forked from OSchip/llvm-project
2055 lines
116 KiB
LLVM
2055 lines
116 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -O3 -disable-peephole -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512dq < %s | FileCheck %s
|
|
|
|
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
|
|
target triple = "x86_64-unknown-unknown"
|
|
|
|
; Stack reload folding tests.
|
|
;
|
|
; By including a nop call with sideeffects we can force a partial register spill of the
|
|
; relevant registers and check that the reload is correctly folded into the instruction.
|
|
|
|
define <8 x double> @stack_fold_addpd_zmm(<8 x double> %a0, <8 x double> %a1) {
|
|
; CHECK-LABEL: stack_fold_addpd_zmm:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vaddpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = fadd <8 x double> %a0, %a1
|
|
ret <8 x double> %2
|
|
}
|
|
|
|
define <8 x double> @stack_fold_addpd_zmm_k(<8 x double> %a0, <8 x double> %a1, i8 %mask, <8 x double>* %passthru) {
|
|
; CHECK-LABEL: stack_fold_addpd_zmm_k:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovapd (%rsi), %zmm2
|
|
; CHECK-NEXT: vaddpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm2 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: vmovapd %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = fadd <8 x double> %a0, %a1
|
|
%3 = bitcast i8 %mask to <8 x i1>
|
|
%4 = load <8 x double>, <8 x double>* %passthru
|
|
%5 = select <8 x i1> %3, <8 x double> %2, <8 x double> %4
|
|
ret <8 x double> %5
|
|
}
|
|
|
|
define <8 x double> @stack_fold_addpd_zmm_k_commuted(<8 x double> %a0, <8 x double> %a1, i8 %mask, <8 x double>* %passthru) {
|
|
; CHECK-LABEL: stack_fold_addpd_zmm_k_commuted:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovapd (%rsi), %zmm2
|
|
; CHECK-NEXT: vaddpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm2 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: vmovapd %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = fadd <8 x double> %a1, %a0
|
|
%3 = bitcast i8 %mask to <8 x i1>
|
|
%4 = load <8 x double>, <8 x double>* %passthru
|
|
%5 = select <8 x i1> %3, <8 x double> %2, <8 x double> %4
|
|
ret <8 x double> %5
|
|
}
|
|
|
|
define <8 x double> @stack_fold_addpd_zmm_kz(<8 x double> %a0, <8 x double> %a1, i8 %mask) {
|
|
; CHECK-LABEL: stack_fold_addpd_zmm_kz:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vaddpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 {%k1} {z} # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = fadd <8 x double> %a1, %a0
|
|
%3 = bitcast i8 %mask to <8 x i1>
|
|
%4 = select <8 x i1> %3, <8 x double> %2, <8 x double> zeroinitializer
|
|
ret <8 x double> %4
|
|
}
|
|
|
|
define <16 x float> @stack_fold_addps_zmm(<16 x float> %a0, <16 x float> %a1) {
|
|
; CHECK-LABEL: stack_fold_addps_zmm:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vaddps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = fadd <16 x float> %a0, %a1
|
|
ret <16 x float> %2
|
|
}
|
|
|
|
define <16 x float> @stack_fold_addps_zmm_k(<16 x float> %a0, <16 x float> %a1, i16 %mask, <16 x float>* %passthru) {
|
|
; CHECK-LABEL: stack_fold_addps_zmm_k:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovaps (%rsi), %zmm2
|
|
; CHECK-NEXT: vaddps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm2 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = fadd <16 x float> %a0, %a1
|
|
%3 = bitcast i16 %mask to <16 x i1>
|
|
%4 = load <16 x float>, <16 x float>* %passthru
|
|
%5 = select <16 x i1> %3, <16 x float> %2, <16 x float> %4
|
|
ret <16 x float> %5
|
|
}
|
|
|
|
define <16 x float> @stack_fold_addps_zmm_k_commuted(<16 x float> %a0, <16 x float> %a1, i16 %mask, <16 x float>* %passthru) {
|
|
; CHECK-LABEL: stack_fold_addps_zmm_k_commuted:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovaps (%rsi), %zmm2
|
|
; CHECK-NEXT: vaddps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm2 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = fadd <16 x float> %a1, %a0
|
|
%3 = bitcast i16 %mask to <16 x i1>
|
|
%4 = load <16 x float>, <16 x float>* %passthru
|
|
%5 = select <16 x i1> %3, <16 x float> %2, <16 x float> %4
|
|
ret <16 x float> %5
|
|
}
|
|
|
|
define <16 x float> @stack_fold_addps_zmm_kz(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: stack_fold_addps_zmm_kz:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vaddps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 {%k1} {z} # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = fadd <16 x float> %a1, %a0
|
|
%3 = bitcast i16 %mask to <16 x i1>
|
|
%4 = select <16 x i1> %3, <16 x float> %2, <16 x float> zeroinitializer
|
|
ret <16 x float> %4
|
|
}
|
|
|
|
define double @stack_fold_addsd(double %a0, double %a1) {
|
|
; CHECK-LABEL: stack_fold_addsd:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovsd %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vaddsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 8-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = fadd double %a0, %a1
|
|
ret double %2
|
|
}
|
|
|
|
define <2 x double> @stack_fold_addsd_int(<2 x double> %a0, <2 x double> %a1) {
|
|
; CHECK-LABEL: stack_fold_addsd_int:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vaddsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = extractelement <2 x double> %a0, i32 0
|
|
%3 = extractelement <2 x double> %a1, i32 0
|
|
%4 = fadd double %2, %3
|
|
%5 = insertelement <2 x double> %a0, double %4, i32 0
|
|
ret <2 x double> %5
|
|
}
|
|
|
|
define float @stack_fold_addss(float %a0, float %a1) {
|
|
; CHECK-LABEL: stack_fold_addss:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovss %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vaddss {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 4-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = fadd float %a0, %a1
|
|
ret float %2
|
|
}
|
|
|
|
define <4 x float> @stack_fold_addss_int(<4 x float> %a0, <4 x float> %a1) {
|
|
; CHECK-LABEL: stack_fold_addss_int:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vaddss {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = extractelement <4 x float> %a0, i32 0
|
|
%3 = extractelement <4 x float> %a1, i32 0
|
|
%4 = fadd float %2, %3
|
|
%5 = insertelement <4 x float> %a0, float %4, i32 0
|
|
ret <4 x float> %5
|
|
}
|
|
|
|
define <8 x double> @stack_fold_andnpd_zmm(<8 x double> %a0, <8 x double> %a1) {
|
|
; CHECK-LABEL: stack_fold_andnpd_zmm:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vandnpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: vxorpd %xmm1, %xmm1, %xmm1
|
|
; CHECK-NEXT: vaddpd %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = bitcast <8 x double> %a0 to <8 x i64>
|
|
%3 = bitcast <8 x double> %a1 to <8 x i64>
|
|
%4 = xor <8 x i64> %2, <i64 -1, i64 -1, i64 -1, i64 -1, i64 -1, i64 -1, i64 -1, i64 -1>
|
|
%5 = and <8 x i64> %4, %3
|
|
%6 = bitcast <8 x i64> %5 to <8 x double>
|
|
; fadd forces execution domain
|
|
%7 = fadd <8 x double> %6, <double 0x0, double 0x0, double 0x0, double 0x0, double 0x0, double 0x0, double 0x0, double 0x0>
|
|
ret <8 x double> %7
|
|
}
|
|
|
|
define <16 x float> @stack_fold_andnps_zmm(<16 x float> %a0, <16 x float> %a1) {
|
|
; CHECK-LABEL: stack_fold_andnps_zmm:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vandnps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
|
; CHECK-NEXT: vaddps %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = bitcast <16 x float> %a0 to <16 x i32>
|
|
%3 = bitcast <16 x float> %a1 to <16 x i32>
|
|
%4 = xor <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>
|
|
%5 = and <16 x i32> %4, %3
|
|
%6 = bitcast <16 x i32> %5 to <16 x float>
|
|
; fadd forces execution domain
|
|
%7 = fadd <16 x float> %6, <float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0>
|
|
ret <16 x float> %7
|
|
}
|
|
|
|
define <8 x double> @stack_fold_andpd_zmm(<8 x double> %a0, <8 x double> %a1) {
|
|
; CHECK-LABEL: stack_fold_andpd_zmm:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vandpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: vxorpd %xmm1, %xmm1, %xmm1
|
|
; CHECK-NEXT: vaddpd %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = bitcast <8 x double> %a0 to <8 x i64>
|
|
%3 = bitcast <8 x double> %a1 to <8 x i64>
