Skip to content

release/20.x: [X86][SSE] Don't emit SSE2 load instructions in SSE1-only mode (#134547) #135191

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Apr 11, 2025
Merged

release/20.x: [X86][SSE] Don't emit SSE2 load instructions in SSE1-only mode (#134547) #135191

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 7 additions & 4 deletions llvm/lib/Target/X86/X86FixupVectorConstants.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -333,6 +333,7 @@ bool X86FixupVectorConstantsPass::processInstruction(MachineFunction &MF,
MachineInstr &MI) {
unsigned Opc = MI.getOpcode();
MachineConstantPool *CP = MI.getParent()->getParent()->getConstantPool();
bool HasSSE2 = ST->hasSSE2();
bool HasSSE41 = ST->hasSSE41();
bool HasAVX2 = ST->hasAVX2();
bool HasDQI = ST->hasDQI();
Expand Down Expand Up @@ -394,11 +395,13 @@ bool X86FixupVectorConstantsPass::processInstruction(MachineFunction &MF,
case X86::MOVAPDrm:
case X86::MOVAPSrm:
case X86::MOVUPDrm:
case X86::MOVUPSrm:
case X86::MOVUPSrm: {
// TODO: SSE3 MOVDDUP Handling
return FixupConstant({{X86::MOVSSrm, 1, 32, rebuildZeroUpperCst},
{X86::MOVSDrm, 1, 64, rebuildZeroUpperCst}},
128, 1);
FixupEntry Fixups[] = {
{X86::MOVSSrm, 1, 32, rebuildZeroUpperCst},
{HasSSE2 ? X86::MOVSDrm : 0, 1, 64, rebuildZeroUpperCst}};
return FixupConstant(Fixups, 128, 1);
}
case X86::VMOVAPDrm:
case X86::VMOVAPSrm:
case X86::VMOVUPDrm:
Expand Down
20 changes: 20 additions & 0 deletions llvm/test/CodeGen/X86/pr134607.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,20 @@
; RUN: llc < %s -mtriple=i386-unknown-unknown -mattr=+sse -O3 | FileCheck %s --check-prefixes=X86
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=-sse2,+sse -O3 | FileCheck %s --check-prefixes=X64-SSE1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2,+sse -O3 | FileCheck %s --check-prefixes=X64-SSE2

define void @store_v2f32_constant(ptr %v) {
; X86-LABEL: store_v2f32_constant:
; X86: # %bb.0:
; X86-NEXT: movl 4(%esp), %eax
; X86-NEXT: movaps {{\.?LCPI[0-9]+_[0-9]+}}, %xmm0

; X64-SSE1-LABEL: store_v2f32_constant:
; X64-SSE1: # %bb.0:
; X64-SSE1-NEXT: movaps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0

; X64-SSE2-LABEL: store_v2f32_constant:
; X64-SSE2: # %bb.0:
; X64-SSE2-NEXT: movsd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
store <2 x float> <float 2.560000e+02, float 5.120000e+02>, ptr %v, align 4
ret void
}
Loading