lowering will be handled by the generic optimizer and those modifications will generate bad code in the generic optimizer. This patch fixes that by preventing the optimization if the VSELECT will be handled by the generic optimizer. <rdar://problem/18675020> llvm-svn: 220242
2014-10-21 07:13:30 +08:00
; RUN: llc %s -o - -mattr=+avx | FileCheck %s
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx"
; For this test we used to optimize the <i1 true, i1 false, i1 false, i1 true>
; mask into <i32 2147483648, i32 0, i32 0, i32 2147483648> because we thought
; we would lower that into a blend where only the high bit is relevant.
; However, since the whole mask is constant, this is simplified incorrectly
; by the generic code, because it was expecting -1 in place of 2147483648.
;
; The problem does not occur without AVX, because vselect of v4i32 is not legal
; nor custom.
;
; <rdar://problem/18675020>
; CHECK-LABEL: test:
Revert "Temporarily revert r220777 to sort out build bot breakage." This reverts commit r221028. Later commits depend on this and reverting just this one causes even more bots to fail. llvm-svn: 221041
2014-11-01 11:19:45 +08:00
; CHECK: vmovdqa {{.*#+}} xmm0 = [65535,0,0,65535]
; CHECK: vmovdqa {{.*#+}} xmm2 = [65533,124,125,14807]
[X86] Fix a bug in the lowering of the mask of VSELECT. X86 code to lower VSELECT messed a bit with the bits set in the mask of VSELECT when it knows it can be lowered into BLEND. Indeed, only the high bits need to be set for those and it optimizes those accordingly. However, when the mask is a compile time constant, the lowering will be handled by the generic optimizer and those modifications will generate bad code in the generic optimizer. This patch fixes that by preventing the optimization if the VSELECT will be handled by the generic optimizer. <rdar://problem/18675020> llvm-svn: 220242
2014-10-21 07:13:30 +08:00
; CHECK: ret
define void @test(<4 x i16>* %a, <4 x i16>* %b) {
body:
%predphi = select <4 x i1> <i1 true, i1 false, i1 false, i1 true>, <4 x i16> <i16 -3, i16 545, i16 4385, i16 14807>, <4 x i16> <i16 123, i16 124, i16 125, i16 127>
%predphi42 = select <4 x i1> <i1 true, i1 false, i1 false, i1 true>, <4 x i16> <i16 -1, i16 -1, i16 -1, i16 -1>, <4 x i16> zeroinitializer
store <4 x i16> %predphi, <4 x i16>* %a, align 8
store <4 x i16> %predphi42, <4 x i16>* %b, align 8
ret void
}
[X86] Lower VSELECT into SHRUNKBLEND when we shrink the bits used into the condition to match a blend. This prevents optimizations that work on VSELECT to perform invalid transformations. Indeed, the optimized condition does not match the vector boolean content that is expected and bad things may happen. This patch yields the exact same code on the whole test-suite + specs (-O3 and -O3 -march=core-avx2), it improves one test case (vector-blend.ll) and fixes a bug reduced in vselect-avx.ll. <rdar://problem/18819506> llvm-svn: 221429
2014-11-06 10:25:03 +08:00
; Improve code coverage.
;
; When shrinking the condition used into the select to match a blend, this
; test case exercises the path where the modified node is not the root
; of the condition.