|
|
%4 = and <8 x i64> %2, %3
|
|
%5 = bitcast <8 x i64> %4 to <8 x double>
|
|
; fadd forces execution domain
|
|
%6 = fadd <8 x double> %5, <double 0x0, double 0x0, double 0x0, double 0x0, double 0x0, double 0x0, double 0x0, double 0x0>
|
|
ret <8 x double> %6
|
|
}
|
|
|
|
define <16 x float> @stack_fold_andps_zmm(<16 x float> %a0, <16 x float> %a1) {
|
|
; CHECK-LABEL: stack_fold_andps_zmm:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vandps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
|
; CHECK-NEXT: vaddps %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = bitcast <16 x float> %a0 to <16 x i32>
|
|
%3 = bitcast <16 x float> %a1 to <16 x i32>
|
|
%4 = and <16 x i32> %2, %3
|
|
%5 = bitcast <16 x i32> %4 to <16 x float>
|
|
; fadd forces execution domain
|
|
%6 = fadd <16 x float> %5, <float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0>
|
|
ret <16 x float> %6
|
|
}
|
|
|
|
define i8 @stack_fold_cmppd(<8 x double> %a0, <8 x double> %a1) {
|
|
; CHECK-LABEL: stack_fold_cmppd:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vcmpeqpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %k0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: # kill: def $al killed $al killed $eax
|
|
; CHECK-NEXT: vzeroupper
|
|
; CHECK-NEXT: retq
|
|
%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}"()
|
|
%res = call <8 x i1> @llvm.x86.avx512.cmp.pd.512(<8 x double> %a0, <8 x double> %a1, i32 0, i32 4)
|
|
%2 = bitcast <8 x i1> %res to i8
|
|
ret i8 %2
|
|
}
|
|
declare <8 x i1> @llvm.x86.avx512.cmp.pd.512(<8 x double>, <8 x double>, i32, i32)
|
|
|
|
define <8 x double> @stack_fold_cmppd_mask(<8 x double> %a0, <8 x double> %a1, <8 x double>* %a2, i8 %mask, <8 x double> %b0, <8 x double> %b1) {
|
|
; CHECK-LABEL: stack_fold_cmppd_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: subq $184, %rsp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 192
|
|
; CHECK-NEXT: vmovups %zmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: vmovups %zmm2, (%rsp) # 64-byte Spill
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
|
|
; CHECK-NEXT: vaddpd (%rdi), %zmm0, %zmm0
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vcmpeqpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %k1 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
|
|
; CHECK-NEXT: vblendmpd (%rsp), %zmm0, %zmm0 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: addq $184, %rsp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
|
; CHECK-NEXT: retq
|
|
%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}"()
|
|
; load and fadd are here to keep the operations below the side effecting block and to avoid folding the wrong load
|
|
%2 = load <8 x double>, <8 x double>* %a2
|
|
%3 = fadd <8 x double> %a1, %2
|
|
%4 = bitcast i8 %mask to <8 x i1>
|
|
%5 = call <8 x i1> @llvm.x86.avx512.cmp.pd.512(<8 x double> %3, <8 x double> %a0, i32 0, i32 4)
|
|
%6 = and <8 x i1> %4, %5
|
|
%7 = select <8 x i1> %6, <8 x double> %b0, <8 x double> %b1
|
|
ret <8 x double> %7
|
|
}
|
|
|
|
define <8 x double> @stack_fold_cmppd_mask_commuted(<8 x double> %a0, <8 x double> %a1, <8 x double>* %a2, i8 %mask, <8 x double> %b0, <8 x double> %b1) {
|
|
; CHECK-LABEL: stack_fold_cmppd_mask_commuted:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: subq $184, %rsp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 192
|
|
; CHECK-NEXT: vmovups %zmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: vmovups %zmm2, (%rsp) # 64-byte Spill
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
|
|
; CHECK-NEXT: vaddpd (%rdi), %zmm0, %zmm0
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vcmpeqpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %k1 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
|
|
; CHECK-NEXT: vblendmpd (%rsp), %zmm0, %zmm0 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: addq $184, %rsp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
|
; CHECK-NEXT: retq
|
|
%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}"()
|
|
; load and fadd are here to keep the operations below the side effecting block and to avoid folding the wrong load
|
|
%2 = load <8 x double>, <8 x double>* %a2
|
|
%3 = fadd <8 x double> %a1, %2
|
|
%4 = bitcast i8 %mask to <8 x i1>
|
|
%5 = call <8 x i1> @llvm.x86.avx512.cmp.pd.512(<8 x double> %a0, <8 x double> %3, i32 0, i32 4)
|
|
%6 = and <8 x i1> %4, %5
|
|
%7 = select <8 x i1> %6, <8 x double> %b0, <8 x double> %b1
|
|
ret <8 x double> %7
|
|
}
|
|
|
|
define i16 @stack_fold_cmpps(<16 x float> %a0, <16 x float> %a1) {
|
|
; CHECK-LABEL: stack_fold_cmpps:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vcmpeqps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %k0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: kmovw %k0, %eax
|
|
; CHECK-NEXT: # kill: def $ax killed $ax killed $eax
|
|
; CHECK-NEXT: vzeroupper
|
|
; CHECK-NEXT: retq
|
|
%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}"()
|
|
%res = call <16 x i1> @llvm.x86.avx512.cmp.ps.512(<16 x float> %a0, <16 x float> %a1, i32 0, i32 4)
|
|
%2 = bitcast <16 x i1> %res to i16
|
|
ret i16 %2
|
|
}
|
|
declare <16 x i1> @llvm.x86.avx512.cmp.ps.512(<16 x float>, <16 x float>, i32, i32)
|
|
|
|
define <16 x float> @stack_fold_cmpps_mask(<16 x float> %a0, <16 x float> %a1, <16 x float>* %a2, i16 %mask, <16 x float> %b0, <16 x float> %b1) {
|
|
; CHECK-LABEL: stack_fold_cmpps_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: subq $184, %rsp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 192
|
|
; CHECK-NEXT: vmovups %zmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: vmovups %zmm2, (%rsp) # 64-byte Spill
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
|
|
; CHECK-NEXT: vaddps (%rdi), %zmm0, %zmm0
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vcmpeqps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %k1 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
|
|
; CHECK-NEXT: vblendmps (%rsp), %zmm0, %zmm0 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: addq $184, %rsp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
|
; CHECK-NEXT: retq
|
|
%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}"()
|
|
; load and fadd are here to keep the operations below the side effecting block and to avoid folding the wrong load
|
|
%2 = load <16 x float>, <16 x float>* %a2
|
|
%3 = fadd <16 x float> %a1, %2
|
|
%4 = bitcast i16 %mask to <16 x i1>
|
|
%5 = call <16 x i1> @llvm.x86.avx512.cmp.ps.512(<16 x float> %3, <16 x float> %a0, i32 0, i32 4)
|
|
%6 = and <16 x i1> %4, %5
|
|
%7 = select <16 x i1> %6, <16 x float> %b0, <16 x float> %b1
|
|
ret <16 x float> %7
|
|
}
|
|
|
|
define <16 x float> @stack_fold_cmpps_mask_commuted(<16 x float> %a0, <16 x float> %a1, <16 x float>* %a2, i16 %mask, <16 x float> %b0, <16 x float> %b1) {
|
|
; CHECK-LABEL: stack_fold_cmpps_mask_commuted:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: subq $184, %rsp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 192
|
|
; CHECK-NEXT: vmovups %zmm3, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: vmovups %zmm2, (%rsp) # 64-byte Spill
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
|
|
; CHECK-NEXT: vaddps (%rdi), %zmm0, %zmm0
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vcmpeqps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %k1 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
|
|
; CHECK-NEXT: vblendmps (%rsp), %zmm0, %zmm0 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: addq $184, %rsp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
|
; CHECK-NEXT: retq
|
|
%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}"()
|
|
; load and fadd are here to keep the operations below the side effecting block and to avoid folding the wrong load
|
|
%2 = load <16 x float>, <16 x float>* %a2
|
|
%3 = fadd <16 x float> %a1, %2
|
|
%4 = bitcast i16 %mask to <16 x i1>
|
|
%5 = call <16 x i1> @llvm.x86.avx512.cmp.ps.512(<16 x float> %a0, <16 x float> %3, i32 0, i32 4)
|
|
%6 = and <16 x i1> %4, %5
|
|
%7 = select <16 x i1> %6, <16 x float> %b0, <16 x float> %b1
|
|
ret <16 x float> %7
|
|
}
|
|
|
|
define <2 x double> @stack_fold_divsd_int(<2 x double> %a0, <2 x double> %a1) {
|
|
