[llvm] r345285 - [X86] Remove some uarch tuning flags from KNL that look to have been inherited from SNB/IVB incorrectly
Craig Topper via llvm-commits
llvm-commits at lists.llvm.org
Thu Oct 25 10:28:57 PDT 2018
Author: ctopper
Date: Thu Oct 25 10:28:57 2018
New Revision: 345285
URL: http://llvm.org/viewvc/llvm-project?rev=345285&view=rev
Log:
[X86] Remove some uarch tuning flags from KNL that look to have been inherited from SNB/IVB incorrectly
KNL is based on a modified Silvermont core so I don't think these features apply. I think the LEA flag is probably also wrong, but I'm less sure as I barely understand the 3 LEA flags we have currently.
Differential Revision: https://reviews.llvm.org/D53671
Modified:
llvm/trunk/lib/Target/X86/X86.td
llvm/trunk/test/CodeGen/X86/avx512-select.ll
Modified: llvm/trunk/lib/Target/X86/X86.td
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/X86/X86.td?rev=345285&r1=345284&r2=345285&view=diff
==============================================================================
--- llvm/trunk/lib/Target/X86/X86.td (original)
+++ llvm/trunk/lib/Target/X86/X86.td Thu Oct 25 10:28:57 2018
@@ -823,11 +823,7 @@ def KNLFeatures : ProcessorFeatures<[],
FeatureXSAVEOPT,
FeatureLAHFSAHF,
FeatureSlow3OpsLEA,
- FeatureFastScalarFSQRT,
- FeatureFastSHLDRotate,
FeatureSlowIncDec,
- FeatureMergeToThreeWayBranch,
- FeatureMacroFusion,
FeatureRDRAND,
FeatureF16C,
FeatureFSGSBase,
Modified: llvm/trunk/test/CodeGen/X86/avx512-select.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/avx512-select.ll?rev=345285&r1=345284&r2=345285&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/avx512-select.ll (original)
+++ llvm/trunk/test/CodeGen/X86/avx512-select.ll Thu Oct 25 10:28:57 2018
@@ -16,8 +16,8 @@ define <16 x i32> @select00(i32 %a, <16
;
; X64-LABEL: select00:
; X64: # %bb.0:
-; X64-NEXT: vpxor %xmm1, %xmm1, %xmm1
; X64-NEXT: cmpl $255, %edi
+; X64-NEXT: vpxor %xmm1, %xmm1, %xmm1
; X64-NEXT: je .LBB0_2
; X64-NEXT: # %bb.1:
; X64-NEXT: vmovdqa64 %zmm0, %zmm1
@@ -44,8 +44,8 @@ define <8 x i64> @select01(i32 %a, <8 x
;
; X64-LABEL: select01:
; X64: # %bb.0:
-; X64-NEXT: vpxor %xmm1, %xmm1, %xmm1
; X64-NEXT: cmpl $255, %edi
+; X64-NEXT: vpxor %xmm1, %xmm1, %xmm1
; X64-NEXT: je .LBB1_2
; X64-NEXT: # %bb.1:
; X64-NEXT: vmovdqa64 %zmm0, %zmm1
More information about the llvm-commits
mailing list