diff options
| author | Eric Christopher <echristo@gmail.com> | 2019-11-20 15:18:08 -0800 |
|---|---|---|
| committer | Eric Christopher <echristo@gmail.com> | 2019-11-20 15:19:31 -0800 |
| commit | cd8748a15f2d18861b3548eb26ed2b52e5ee50b4 (patch) | |
| tree | 1c0b1e08c680147e4f5f148d5232870771ae78b7 /llvm/test/Transforms/SLPVectorizer | |
| parent | 24aafcadff3851ec3a0c42303fec63e815b19566 (diff) | |
| download | bcm5719-llvm-cd8748a15f2d18861b3548eb26ed2b52e5ee50b4.tar.gz bcm5719-llvm-cd8748a15f2d18861b3548eb26ed2b52e5ee50b4.zip | |
Temporarily Revert "[SLP] allow forming 2-way reduction patterns"
After speaking with Sanjay - seeing a number of miscompiles and working
on tracking down a testcase. None of the follow on patches seem to
have helped so far.
This reverts commit 7ff57705ba196ce649d6034614b3b9df57e1f84f.
Diffstat (limited to 'llvm/test/Transforms/SLPVectorizer')
| -rw-r--r-- | llvm/test/Transforms/SLPVectorizer/X86/reduction2.ll | 19 |
1 files changed, 10 insertions, 9 deletions
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/reduction2.ll b/llvm/test/Transforms/SLPVectorizer/X86/reduction2.ll index fef9a8e50cd..b5f43354927 100644 --- a/llvm/test/Transforms/SLPVectorizer/X86/reduction2.ll +++ b/llvm/test/Transforms/SLPVectorizer/X86/reduction2.ll @@ -54,10 +54,10 @@ define double @foo(double* nocapture %D) { define i1 @two_wide_fcmp_reduction(<2 x double> %a0) { ; CHECK-LABEL: @two_wide_fcmp_reduction( ; CHECK-NEXT: [[A:%.*]] = fcmp ogt <2 x double> [[A0:%.*]], <double 1.000000e+00, double 1.000000e+00> -; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <2 x i1> [[A]], <2 x i1> undef, <2 x i32> <i32 1, i32 undef> -; CHECK-NEXT: [[BIN_RDX:%.*]] = and <2 x i1> [[A]], [[RDX_SHUF]] -; CHECK-NEXT: [[TMP1:%.*]] = extractelement <2 x i1> [[BIN_RDX]], i32 0 -; CHECK-NEXT: ret i1 [[TMP1]] +; CHECK-NEXT: [[B:%.*]] = extractelement <2 x i1> [[A]], i32 0 +; CHECK-NEXT: [[C:%.*]] = extractelement <2 x i1> [[A]], i32 1 +; CHECK-NEXT: [[D:%.*]] = and i1 [[B]], [[C]] +; CHECK-NEXT: ret i1 [[D]] ; %a = fcmp ogt <2 x double> %a0, <double 1.0, double 1.0> %b = extractelement <2 x i1> %a, i32 0 @@ -96,11 +96,12 @@ define i1 @fcmp_lt_gt(double %a, double %b, double %c) { ; CHECK-NEXT: [[TMP5:%.*]] = insertelement <2 x double> undef, double [[MUL]], i32 0 ; CHECK-NEXT: [[TMP6:%.*]] = insertelement <2 x double> [[TMP5]], double [[MUL]], i32 1 ; CHECK-NEXT: [[TMP7:%.*]] = fdiv <2 x double> [[TMP4]], [[TMP6]] -; CHECK-NEXT: [[TMP8:%.*]] = fcmp olt <2 x double> [[TMP7]], <double 0x3EB0C6F7A0B5ED8D, double 0x3EB0C6F7A0B5ED8D> -; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <2 x i1> [[TMP8]], <2 x i1> undef, <2 x i32> <i32 1, i32 undef> -; CHECK-NEXT: [[BIN_RDX:%.*]] = and <2 x i1> [[TMP8]], [[RDX_SHUF]] -; CHECK-NEXT: [[TMP9:%.*]] = extractelement <2 x i1> [[BIN_RDX]], i32 0 -; CHECK-NEXT: br i1 [[TMP9]], label [[CLEANUP:%.*]], label [[LOR_LHS_FALSE:%.*]] +; CHECK-NEXT: [[TMP8:%.*]] = extractelement <2 x double> [[TMP7]], i32 1 +; CHECK-NEXT: [[CMP:%.*]] = fcmp olt double [[TMP8]], 0x3EB0C6F7A0B5ED8D +; CHECK-NEXT: [[TMP9:%.*]] = extractelement <2 x double> [[TMP7]], i32 0 +; CHECK-NEXT: [[CMP4:%.*]] = fcmp olt double [[TMP9]], 0x3EB0C6F7A0B5ED8D +; CHECK-NEXT: [[OR_COND:%.*]] = and i1 [[CMP]], [[CMP4]] +; CHECK-NEXT: br i1 [[OR_COND]], label [[CLEANUP:%.*]], label [[LOR_LHS_FALSE:%.*]] ; CHECK: lor.lhs.false: ; CHECK-NEXT: [[TMP10:%.*]] = fcmp ule <2 x double> [[TMP7]], <double 1.000000e+00, double 1.000000e+00> ; CHECK-NEXT: [[TMP11:%.*]] = extractelement <2 x i1> [[TMP10]], i32 0 |