; CHECK-LABEL: stack_fold_divsd_int:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vdivsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = extractelement <2 x double> %a0, i32 0
|
|
%3 = extractelement <2 x double> %a1, i32 0
|
|
%4 = fdiv double %2, %3
|
|
%5 = insertelement <2 x double> %a0, double %4, i32 0
|
|
ret <2 x double> %5
|
|
}
|
|
|
|
define float @stack_fold_divss(float %a0, float %a1) {
|
|
; CHECK-LABEL: stack_fold_divss:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovss %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vdivss {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 4-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = fdiv float %a0, %a1
|
|
ret float %2
|
|
}
|
|
|
|
define <4 x float> @stack_fold_divss_int(<4 x float> %a0, <4 x float> %a1) {
|
|
; CHECK-LABEL: stack_fold_divss_int:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vdivss {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = extractelement <4 x float> %a0, i32 0
|
|
%3 = extractelement <4 x float> %a1, i32 0
|
|
%4 = fdiv float %2, %3
|
|
%5 = insertelement <4 x float> %a0, float %4, i32 0
|
|
ret <4 x float> %5
|
|
}
|
|
|
|
define <8 x double> @stack_fold_cvtdq2pd(<8 x i32> %a0) {
|
|
; CHECK-LABEL: stack_fold_cvtdq2pd:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vcvtdq2pd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 32-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = sitofp <8 x i32> %a0 to <8 x double>
|
|
ret <8 x double> %2
|
|
}
|
|
|
|
define <8 x double> @stack_fold_cvtudq2pd(<8 x i32> %a0) {
|
|
; CHECK-LABEL: stack_fold_cvtudq2pd:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vcvtudq2pd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 32-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = uitofp <8 x i32> %a0 to <8 x double>
|
|
ret <8 x double> %2
|
|
}
|
|
|
|
define <8 x float> @stack_fold_cvtpd2ps(<8 x double> %a0) {
|
|
; CHECK-LABEL: stack_fold_cvtpd2ps:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vcvtpd2ps {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = fptrunc <8 x double> %a0 to <8 x float>
|
|
ret <8 x float> %2
|
|
}
|
|
|
|
define <16 x float> @stack_fold_cvtph2ps(<16 x i16> %a0) {
|
|
; CHECK-LABEL: stack_fold_cvtph2ps:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vcvtph2ps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 32-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = call <16 x float> @llvm.x86.avx512.mask.vcvtph2ps.512(<16 x i16> %a0, <16 x float> undef, i16 -1, i32 4)
|
|
ret <16 x float> %2
|
|
}
|
|
declare <16 x float> @llvm.x86.avx512.mask.vcvtph2ps.512(<16 x i16>, <16 x float>, i16, i32) nounwind readonly
|
|
|
|
define <16 x i16> @stack_fold_cvtps2ph(<16 x float> %a0) {
|
|
; CHECK-LABEL: stack_fold_cvtps2ph:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vcvtps2ph $0, %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Folded Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
|
; CHECK-NEXT: retq
|
|
%1 = call <16 x i16> @llvm.x86.avx512.mask.vcvtps2ph.512(<16 x float> %a0, i32 0, <16 x i16> undef, i16 -1)
|
|
%2 = 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}"()
|
|
ret <16 x i16> %1
|
|
}
|
|
declare <16 x i16> @llvm.x86.avx512.mask.vcvtps2ph.512(<16 x float>, i32, <16 x i16>, i16) nounwind readonly
|
|
|
|
define <4 x float> @stack_fold_insertps(<4 x float> %a0, <4 x float> %a1) {
|
|
; CHECK-LABEL: stack_fold_insertps:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vinsertps $17, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
|
|
; CHECK-NEXT: # xmm0 = zero,mem[0],xmm0[2,3]
|
|
; CHECK-NEXT: retq
|
|
%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 = call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a0, <4 x float> %a1, i8 209)
|
|
ret <4 x float> %2
|
|
}
|
|
declare <4 x float> @llvm.x86.sse41.insertps(<4 x float>, <4 x float>, i8) nounwind readnone
|
|
|
|
define <8 x double> @stack_fold_maxpd_zmm(<8 x double> %a0, <8 x double> %a1) #0 {
|
|
; CHECK-LABEL: stack_fold_maxpd_zmm:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vmaxpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = call <8 x double> @llvm.x86.avx512.max.pd.512(<8 x double> %a0, <8 x double> %a1, i32 4)
|
|
ret <8 x double> %2
|
|
}
|
|
declare <8 x double> @llvm.x86.avx512.max.pd.512(<8 x double>, <8 x double>, i32) nounwind readnone
|
|
|
|
define <8 x double> @stack_fold_maxpd_zmm_commutable(<8 x double> %a0, <8 x double> %a1) #1 {
|
|
; CHECK-LABEL: stack_fold_maxpd_zmm_commutable:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vmaxpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = call <8 x double> @llvm.x86.avx512.max.pd.512(<8 x double> %a0, <8 x double> %a1, i32 4)
|
|
ret <8 x double> %2
|
|
}
|
|
|
|
define <8 x double> @stack_fold_maxpd_zmm_commutable_k(<8 x double> %a0, <8 x double> %a1, i8 %mask, <8 x double>* %passthru) #1 {
|
|
; CHECK-LABEL: stack_fold_maxpd_zmm_commutable_k:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovapd (%rsi), %zmm2
|
|
; CHECK-NEXT: vmaxpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm2 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: vmovapd %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = call <8 x double> @llvm.x86.avx512.max.pd.512(<8 x double> %a0, <8 x double> %a1, i32 4)
|
|
%3 = bitcast i8 %mask to <8 x i1>
|
|
%4 = load <8 x double>, <8 x double>* %passthru
|
|
%5 = select <8 x i1> %3, <8 x double> %2, <8 x double> %4
|
|
ret <8 x double> %5
|
|
}
|
|
|
|
define <8 x double> @stack_fold_maxpd_zmm_commutable_k_commuted(<8 x double> %a0, <8 x double> %a1, i8 %mask, <8 x double>* %passthru) #1 {
|
|
; CHECK-LABEL: stack_fold_maxpd_zmm_commutable_k_commuted:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovapd (%rsi), %zmm2
|
|
; CHECK-NEXT: vmaxpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm2 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: vmovapd %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = call <8 x double> @llvm.x86.avx512.max.pd.512(<8 x double> %a1, <8 x double> %a0, i32 4)
|
|
%3 = bitcast i8 %mask to <8 x i1>
|
|
%4 = load <8 x double>, <8 x double>* %passthru
|
|
%5 = select <8 x i1> %3, <8 x double> %2, <8 x double> %4
|
|
ret <8 x double> %5
|
|
}
|
|
|
|
define <8 x double> @stack_fold_maxpd_zmm_commutable_kz(<8 x double> %a0, <8 x double> %a1, i8 %mask) #1 {
|
|
; CHECK-LABEL: stack_fold_maxpd_zmm_commutable_kz:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmaxpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 {%k1} {z} # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = call <8 x double> @llvm.x86.avx512.max.pd.512(<8 x double> %a1, <8 x double> %a0, i32 4)
|
|
%3 = bitcast i8 %mask to <8 x i1>
|
|
%4 = select <8 x i1> %3, <8 x double> %2, <8 x double> zeroinitializer
|
|
ret <8 x double> %4
|
|
}
|
|
|
|
define <16 x float> @stack_fold_maxps_zmm(<16 x float> %a0, <16 x float> %a1) #0 {
|
|
; CHECK-LABEL: stack_fold_maxps_zmm:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vmaxps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = call <16 x float> @llvm.x86.avx512.max.ps.512(<16 x float> %a0, <16 x float> %a1, i32 4)
|
|
ret <16 x float> %2
|
|
}
|
|
declare <16 x float> @llvm.x86.avx512.max.ps.512(<16 x float>, <16 x float>, i32) nounwind readnone
|
|
|
|
define <16 x float> @stack_fold_maxps_zmm_commutable(<16 x float> %a0, <16 x float> %a1) #1 {
|
|
; CHECK-LABEL: stack_fold_maxps_zmm_commutable:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vmaxps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = call <16 x float> @llvm.x86.avx512.max.ps.512(<16 x float> %a0, <16 x float> %a1, i32 4)
|
|
ret <16 x float> %2
|
|
}
|
|
|
|
define <16 x float> @stack_fold_maxps_zmm_commutable_k(<16 x float> %a0, <16 x float> %a1, i16 %mask, <16 x float>* %passthru) #1 {
|
|
; CHECK-LABEL: stack_fold_maxps_zmm_commutable_k:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovaps (%rsi), %zmm2
|
|
; CHECK-NEXT: vmaxps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm2 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = call <16 x float> @llvm.x86.avx512.max.ps.512(<16 x float> %a0, <16 x float> %a1, i32 4)
|
|
%3 = bitcast i16 %mask to <16 x i1>
|
|
