RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-02-09 05:47:13 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

[x86, AVX] don't add a vzeroupper if that's what the code is already doing (PR27823)

Browse Source 
This isn't the complete fix, but it handles the trivial examples of duplicate vzero* ops in PR27823:
https://llvm.org/bugs/show_bug.cgi?id=27823
...and amusingly, the bogus cases already exist as regression tests, so let's take this baby step.

We'll need to do more in the general case where there's legitimate AVX usage in the function + there's
already a vzero in the code.

Differential Revision: http://reviews.llvm.org/D20477

llvm-svn: 270378
This commit is contained in:
Sanjay Patel 2016-05-22 20:22:47 +00:00
parent e49c68f164
commit b2763427c2
3 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
lib/Target/X86/X86VZeroUpper.cpp
View File

@ -192,6 +192,12 @@ void VZeroUpperInserter::processBasicBlock(MachineBasicBlock &MBB) {
if ((!IsControlFlow || IsReturnFromX86INTR) && CurState == EXITS_DIRTY)
continue;
// Ignore existing VZERO* instructions.
// FIXME: The existence of these instructions should be used to modify the
// current state and/or used when deciding whether we need to create a VZU.
if (MI->getOpcode() == X86::VZEROALL || MI->getOpcode() == X86::VZEROUPPER)
continue;
if (hasYmmReg(MI)) {
// We found a ymm-using instruction; this could be an AVX instruction,
// or it could be control flow.

4
test/CodeGen/X86/avx-intrinsics-fast-isel.ll
View File

@ -3736,13 +3736,11 @@ define void @test_mm256_zeroall() nounwind {
; X32-LABEL: test_mm256_zeroall:
; X32: # BB#0:
; X32-NEXT: vzeroall
; X32-NEXT: vzeroupper
; X32-NEXT: retl
;
; X64-LABEL: test_mm256_zeroall:
; X64: # BB#0:
; X64-NEXT: vzeroall
; X64-NEXT: vzeroupper
; X64-NEXT: retq
call void @llvm.x86.avx.vzeroall()
ret void
@ -3753,13 +3751,11 @@ define void @test_mm256_zeroupper() nounwind {
; X32-LABEL: test_mm256_zeroupper:
; X32: # BB#0:
; X32-NEXT: vzeroupper
; X32-NEXT: vzeroupper
; X32-NEXT: retl
;
; X64-LABEL: test_mm256_zeroupper:
; X64: # BB#0:
; X64-NEXT: vzeroupper
; X64-NEXT: vzeroupper
; X64-NEXT: retq
call void @llvm.x86.avx.vzeroupper()
ret void

2
test/CodeGen/X86/avx-intrinsics-x86.ll
View File

@ -4755,7 +4755,6 @@ define void @test_x86_avx_vzeroall() {
; AVX-LABEL: test_x86_avx_vzeroall:
; AVX: ## BB#0:
; AVX-NEXT: vzeroall
; AVX-NEXT: vzeroupper
; AVX-NEXT: retl
;
; AVX512VL-LABEL: test_x86_avx_vzeroall:
@ -4772,7 +4771,6 @@ define void @test_x86_avx_vzeroupper() {
; AVX-LABEL: test_x86_avx_vzeroupper:
; AVX: ## BB#0:
; AVX-NEXT: vzeroupper
; AVX-NEXT: vzeroupper
; AVX-NEXT: retl
;
; AVX512VL-LABEL: test_x86_avx_vzeroupper: