OSchip
/
llvm-project
mirror of https://github.com/THU-DSP-LAB/llvm-project.git
13
0
Fork 6
Code Issues Packages Projects Releases Wiki Activity

[X86] Add MMX MOVD/MOVQ stores to folding tables to support stack folding 

llvm-svn: 372770
This commit is contained in:
Simon Pilgrim 2019-09-24 16:15:32 +00:00
parent 45fd1e9d50
commit a7f27f357d
2 changed files with 4 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llvm/lib/Target/X86/X86InstrFoldTables.cpp
View File

@ -292,6 +292,8 @@ static const X86MemoryFoldTableEntry MemoryFoldTable0[] = {
{ X86::JMP32r_NT, X86::JMP32m_NT, TB_FOLDED_LOAD },
{ X86::JMP64r, X86::JMP64m, TB_FOLDED_LOAD },
{ X86::JMP64r_NT, X86::JMP64m_NT, TB_FOLDED_LOAD },
{ X86::MMX_MOVD64from64rr, X86::MMX_MOVD64from64rm, TB_FOLDED_STORE | TB_NO_REVERSE },
{ X86::MMX_MOVD64grr, X86::MMX_MOVD64mr, TB_FOLDED_STORE | TB_NO_REVERSE },
{ X86::MOV16ri, X86::MOV16mi, TB_FOLDED_STORE },
{ X86::MOV16rr, X86::MOV16mr, TB_FOLDED_STORE },
{ X86::MOV32ri, X86::MOV32mi, TB_FOLDED_STORE },

8
llvm/test/CodeGen/X86/stack-folding-mmx.ll
View File

@ -97,7 +97,6 @@ declare x86_mmx @llvm.x86.sse.cvttps2pi(<4 x float>) nounwind readnone
; TODO stack_fold_movd_load
; TODO stack_fold_movd_store
; padd forces execution on mmx
define i32 @stack_fold_movd_store(x86_mmx %a0) nounwind {
; CHECK-LABEL: stack_fold_movd_store:
@ -109,8 +108,7 @@ define i32 @stack_fold_movd_store(x86_mmx %a0) nounwind {
; CHECK-NEXT: pushq %r12
; CHECK-NEXT: pushq %rbx
; CHECK-NEXT: paddb %mm0, %mm0
; CHECK-NEXT: movd %mm0, %eax
; CHECK-NEXT: movl %eax, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
; CHECK-NEXT: movd %mm0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
; CHECK-NEXT: #APP
; CHECK-NEXT: nop
; CHECK-NEXT: #NO_APP
@ -131,7 +129,6 @@ define i32 @stack_fold_movd_store(x86_mmx %a0) nounwind {
; TODO stack_fold_movq_load
; TODO stack_fold_movq_store
; padd forces execution on mmx
define i64 @stack_fold_movq_store(x86_mmx %a0) nounwind {
; CHECK-LABEL: stack_fold_movq_store:
@ -143,8 +140,7 @@ define i64 @stack_fold_movq_store(x86_mmx %a0) nounwind {
; CHECK-NEXT: pushq %r12
; CHECK-NEXT: pushq %rbx
; CHECK-NEXT: paddb %mm0, %mm0
; CHECK-NEXT: movq %mm0, %rax
; CHECK-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; CHECK-NEXT: movq %mm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Folded Spill
; CHECK-NEXT: #APP
; CHECK-NEXT: nop
; CHECK-NEXT: #NO_APP