%4 = load <16 x float>, <16 x float>* %passthru
|
|
%5 = select <16 x i1> %3, <16 x float> %2, <16 x float> %4
|
|
ret <16 x float> %5
|
|
}
|
|
|
|
define <16 x float> @stack_fold_maxps_zmm_commutable_k_commuted(<16 x float> %a0, <16 x float> %a1, i16 %mask, <16 x float>* %passthru) #1 {
|
|
; CHECK-LABEL: stack_fold_maxps_zmm_commutable_k_commuted:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovaps (%rsi), %zmm2
|
|
; CHECK-NEXT: vmaxps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm2 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = call <16 x float> @llvm.x86.avx512.max.ps.512(<16 x float> %a1, <16 x float> %a0, i32 4)
|
|
%3 = bitcast i16 %mask to <16 x i1>
|
|
%4 = load <16 x float>, <16 x float>* %passthru
|
|
%5 = select <16 x i1> %3, <16 x float> %2, <16 x float> %4
|
|
ret <16 x float> %5
|
|
}
|
|
|
|
define <16 x float> @stack_fold_maxps_zmm_commutable_kz(<16 x float> %a0, <16 x float> %a1, i16 %mask) #1 {
|
|
; CHECK-LABEL: stack_fold_maxps_zmm_commutable_kz:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmaxps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 {%k1} {z} # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = call <16 x float> @llvm.x86.avx512.max.ps.512(<16 x float> %a1, <16 x float> %a0, i32 4)
|
|
%3 = bitcast i16 %mask to <16 x i1>
|
|
%4 = select <16 x i1> %3, <16 x float> %2, <16 x float> zeroinitializer
|
|
ret <16 x float> %4
|
|
}
|
|
|
|
define <8 x double> @stack_fold_minpd_zmm(<8 x double> %a0, <8 x double> %a1) #0 {
|
|
; CHECK-LABEL: stack_fold_minpd_zmm:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vminpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = call <8 x double> @llvm.x86.avx512.min.pd.512(<8 x double> %a0, <8 x double> %a1, i32 4)
|
|
ret <8 x double> %2
|
|
}
|
|
declare <8 x double> @llvm.x86.avx512.min.pd.512(<8 x double>, <8 x double>, i32) nounwind readnone
|
|
|
|
define <8 x double> @stack_fold_minpd_zmm_commutable(<8 x double> %a0, <8 x double> %a1) #1 {
|
|
; CHECK-LABEL: stack_fold_minpd_zmm_commutable:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vminpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = call <8 x double> @llvm.x86.avx512.min.pd.512(<8 x double> %a0, <8 x double> %a1, i32 4)
|
|
ret <8 x double> %2
|
|
}
|
|
|
|
define <8 x double> @stack_fold_minpd_zmm_commutable_k(<8 x double> %a0, <8 x double> %a1, i8 %mask, <8 x double>* %passthru) #1 {
|
|
; CHECK-LABEL: stack_fold_minpd_zmm_commutable_k:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovapd (%rsi), %zmm2
|
|
; CHECK-NEXT: vminpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm2 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: vmovapd %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = call <8 x double> @llvm.x86.avx512.min.pd.512(<8 x double> %a0, <8 x double> %a1, i32 4)
|
|
%3 = bitcast i8 %mask to <8 x i1>
|
|
%4 = load <8 x double>, <8 x double>* %passthru
|
|
%5 = select <8 x i1> %3, <8 x double> %2, <8 x double> %4
|
|
ret <8 x double> %5
|
|
}
|
|
|
|
define <8 x double> @stack_fold_minpd_zmm_commutable_k_commuted(<8 x double> %a0, <8 x double> %a1, i8 %mask, <8 x double>* %passthru) #1 {
|
|
; CHECK-LABEL: stack_fold_minpd_zmm_commutable_k_commuted:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovapd (%rsi), %zmm2
|
|
; CHECK-NEXT: vminpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm2 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: vmovapd %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = call <8 x double> @llvm.x86.avx512.min.pd.512(<8 x double> %a1, <8 x double> %a0, i32 4)
|
|
%3 = bitcast i8 %mask to <8 x i1>
|
|
%4 = load <8 x double>, <8 x double>* %passthru
|
|
%5 = select <8 x i1> %3, <8 x double> %2, <8 x double> %4
|
|
ret <8 x double> %5
|
|
}
|
|
|
|
define <8 x double> @stack_fold_minpd_zmm_commutable_kz(<8 x double> %a0, <8 x double> %a1, i8 %mask) #1 {
|
|
; CHECK-LABEL: stack_fold_minpd_zmm_commutable_kz:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vminpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 {%k1} {z} # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = call <8 x double> @llvm.x86.avx512.min.pd.512(<8 x double> %a1, <8 x double> %a0, i32 4)
|
|
%3 = bitcast i8 %mask to <8 x i1>
|
|
%4 = select <8 x i1> %3, <8 x double> %2, <8 x double> zeroinitializer
|
|
ret <8 x double> %4
|
|
}
|
|
|
|
define <16 x float> @stack_fold_minps_zmm(<16 x float> %a0, <16 x float> %a1) #0 {
|
|
; CHECK-LABEL: stack_fold_minps_zmm:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vminps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = call <16 x float> @llvm.x86.avx512.min.ps.512(<16 x float> %a0, <16 x float> %a1, i32 4)
|
|
ret <16 x float> %2
|
|
}
|
|
declare <16 x float> @llvm.x86.avx512.min.ps.512(<16 x float>, <16 x float>, i32) nounwind readnone
|
|
|
|
define <16 x float> @stack_fold_minps_zmm_commutable(<16 x float> %a0, <16 x float> %a1) #1 {
|
|
; CHECK-LABEL: stack_fold_minps_zmm_commutable:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vminps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = call <16 x float> @llvm.x86.avx512.min.ps.512(<16 x float> %a0, <16 x float> %a1, i32 4)
|
|
ret <16 x float> %2
|
|
}
|
|
|
|
define <16 x float> @stack_fold_minps_zmm_commutable_k(<16 x float> %a0, <16 x float> %a1, i16 %mask, <16 x float>* %passthru) #1 {
|
|
; CHECK-LABEL: stack_fold_minps_zmm_commutable_k:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovaps (%rsi), %zmm2
|
|
; CHECK-NEXT: vminps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm2 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = call <16 x float> @llvm.x86.avx512.min.ps.512(<16 x float> %a0, <16 x float> %a1, i32 4)
|
|
%3 = bitcast i16 %mask to <16 x i1>
|
|
%4 = load <16 x float>, <16 x float>* %passthru
|
|
%5 = select <16 x i1> %3, <16 x float> %2, <16 x float> %4
|
|
ret <16 x float> %5
|
|
}
|
|
|
|
define <16 x float> @stack_fold_minps_zmm_commutable_k_commuted(<16 x float> %a0, <16 x float> %a1, i16 %mask, <16 x float>* %passthru) #1 {
|
|
; CHECK-LABEL: stack_fold_minps_zmm_commutable_k_commuted:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovaps (%rsi), %zmm2
|
|
; CHECK-NEXT: vminps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm2 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = call <16 x float> @llvm.x86.avx512.min.ps.512(<16 x float> %a1, <16 x float> %a0, i32 4)
|
|
%3 = bitcast i16 %mask to <16 x i1>
|
|
%4 = load <16 x float>, <16 x float>* %passthru
|
|
%5 = select <16 x i1> %3, <16 x float> %2, <16 x float> %4
|
|
ret <16 x float> %5
|
|
}
|
|
|
|
define <16 x float> @stack_fold_minps_zmm_commutable_kz(<16 x float> %a0, <16 x float> %a1, i16 %mask) #1 {
|
|
; CHECK-LABEL: stack_fold_minps_zmm_commutable_kz:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vminps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 {%k1} {z} # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = call <16 x float> @llvm.x86.avx512.min.ps.512(<16 x float> %a1, <16 x float> %a0, i32 4)
|
|
%3 = bitcast i16 %mask to <16 x i1>
|
|
%4 = select <16 x i1> %3, <16 x float> %2, <16 x float> zeroinitializer
|
|
ret <16 x float> %4
|
|
}
|
|
|
|
define <8 x double> @stack_fold_mulpd_zmm(<8 x double> %a0, <8 x double> %a1) {
|
|
; CHECK-LABEL: stack_fold_mulpd_zmm:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vmulpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = fmul <8 x double> %a0, %a1
|
|
ret <8 x double> %2
|
|
}
|
|
|
|
define <8 x double> @stack_fold_mulpd_zmm_k(<8 x double> %a0, <8 x double> %a1, i8 %mask, <8 x double>* %passthru) {
|
|
; CHECK-LABEL: stack_fold_mulpd_zmm_k:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovapd (%rsi), %zmm2
|
|
; CHECK-NEXT: vmulpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm2 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: vmovapd %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = fmul <8 x double> %a0, %a1
|
|
%3 = bitcast i8 %mask to <8 x i1>
|
|
%4 = load <8 x double>, <8 x double>* %passthru
|
|
%5 = select <8 x i1> %3, <8 x double> %2, <8 x double> %4
|
|
ret <8 x double> %5
|
|
}
|
|
|
|
define <8 x double> @stack_fold_mulpd_zmm_k_commuted(<8 x double> %a0, <8 x double> %a1, i8 %mask, <8 x double>* %passthru) {
|
|