;
; CHECK-LABEL: test2:
; CHECK: vpslld $31, %xmm0, %xmm0
; CHECK-NEXT: vpmovsxdq %xmm0, %xmm1
; CHECK-NEXT: vpshufd $78, %xmm0, %xmm0 ## xmm0 = xmm0[2,3,0,1]
; CHECK-NEXT: vpmovsxdq %xmm0, %xmm0
; CHECK-NEXT: vinsertf128 $1, %xmm0, %ymm1, [[MASK:%ymm[0-9]+]]
; CHECK: vblendvpd [[MASK]]
; CHECK: retq
define void @test2(double** %call1559, i64 %indvars.iv4198, <4 x i1> %tmp1895) {
bb:
[opaque pointer type] Add textual IR support for explicit type parameter to getelementptr instruction One of several parallel first steps to remove the target type of pointers, replacing them with a single opaque pointer type. This adds an explicit type parameter to the gep instruction so that when the first parameter becomes an opaque pointer type, the type to gep through is still available to the instructions. * This doesn't modify gep operators, only instructions (operators will be handled separately) * Textual IR changes only. Bitcode (including upgrade) and changing the in-memory representation will be in separate changes. * geps of vectors are transformed as: getelementptr <4 x float*> %x, ... ->getelementptr float, <4 x float*> %x, ... Then, once the opaque pointer type is introduced, this will ultimately look like: getelementptr float, <4 x ptr> %x with the unambiguous interpretation that it is a vector of pointers to float. * address spaces remain on the pointer, not the type: getelementptr float addrspace(1)* %x ->getelementptr float, float addrspace(1)* %x Then, eventually: getelementptr float, ptr addrspace(1) %x Importantly, the massive amount of test case churn has been automated by same crappy python code. I had to manually update a few test cases that wouldn't fit the script's model (r228970,r229196,r229197,r229198). The python script just massages stdin and writes the result to stdout, I then wrapped that in a shell script to handle replacing files, then using the usual find+xargs to migrate all the files. update.py: import fileinput import sys import re ibrep = re.compile(r"(^.*?[^%\w]getelementptr inbounds )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))") normrep = re.compile( r"(^.*?[^%\w]getelementptr )(((?:<\d* x )?)(.*?)(| addrspace\(\d\)) *\*(|>)(?:$| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$))") def conv(match, line): if not match: return line line = match.groups()[0] if len(match.groups()[5]) == 0: line += match.groups()[2] line += match.groups()[3] line += ", " line += match.groups()[1] line += "\n" return line for line in sys.stdin: if line.find("getelementptr ") == line.find("getelementptr inbounds"): if line.find("getelementptr inbounds") != line.find("getelementptr inbounds ("): line = conv(re.match(ibrep, line), line) elif line.find("getelementptr ") != line.find("getelementptr ("): line = conv(re.match(normrep, line), line) sys.stdout.write(line) apply.sh: for name in "$@" do python3 `dirname "$0"`/update.py < "$name" > "$name.tmp" && mv "$name.tmp" "$name" rm -f "$name.tmp" done The actual commands: From llvm/src: find test/ -name *.ll | xargs ./apply.sh From llvm/src/tools/clang: find test/ -name *.mm -o -name *.m -o -name *.cpp -o -name *.c | xargs -I '{}' ../../apply.sh "{}" From llvm/src/tools/polly: find test/ -name *.ll | xargs ./apply.sh After that, check-all (with llvm, clang, clang-tools-extra, lld, compiler-rt, and polly all checked out). The extra 'rm' in the apply.sh script is due to a few files in clang's test suite using interesting unicode stuff that my python script was throwing exceptions on. None of those files needed to be migrated, so it seemed sufficient to ignore those cases. Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7636 llvm-svn: 230786
2015-02-28 03:29:02 +08:00
%arrayidx1928 = getelementptr inbounds double*, double** %call1559, i64 %indvars.iv4198
[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
%tmp1888 = load double*, double** %arrayidx1928, align 8
[X86] Lower VSELECT into SHRUNKBLEND when we shrink the bits used into the condition to match a blend. This prevents optimizations that work on VSELECT to perform invalid transformations. Indeed, the optimized condition does not match the vector boolean content that is expected and bad things may happen. This patch yields the exact same code on the whole test-suite + specs (-O3 and -O3 -march=core-avx2), it improves one test case (vector-blend.ll) and fixes a bug reduced in vselect-avx.ll. <rdar://problem/18819506> llvm-svn: 221429
2014-11-06 10:25:03 +08:00
%predphi.v.v = select <4 x i1> %tmp1895, <4 x double> <double -5.000000e-01, double -5.000000e-01, double -5.000000e-01, double -5.000000e-01>, <4 x double> <double 5.000000e-01, double 5.000000e-01, double 5.000000e-01, double 5.000000e-01>
%tmp1900 = bitcast double* %tmp1888 to <4 x double>*
store <4 x double> %predphi.v.v, <4 x double>* %tmp1900, align 8
ret void
}
; For this test, we used to optimized the conditional mask for the blend, i.e.,
; we shrunk some of its bits.
