maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[AVX-512] Add EVEX form of VMOVZPQILo2PQIZrm to load folding tables to match SSE and AVX. 

llvm-svn: 287523
This commit is contained in:
Craig Topper 2016-11-21 07:51:31 +00:00
parent 2bb523f554
commit 9f2d632ee7
2 changed files with 13 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
llvm/lib/Target/X86/X86InstrInfo.cpp
View File

@ -855,6 +855,7 @@ X86InstrInfo::X86InstrInfo(X86Subtarget &STI)
// AVX-512 foldable instructions
{ X86::VMOV64toPQIZrr, X86::VMOVQI2PQIZrm, 0 },
{ X86::VMOVZPQILo2PQIZrr,X86::VMOVZPQILo2PQIZrm, TB_ALIGN_16 },
{ X86::VMOVDI2SSZrr, X86::VMOVDI2SSZrm, 0 },
{ X86::VMOVAPDZrr, X86::VMOVAPDZrm, TB_ALIGN_64 },
{ X86::VMOVAPSZrr, X86::VMOVAPSZrm, TB_ALIGN_64 },

14
llvm/test/CodeGen/X86/stack-folding-int-avx512.ll
View File

@ -377,7 +377,7 @@ define <4 x i64> @stack_fold_extracti64x4(<8 x i64> %a0, <8 x i64> %a1) {
define <16 x i32> @stack_fold_inserti32x8(<8 x i32> %a0, <8 x i32> %a1) {
;CHECK-LABEL: stack_fold_inserti32x8
;CHECK: vinserti32x8 $1, {{-?[0-9]*}}(%rsp), {{%zmm[0-9][0-9]*}}, {{%zmm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
%2 = shufflevector <8 x i32> %a0, <8 x i32> %a1, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
; add forces execution domain
%3 = add <16 x i32> %2, <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
@ -387,9 +387,19 @@ define <16 x i32> @stack_fold_inserti32x8(<8 x i32> %a0, <8 x i32> %a1) {
define <8 x i64> @stack_fold_inserti64x4(<4 x i64> %a0, <4 x i64> %a1) {
;CHECK-LABEL: stack_fold_inserti64x4
;CHECK: vinserti64x4 $1, {{-?[0-9]*}}(%rsp), {{%zmm[0-9][0-9]*}}, {{%zmm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
%2 = shufflevector <4 x i64> %a0, <4 x i64> %a1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; add forces execution domain
%3 = add <8 x i64> %2, <i64 1, i64 1, i64 1, i64 1, i64 1, i64 1, i64 1, i64 1>
ret <8 x i64> %3
}
define <2 x i64> @stack_fold_movq_load(<2 x i64> %a0) {
;CHECK-LABEL: stack_fold_movq_load
;CHECK: movq {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
%2 = shufflevector <2 x i64> %a0, <2 x i64> zeroinitializer, <2 x i32> <i32 0, i32 2>
; add forces execution domain
%3 = add <2 x i64> %2, <i64 1, i64 1>
ret <2 x i64> %3
}