; CHECK-LABEL: stack_fold_mulpd_zmm_k_commuted:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovapd (%rsi), %zmm2
|
|
; CHECK-NEXT: vmulpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm2 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: vmovapd %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = fmul <8 x double> %a1, %a0
|
|
%3 = bitcast i8 %mask to <8 x i1>
|
|
%4 = load <8 x double>, <8 x double>* %passthru
|
|
%5 = select <8 x i1> %3, <8 x double> %2, <8 x double> %4
|
|
ret <8 x double> %5
|
|
}
|
|
|
|
define <8 x double> @stack_fold_mulpd_zmm_kz(<8 x double> %a0, <8 x double> %a1, i8 %mask) {
|
|
; CHECK-LABEL: stack_fold_mulpd_zmm_kz:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmulpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 {%k1} {z} # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = fmul <8 x double> %a1, %a0
|
|
%3 = bitcast i8 %mask to <8 x i1>
|
|
%4 = select <8 x i1> %3, <8 x double> %2, <8 x double> zeroinitializer
|
|
ret <8 x double> %4
|
|
}
|
|
|
|
define <16 x float> @stack_fold_mulps_zmm(<16 x float> %a0, <16 x float> %a1) {
|
|
; CHECK-LABEL: stack_fold_mulps_zmm:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vmulps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = fmul <16 x float> %a0, %a1
|
|
ret <16 x float> %2
|
|
}
|
|
|
|
define <16 x float> @stack_fold_mulps_zmm_k(<16 x float> %a0, <16 x float> %a1, i16 %mask, <16 x float>* %passthru) {
|
|
; CHECK-LABEL: stack_fold_mulps_zmm_k:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovaps (%rsi), %zmm2
|
|
; CHECK-NEXT: vmulps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm2 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = fmul <16 x float> %a0, %a1
|
|
%3 = bitcast i16 %mask to <16 x i1>
|
|
%4 = load <16 x float>, <16 x float>* %passthru
|
|
%5 = select <16 x i1> %3, <16 x float> %2, <16 x float> %4
|
|
ret <16 x float> %5
|
|
}
|
|
|
|
define <16 x float> @stack_fold_mulps_zmm_k_commuted(<16 x float> %a0, <16 x float> %a1, i16 %mask, <16 x float>* %passthru) {
|
|
; CHECK-LABEL: stack_fold_mulps_zmm_k_commuted:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovaps (%rsi), %zmm2
|
|
; CHECK-NEXT: vmulps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm2 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = fmul <16 x float> %a1, %a0
|
|
%3 = bitcast i16 %mask to <16 x i1>
|
|
%4 = load <16 x float>, <16 x float>* %passthru
|
|
%5 = select <16 x i1> %3, <16 x float> %2, <16 x float> %4
|
|
ret <16 x float> %5
|
|
}
|
|
|
|
define <16 x float> @stack_fold_mulps_zmm_kz(<16 x float> %a0, <16 x float> %a1, i16 %mask) {
|
|
; CHECK-LABEL: stack_fold_mulps_zmm_kz:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmulps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 {%k1} {z} # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = fmul <16 x float> %a1, %a0
|
|
%3 = bitcast i16 %mask to <16 x i1>
|
|
%4 = select <16 x i1> %3, <16 x float> %2, <16 x float> zeroinitializer
|
|
ret <16 x float> %4
|
|
}
|
|
|
|
define double @stack_fold_mulsd(double %a0, double %a1) {
|
|
; CHECK-LABEL: stack_fold_mulsd:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovsd %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vmulsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 8-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = fmul double %a0, %a1
|
|
ret double %2
|
|
}
|
|
|
|
define <2 x double> @stack_fold_mulsd_int(<2 x double> %a0, <2 x double> %a1) {
|
|
; CHECK-LABEL: stack_fold_mulsd_int:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vmulsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = extractelement <2 x double> %a0, i32 0
|
|
%3 = extractelement <2 x double> %a1, i32 0
|
|
%4 = fmul double %2, %3
|
|
%5 = insertelement <2 x double> %a0, double %4, i32 0
|
|
ret <2 x double> %5
|
|
}
|
|
|
|
define float @stack_fold_mulss(float %a0, float %a1) {
|
|
; CHECK-LABEL: stack_fold_mulss:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovss %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vmulss {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 4-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = fmul float %a0, %a1
|
|
ret float %2
|
|
}
|
|
|
|
define <4 x float> @stack_fold_mulss_int(<4 x float> %a0, <4 x float> %a1) {
|
|
; CHECK-LABEL: stack_fold_mulss_int:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vmulss {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = extractelement <4 x float> %a0, i32 0
|
|
%3 = extractelement <4 x float> %a1, i32 0
|
|
%4 = fmul float %2, %3
|
|
%5 = insertelement <4 x float> %a0, float %4, i32 0
|
|
ret <4 x float> %5
|
|
}
|
|
|
|
define <8 x double> @stack_fold_orpd_zmm(<8 x double> %a0, <8 x double> %a1) #0 {
|
|
; CHECK-LABEL: stack_fold_orpd_zmm:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vorpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: vxorpd %xmm1, %xmm1, %xmm1
|
|
; CHECK-NEXT: vaddpd %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = bitcast <8 x double> %a0 to <8 x i64>
|
|
%3 = bitcast <8 x double> %a1 to <8 x i64>
|
|
%4 = or <8 x i64> %2, %3
|
|
%5 = bitcast <8 x i64> %4 to <8 x double>
|
|
; fadd forces execution domain
|
|
%6 = fadd <8 x double> %5, <double 0x0, double 0x0, double 0x0, double 0x0, double 0x0, double 0x0, double 0x0, double 0x0>
|
|
ret <8 x double> %6
|
|
}
|
|
|
|
define <16 x float> @stack_fold_orps_zmm(<16 x float> %a0, <16 x float> %a1) #0 {
|
|
; CHECK-LABEL: stack_fold_orps_zmm:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vorps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
|
; CHECK-NEXT: vaddps %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = bitcast <16 x float> %a0 to <16 x i32>
|
|
%3 = bitcast <16 x float> %a1 to <16 x i32>
|
|
%4 = or <16 x i32> %2, %3
|
|
%5 = bitcast <16 x i32> %4 to <16 x float>
|
|
; fadd forces execution domain
|
|
%6 = fadd <16 x float> %5, <float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0>
|
|
ret <16 x float> %6
|
|
}
|
|
|
|
define <8 x double> @stack_fold_shuff64x2(<8 x double> %a, <8 x double> %b) {
|
|
; CHECK-LABEL: stack_fold_shuff64x2:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: subq $56, %rsp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 64
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
|
|
; CHECK-NEXT: vshuff64x2 $24, {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: # zmm0 = zmm0[0,1,4,5],mem[2,3,0,1]
|
|
; CHECK-NEXT: addq $56, %rsp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
|
; CHECK-NEXT: retq
|
|
%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 <8 x double> %a, <8 x double> %b, <8 x i32> <i32 0, i32 1, i32 4, i32 5, i32 10, i32 11, i32 8, i32 9>
|
|
ret <8 x double> %2
|
|
}
|
|
|
|
define <8 x double> @stack_fold_shuff64x2_mask(<8 x double> %a, <8 x double> %b, i8 %mask, <8 x double>* %passthru) {
|
|
; CHECK-LABEL: stack_fold_shuff64x2_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: subq $56, %rsp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 64
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovapd (%rsi), %zmm1
|
|
; CHECK-NEXT: vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
|
|
; CHECK-NEXT: vshuff64x2 $24, {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm1 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: # zmm1 {%k1} = zmm0[0,1,4,5],mem[2,3,0,1]
|
|
; CHECK-NEXT: vmovapd %zmm1, %zmm0
|
|
; CHECK-NEXT: addq $56, %rsp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
|
; CHECK-NEXT: retq
|
|
%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 <8 x double> %a, <8 x double> %b, <8 x i32> <i32 0, i32 1, i32 4, i32 5, i32 10, i32 11, i32 8, i32 9>
|
|
%3 = bitcast i8 %mask to <8 x i1>
|
|
; load needed to keep the operation from being scheduled above the asm block
|
|
%4 = load <8 x double>, <8 x double>* %passthru
|
|
%5 = select <8 x i1> %3, <8 x double> %2, <8 x double> %4
|
|
ret <8 x double> %5
|
|
}
|
|
|
|
define <8 x double> @stack_fold_shuff64x2_maskz(<8 x double> %a, <8 x double> %b, i8 %mask, <8 x double>* %passthru) {
|
|
; CHECK-LABEL: stack_fold_shuff64x2_maskz:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: subq $56, %rsp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 64