; However, this same mask was used in another select (%predphi31) that turned out
; to be optimized into a and. In that case, the conditional mask was wrong.
;
; Make sure that the and is fed by the original mask.
;
; <rdar://problem/18819506>
; CHECK-LABEL: test3:
Fixes two issue in SimplifyDemandedBits of sext_in_reg: 1) We should not try to simplify if the sext has multiple uses 2) There is no need to simplify is the source value is already sign-extended. Patch by Gil Rapaport <gil.rapaport@intel.com> Differential Revision: http://reviews.llvm.org/D6949 llvm-svn: 229659
2015-02-18 17:43:40 +08:00
; Compute the mask.
; CHECK: vpcmpeqd {{%xmm[0-9]+}}, {{%xmm[0-9]+}}, [[MASK:%xmm[0-9]+]]
; Do not shrink the bit of the mask.
; CHECK-NOT: vpslld $31, [[MASK]], {{%xmm[0-9]+}}
; Use the mask in the blend.
; CHECK-NEXT: vblendvps [[MASK]], %xmm{{[0-9]+}}, %xmm{{[0-9]+}}, %xmm{{[0-9]+}}
; Use the mask in the and.
; CHECK-NEXT: vpand LCPI2_2(%rip), [[MASK]], {{%xmm[0-9]+}}
[X86] Lower VSELECT into SHRUNKBLEND when we shrink the bits used into the condition to match a blend. This prevents optimizations that work on VSELECT to perform invalid transformations. Indeed, the optimized condition does not match the vector boolean content that is expected and bad things may happen. This patch yields the exact same code on the whole test-suite + specs (-O3 and -O3 -march=core-avx2), it improves one test case (vector-blend.ll) and fixes a bug reduced in vselect-avx.ll. <rdar://problem/18819506> llvm-svn: 221429
2014-11-06 10:25:03 +08:00
; CHECK: retq
define void @test3(<4 x i32> %induction30, <4 x i16>* %tmp16, <4 x i16>* %tmp17, <4 x i16> %tmp3, <4 x i16> %tmp12) {
%tmp6 = srem <4 x i32> %induction30, <i32 3, i32 3, i32 3, i32 3>
%tmp7 = icmp eq <4 x i32> %tmp6, zeroinitializer
%predphi = select <4 x i1> %tmp7, <4 x i16> %tmp3, <4 x i16> %tmp12
%predphi31 = select <4 x i1> %tmp7, <4 x i16> <i16 -1, i16 -1, i16 -1, i16 -1>, <4 x i16> zeroinitializer
store <4 x i16> %predphi31, <4 x i16>* %tmp16, align 8
store <4 x i16> %predphi, <4 x i16>* %tmp17, align 8
ret void
}
[x86] Fix PR22706 where we would incorrectly try lower a v32i8 dynamic blend as legal. We made the same mistake in two different places. Whenever we are custom lowering a v32i8 blend we need to check whether we are custom lowering it only for constant conditions that can be shuffled, or whether we actually have AVX2 and full dynamic blending support on bytes. Both are fixed, with comments added to make it clear what is going on and a new test case. llvm-svn: 230695
2015-02-27 06:15:34 +08:00
; We shouldn't try to lower this directly using VSELECT because we don't have
; vpblendvb in AVX1, only in AVX2. Instead, it should be expanded.
;
; CHECK-LABEL: PR22706:
; CHECK: vpcmpgtb
; CHECK: vpcmpgtb
define <32 x i8> @PR22706(<32 x i1> %x) {
%tmp = select <32 x i1> %x, <32 x i8> <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>, <32 x i8> <i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2, i8 2>
ret <32 x i8> %tmp
}