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
|
|
; CHECK-NEXT: vshuff64x2 $24, {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 {%k1} {z} # 64-byte Folded Reload
|
|
; CHECK-NEXT: # zmm0 {%k1} {z} = zmm0[0,1,4,5],mem[2,3,0,1]
|
|
; CHECK-NEXT: addq $56, %rsp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
|
; CHECK-NEXT: retq
|
|
%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 <8 x double> %a, <8 x double> %b, <8 x i32> <i32 0, i32 1, i32 4, i32 5, i32 10, i32 11, i32 8, i32 9>
|
|
%3 = bitcast i8 %mask to <8 x i1>
|
|
%4 = select <8 x i1> %3, <8 x double> %2, <8 x double> zeroinitializer
|
|
ret <8 x double> %4
|
|
}
|
|
|
|
define <16 x float> @stack_fold_shuff32x4_mask(<16 x float> %a, <16 x float> %b, i16 %mask, <16 x float>* %passthru) {
|
|
; CHECK-LABEL: stack_fold_shuff32x4_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: subq $56, %rsp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 64
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovaps (%rsi), %zmm1
|
|
; CHECK-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
|
|
; CHECK-NEXT: vshuff32x4 $20, {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm1 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: # zmm1 {%k1} = zmm0[0,1,2,3,4,5,6,7],mem[4,5,6,7,0,1,2,3]
|
|
; CHECK-NEXT: vmovaps %zmm1, %zmm0
|
|
; CHECK-NEXT: addq $56, %rsp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
|
; CHECK-NEXT: retq
|
|
%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 <16 x float> %a, <16 x float> %b, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 20, i32 21, i32 22, i32 23, i32 16, i32 17, i32 18, i32 19>
|
|
%3 = bitcast i16 %mask to <16 x i1>
|
|
; load needed to keep the operation from being scheduled above the asm block
|
|
%4 = load <16 x float>, <16 x float>* %passthru
|
|
%5 = select <16 x i1> %3, <16 x float> %2, <16 x float> %4
|
|
ret <16 x float> %5
|
|
}
|
|
|
|
define <16 x float> @stack_fold_shuff32x4_maskz(<16 x float> %a, <16 x float> %b, i16 %mask) {
|
|
; CHECK-LABEL: stack_fold_shuff32x4_maskz:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: subq $56, %rsp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 64
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
|
|
; CHECK-NEXT: vshuff32x4 $20, {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 {%k1} {z} # 64-byte Folded Reload
|
|
; CHECK-NEXT: # zmm0 {%k1} {z} = zmm0[0,1,2,3,4,5,6,7],mem[4,5,6,7,0,1,2,3]
|
|
; CHECK-NEXT: addq $56, %rsp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
|
; CHECK-NEXT: retq
|
|
%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 <16 x float> %a, <16 x float> %b, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 20, i32 21, i32 22, i32 23, i32 16, i32 17, i32 18, i32 19>
|
|
%3 = bitcast i16 %mask to <16 x i1>
|
|
%4 = select <16 x i1> %3, <16 x float> %2, <16 x float> zeroinitializer
|
|
ret <16 x float> %4
|
|
}
|
|
|
|
define <8 x double> @stack_fold_subpd_zmm(<8 x double> %a0, <8 x double> %a1) {
|
|
; CHECK-LABEL: stack_fold_subpd_zmm:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vsubpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = fsub <8 x double> %a0, %a1
|
|
ret <8 x double> %2
|
|
}
|
|
|
|
define <16 x float> @stack_fold_subps_zmm(<16 x float> %a0, <16 x float> %a1) {
|
|
; CHECK-LABEL: stack_fold_subps_zmm:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vsubps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = fsub <16 x float> %a0, %a1
|
|
ret <16 x float> %2
|
|
}
|
|
|
|
define double @stack_fold_subsd(double %a0, double %a1) {
|
|
; CHECK-LABEL: stack_fold_subsd:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovsd %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vsubsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 8-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = fsub double %a0, %a1
|
|
ret double %2
|
|
}
|
|
|
|
define <2 x double> @stack_fold_subsd_int(<2 x double> %a0, <2 x double> %a1) {
|
|
; CHECK-LABEL: stack_fold_subsd_int:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vsubsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = extractelement <2 x double> %a0, i32 0
|
|
%3 = extractelement <2 x double> %a1, i32 0
|
|
%4 = fsub double %2, %3
|
|
%5 = insertelement <2 x double> %a0, double %4, i32 0
|
|
ret <2 x double> %5
|
|
}
|
|
|
|
define float @stack_fold_subss(float %a0, float %a1) {
|
|
; CHECK-LABEL: stack_fold_subss:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovss %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vsubss {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 4-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = fsub float %a0, %a1
|
|
ret float %2
|
|
}
|
|
|
|
define <4 x float> @stack_fold_subss_int(<4 x float> %a0, <4 x float> %a1) {
|
|
; CHECK-LABEL: stack_fold_subss_int:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vsubss {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = extractelement <4 x float> %a0, i32 0
|
|
%3 = extractelement <4 x float> %a1, i32 0
|
|
%4 = fsub float %2, %3
|
|
%5 = insertelement <4 x float> %a0, float %4, i32 0
|
|
ret <4 x float> %5
|
|
}
|
|
|
|
define <8 x double> @stack_fold_xorpd_zmm(<8 x double> %a0, <8 x double> %a1) #0 {
|
|
; CHECK-LABEL: stack_fold_xorpd_zmm:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vxorpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: vxorpd %xmm1, %xmm1, %xmm1
|
|
; CHECK-NEXT: vaddpd %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = bitcast <8 x double> %a0 to <8 x i64>
|
|
%3 = bitcast <8 x double> %a1 to <8 x i64>
|
|
%4 = xor <8 x i64> %2, %3
|
|
%5 = bitcast <8 x i64> %4 to <8 x double>
|
|
; fadd forces execution domain
|
|
%6 = fadd <8 x double> %5, <double 0x0, double 0x0, double 0x0, double 0x0, double 0x0, double 0x0, double 0x0, double 0x0>
|
|
ret <8 x double> %6
|
|
}
|
|
|
|
define <16 x float> @stack_fold_xorps_zmm(<16 x float> %a0, <16 x float> %a1) #0 {
|
|
; CHECK-LABEL: stack_fold_xorps_zmm:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vxorps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
|
; CHECK-NEXT: vaddps %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = bitcast <16 x float> %a0 to <16 x i32>
|
|
%3 = bitcast <16 x float> %a1 to <16 x i32>
|
|
%4 = xor <16 x i32> %2, %3
|
|
%5 = bitcast <16 x i32> %4 to <16 x float>
|
|
; fadd forces execution domain
|
|
%6 = fadd <16 x float> %5, <float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0, float 0x0>
|
|
ret <16 x float> %6
|
|
}
|
|
|
|
define i32 @stack_fold_extractps(<4 x float> %a0) {
|
|
; CHECK-LABEL: stack_fold_extractps:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: pushq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: pushq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: pushq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: pushq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: pushq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: pushq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 56
|
|
; CHECK-NEXT: .cfi_offset %rbx, -56
|
|
; CHECK-NEXT: .cfi_offset %r12, -48
|
|
; CHECK-NEXT: .cfi_offset %r13, -40
|
|
; CHECK-NEXT: .cfi_offset %r14, -32
|
|
; CHECK-NEXT: .cfi_offset %r15, -24
|
|
; CHECK-NEXT: .cfi_offset %rbp, -16
|
|
; CHECK-NEXT: vextractps $1, %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Folded Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: movl {{[-0-9]+}}(%r{{[sb]}}p), %eax # 4-byte Reload
|
|
; CHECK-NEXT: popq %rbx
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 48
|
|
; CHECK-NEXT: popq %r12
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 40
|
|
; CHECK-NEXT: popq %r13
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
|
; CHECK-NEXT: popq %r14
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 24
|
|
; CHECK-NEXT: popq %r15
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: popq %rbp
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
|
; CHECK-NEXT: retq
|
|
%1 = extractelement <4 x float> %a0, i32 1
|
|
%2 = bitcast float %1 to i32
|
|
%3 = tail call <2 x i64> asm sideeffect "nop", "=x,~{rax},~{rbx},~{rcx},~{rdx},~{rsi},~{rdi},~{rbp},~{r8},~{r9},~{r10},~{r11},~{r12},~{r13},~{r14},~{r15}"()
|
|
ret i32 %2
|
|
}
|
|
|
|
define <4 x float> @stack_fold_extracti32x4(<16 x float> %a0) {
|
|
; CHECK-LABEL: stack_fold_extracti32x4:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vextractf32x4 $3, %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Folded Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
|
; CHECK-NEXT: vzeroupper
|
|
; CHECK-NEXT: retq
|
|
%1 = shufflevector <16 x float> %a0, <16 x float> undef, <4 x i32> <i32 12, i32 13, i32 14, i32 15>
|
|
%2 = 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}"()
|
|
ret <4 x float> %1
|
|
}
|
|
|
|
define <2 x double> @stack_fold_extractf64x2(<8 x double> %a0) {
|
|
; CHECK-LABEL: stack_fold_extractf64x2:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vextractf32x4 $3, %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Folded Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
|
|
; CHECK-NEXT: vzeroupper
|
|
; CHECK-NEXT: retq
|
|
%1 = shufflevector <8 x double> %a0, <8 x double> undef, <2 x i32> <i32 6, i32 7>
|
|
%2 = tail call <2 x double> 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}"()
|
|
ret <2 x double> %1
|
|
}
|
|
|
|
define <8 x float> @stack_fold_extracti32x8(<16 x float> %a0) {
|
|
; CHECK-LABEL: stack_fold_extracti32x8:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vextractf64x4 $1, %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Folded Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
|
; CHECK-NEXT: retq
|
|
%1 = shufflevector <16 x float> %a0, <16 x float> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
|
|
%2 = 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}"()
|
|
ret <8 x float> %1
|
|
}
|
|
|
|
define <4 x double> @stack_fold_extractf64x4(<8 x double> %a0) {
|
|
; CHECK-LABEL: stack_fold_extractf64x4:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vextractf64x4 $1, %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Folded Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
|
|
; CHECK-NEXT: retq
|
|
%1 = shufflevector <8 x double> %a0, <8 x double> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
|
|
%2 = tail call <2 x double> 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}"()
|
|
ret <4 x double> %1
|
|
}
|
|
|
|
define <16 x float> @stack_fold_insertf32x8(<8 x float> %a0, <8 x float> %a1) {
|
|
; CHECK-LABEL: stack_fold_insertf32x8:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; CHECK-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vinsertf64x4 $1, {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 32-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 float> %a0, <8 x float> %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>
|
|
ret <16 x float> %2
|
|
}
|
|
|
|
define <8 x double> @stack_fold_insertf64x4(<4 x double> %a0, <4 x double> %a1) {
|
|
; CHECK-LABEL: stack_fold_insertf64x4:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; CHECK-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vinsertf64x4 $1, {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 32-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 double> %a0, <4 x double> %a1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
ret <8 x double> %2
|
|
}
|
|
|
|
define <8 x double> @stack_fold_insertf64x4_mask(<8 x double>* %passthru, <4 x double> %a0, <4 x double> %a1, i8 %mask) {
|
|
; CHECK-LABEL: stack_fold_insertf64x4_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; CHECK-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vmovapd (%rdi), %zmm2
|
|
; CHECK-NEXT: vinsertf64x4 $1, {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm2 {%k1} # 32-byte Folded Reload
|
|
; CHECK-NEXT: vmovapd %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 double> %a0, <4 x double> %a1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
%3 = bitcast i8 %mask to <8 x i1>
|
|
%4 = load <8 x double>, <8 x double>* %passthru
|
|
%5 = select <8 x i1> %3, <8 x double> %2, <8 x double> %4
|
|
ret <8 x double> %5
|
|
}
|
|
|
|
define <8 x double> @stack_fold_insertf64x4_maskz(<4 x double> %a0, <4 x double> %a1, i8 %mask) {
|
|
; CHECK-LABEL: stack_fold_insertf64x4_maskz:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; CHECK-NEXT: # kill: def $ymm0 killed $ymm0 def $zmm0
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vinsertf64x4 $1, {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 {%k1} {z} # 32-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 double> %a0, <4 x double> %a1, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
%3 = bitcast i8 %mask to <8 x i1>
|
|
%4 = select <8 x i1> %3, <8 x double> %2, <8 x double> zeroinitializer
|
|
ret <8 x double> %4
|
|
}
|
|
|
|
define <16 x float> @stack_fold_vpermt2ps(<16 x float> %x0, <16 x i32> %x1, <16 x float> %x2) {
|
|
; CHECK-LABEL: stack_fold_vpermt2ps:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vpermt2ps {{[-0-9]+}}(%r{{[sb]}}p), %zmm1, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{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 = call <16 x float> @llvm.x86.avx512.vpermi2var.ps.512(<16 x float> %x0, <16 x i32> %x1, <16 x float> %x2)
|
|
ret <16 x float> %2
|
|
}
|
|
declare <16 x float> @llvm.x86.avx512.vpermi2var.ps.512(<16 x float>, <16 x i32>, <16 x float>)
|
|
|
|
define <16 x float> @stack_fold_vpermi2ps(<16 x i32> %x0, <16 x float> %x1, <16 x float> %x2) {
|
|
; CHECK-LABEL: stack_fold_vpermi2ps:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vpermi2ps {{[-0-9]+}}(%r{{[sb]}}p), %zmm1, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{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 = call <16 x float> @llvm.x86.avx512.vpermi2var.ps.512(<16 x float> %x1, <16 x i32> %x0, <16 x float> %x2)
|
|
ret <16 x float> %2
|
|
}
|
|
|
|
define <16 x float> @stack_fold_vpermi2ps_mask(<16 x float> %x0, <16 x i32>* %x1, <16 x float> %x2, i16 %mask) {
|
|
; CHECK-LABEL: stack_fold_vpermi2ps_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vmovaps (%rdi), %zmm2
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpermi2ps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm2 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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}"()
|
|
%x1b = load <16 x i32>, <16 x i32>* %x1
|
|
%2 = call <16 x float> @llvm.x86.avx512.vpermi2var.ps.512(<16 x float> %x0, <16 x i32> %x1b, <16 x float> %x2)
|
|
%3 = bitcast <16 x i32> %x1b to <16 x float>
|
|
%4 = bitcast i16 %mask to <16 x i1>
|
|
%5 = select <16 x i1> %4, <16 x float> %2, <16 x float> %3
|
|
ret <16 x float> %5
|
|
}
|
|
|
|
define <16 x float> @stack_fold_vpermt2ps_mask(<16 x i32>* %x0, <16 x float> %x1, <16 x float> %x2, i16 %mask) {
|
|
; CHECK-LABEL: stack_fold_vpermt2ps_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vmovaps (%rdi), %zmm1
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpermt2ps {{[-0-9]+}}(%r{{[sb]}}p), %zmm1, %zmm0 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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}"()
|
|
%x0b = load <16 x i32>, <16 x i32>* %x0
|
|
%2 = call <16 x float> @llvm.x86.avx512.vpermi2var.ps.512(<16 x float> %x1, <16 x i32> %x0b, <16 x float> %x2)
|
|
%3 = bitcast i16 %mask to <16 x i1>
|
|
%4 = select <16 x i1> %3, <16 x float> %2, <16 x float> %x1
|
|
ret <16 x float> %4
|
|
}
|
|
|
|
define <16 x float> @stack_fold_vpermt2ps_maskz(<16 x i32>* %x0, <16 x float> %x1, <16 x float> %x2, i16 %mask) {
|
|
; CHECK-LABEL: stack_fold_vpermt2ps_maskz:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vmovaps (%rdi), %zmm1
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vpermt2ps {{[-0-9]+}}(%r{{[sb]}}p), %zmm1, %zmm0 {%k1} {z} # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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}"()
|
|
%x0b = load <16 x i32>, <16 x i32>* %x0
|
|
%2 = call <16 x float> @llvm.x86.avx512.vpermi2var.ps.512(<16 x float> %x1, <16 x i32> %x0b, <16 x float> %x2)
|
|
%3 = bitcast i16 %mask to <16 x i1>
|
|
%4 = select <16 x i1> %3, <16 x float> %2, <16 x float> zeroinitializer
|
|
ret <16 x float> %4
|
|
}
|
|
|
|
define <8 x double> @stack_fold_vpermt2pd(<8 x double> %x0, <8 x i64> %x1, <8 x double> %x2) {
|
|
; CHECK-LABEL: stack_fold_vpermt2pd:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vpermt2pd {{[-0-9]+}}(%r{{[sb]}}p), %zmm1, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{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 = call <8 x double> @llvm.x86.avx512.vpermi2var.pd.512(<8 x double> %x0, <8 x i64> %x1, <8 x double> %x2)
|
|
%3 = bitcast <8 x i64> %x1 to <8 x double>
|
|
ret <8 x double> %2
|
|
}
|
|
declare <8 x double> @llvm.x86.avx512.vpermi2var.pd.512(<8 x double>, <8 x i64>, <8 x double>)
|
|
|
|
define <8 x double> @stack_fold_vpermi2pd(<8 x i64> %x0, <8 x double> %x1, <8 x double> %x2) {
|
|
; CHECK-LABEL: stack_fold_vpermi2pd:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vpermi2pd {{[-0-9]+}}(%r{{[sb]}}p), %zmm1, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{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 = call <8 x double> @llvm.x86.avx512.vpermi2var.pd.512(<8 x double> %x1, <8 x i64> %x0, <8 x double> %x2)
|
|
ret <8 x double> %2
|
|
}
|
|
|
|
define <8 x double> @stack_fold_permpd(<8 x double> %a0) {
|
|
; CHECK-LABEL: stack_fold_permpd:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vpermpd $235, {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: # zmm0 = mem[3,2,2,3,7,6,6,7]
|
|
; CHECK-NEXT: vxorpd %xmm1, %xmm1, %xmm1
|
|
; CHECK-NEXT: vaddpd %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 <8 x double> %a0, <8 x double> undef, <8 x i32> <i32 3, i32 2, i32 2, i32 3, i32 7, i32 6, i32 6, i32 7>
|
|
; fadd forces execution domain
|
|
%3 = fadd <8 x double> %2, <double 0x0, double 0x0, double 0x0, double 0x0, double 0x0, double 0x0, double 0x0, double 0x0>
|
|
ret <8 x double> %3
|
|
}
|
|
|
|
define <8 x double> @stack_fold_permpd_mask(<8 x double>* %passthru, <8 x double> %a0, i8 %mask) {
|
|
; CHECK-LABEL: stack_fold_permpd_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vmovapd (%rdi), %zmm0
|
|
; CHECK-NEXT: vpermpd $235, {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: # zmm0 {%k1} = mem[3,2,2,3,7,6,6,7]
|
|
; CHECK-NEXT: vxorpd %xmm1, %xmm1, %xmm1
|
|
; CHECK-NEXT: vaddpd %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 <8 x double> %a0, <8 x double> undef, <8 x i32> <i32 3, i32 2, i32 2, i32 3, i32 7, i32 6, i32 6, i32 7>
|
|
%3 = bitcast i8 %mask to <8 x i1>
|
|
; load needed to keep the operation from being scheduled above the asm block
|
|
%4 = load <8 x double>, <8 x double>* %passthru
|
|
%5 = select <8 x i1> %3, <8 x double> %2, <8 x double> %4
|
|
; fadd forces execution domain
|
|
%6 = fadd <8 x double> %5, <double 0x0, double 0x0, double 0x0, double 0x0, double 0x0, double 0x0, double 0x0, double 0x0>
|
|
ret <8 x double> %6
|
|
}
|
|
|
|
define <8 x double> @stack_fold_permpd_maskz(<8 x double> %a0, i8 %mask) {
|
|
; CHECK-LABEL: stack_fold_permpd_maskz:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpermpd $235, {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 {%k1} {z} # 64-byte Folded Reload
|
|
; CHECK-NEXT: # zmm0 {%k1} {z} = mem[3,2,2,3,7,6,6,7]
|
|
; CHECK-NEXT: retq
|
|
%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 <8 x double> %a0, <8 x double> undef, <8 x i32> <i32 3, i32 2, i32 2, i32 3, i32 7, i32 6, i32 6, i32 7>
|
|
%3 = bitcast i8 %mask to <8 x i1>
|
|
%4 = select <8 x i1> %3, <8 x double> %2, <8 x double> zeroinitializer
|
|
ret <8 x double> %4
|
|
}
|
|
|
|
define <8 x double> @stack_fold_permpdvar(<8 x i64> %a0, <8 x double> %a1) {
|
|
; CHECK-LABEL: stack_fold_permpdvar:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vpermpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: vxorpd %xmm1, %xmm1, %xmm1
|
|
; CHECK-NEXT: vaddpd %zmm1, %zmm0, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = call <8 x double> @llvm.x86.avx512.permvar.df.512(<8 x double> %a1, <8 x i64> %a0)
|
|
; fadd forces execution domain
|
|
%3 = fadd <8 x double> %2, zeroinitializer
|
|
ret <8 x double> %3
|
|
}
|
|
declare <8 x double> @llvm.x86.avx512.permvar.df.512(<8 x double>, <8 x i64>) nounwind readonly
|
|
|
|
define <16 x float> @stack_fold_permps(<16 x i32> %a0, <16 x float> %a1) {
|
|
; CHECK-LABEL: stack_fold_permps:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vpermps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = call <16 x float> @llvm.x86.avx512.permvar.sf.512(<16 x float> %a1, <16 x i32> %a0)
|
|
ret <16 x float> %2
|
|
}
|
|
declare <16 x float> @llvm.x86.avx512.permvar.sf.512(<16 x float>, <16 x i32>) nounwind readonly
|
|
|
|
define <8 x double> @stack_fold_permilpd_zmm(<8 x double> %a0) {
|
|
; CHECK-LABEL: stack_fold_permilpd_zmm:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vpermilpd $85, {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: # zmm0 = mem[1,0,3,2,5,4,7,6]
|
|
; CHECK-NEXT: retq
|
|
%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 <8 x double> %a0, <8 x double> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
|
|
ret <8 x double> %2
|
|
}
|
|
|
|
define <8 x double> @stack_fold_permilpd_zmm_mask(<8 x double>* %passthru, <8 x double> %a0, i8 %mask) {
|
|
; CHECK-LABEL: stack_fold_permilpd_zmm_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vmovapd (%rdi), %zmm1
|
|
; CHECK-NEXT: vpermilpd $85, {{[-0-9]+}}(%r{{[sb]}}p), %zmm1 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: # zmm1 {%k1} = mem[1,0,3,2,5,4,7,6]
|
|
; CHECK-NEXT: vmovapd %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 <8 x double> %a0, <8 x double> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
|
|
%3 = bitcast i8 %mask to <8 x i1>
|
|
; load needed to keep the operation from being scheduled above the asm block
|
|
%4 = load <8 x double>, <8 x double>* %passthru
|
|
%5 = select <8 x i1> %3, <8 x double> %2, <8 x double> %4
|
|
ret <8 x double> %5
|
|
}
|
|
|
|
define <8 x double> @stack_fold_permilpd_zmm_maskz(<8 x double> %a0, i8 %mask) {
|
|
; CHECK-LABEL: stack_fold_permilpd_zmm_maskz:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpermilpd $85, {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 {%k1} {z} # 64-byte Folded Reload
|
|
; CHECK-NEXT: # zmm0 {%k1} {z} = mem[1,0,3,2,5,4,7,6]
|
|
; CHECK-NEXT: retq
|
|
%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 <8 x double> %a0, <8 x double> undef, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
|
|
%3 = bitcast i8 %mask to <8 x i1>
|
|
%4 = select <8 x i1> %3, <8 x double> %2, <8 x double> zeroinitializer
|
|
ret <8 x double> %4
|
|
}
|
|
|
|
define <8 x double> @stack_fold_permilpdvar_zmm(<8 x double> %a0, <8 x i64> %a1) {
|
|
; CHECK-LABEL: stack_fold_permilpdvar_zmm:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vpermilpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = call <8 x double> @llvm.x86.avx512.vpermilvar.pd.512(<8 x double> %a0, <8 x i64> %a1)
|
|
ret <8 x double> %2
|
|
}
|
|
declare <8 x double> @llvm.x86.avx512.vpermilvar.pd.512(<8 x double>, <8 x i64>) nounwind readnone
|
|
|
|
define <8 x double> @stack_fold_permilpdvar_zmm_mask(<8 x double>* %passthru, <8 x double> %a0, <8 x i64> %a1, i8 %mask) {
|
|
; CHECK-LABEL: stack_fold_permilpdvar_zmm_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vmovapd (%rdi), %zmm2
|
|
; CHECK-NEXT: vpermilpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm2 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: vmovapd %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = call <8 x double> @llvm.x86.avx512.vpermilvar.pd.512(<8 x double> %a0, <8 x i64> %a1)
|
|
%3 = bitcast i8 %mask to <8 x i1>
|
|
; load needed to keep the operation from being scheduled above the asm block
|
|
%4 = load <8 x double>, <8 x double>* %passthru
|
|
%5 = select <8 x i1> %3, <8 x double> %2, <8 x double> %4
|
|
ret <8 x double> %5
|
|
}
|
|
|
|
define <8 x double> @stack_fold_permilpdvar_zmm_maskz(<8 x double> %a0, <8 x i64> %a1, i8 %mask) {
|
|
; CHECK-LABEL: stack_fold_permilpdvar_zmm_maskz:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpermilpd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 {%k1} {z} # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = call <8 x double> @llvm.x86.avx512.vpermilvar.pd.512(<8 x double> %a0, <8 x i64> %a1)
|
|
%3 = bitcast i8 %mask to <8 x i1>
|
|
%4 = select <8 x i1> %3, <8 x double> %2, <8 x double> zeroinitializer
|
|
ret <8 x double> %4
|
|
}
|
|
|
|
define <16 x float> @stack_fold_permilps_zmm(<16 x float> %a0) {
|
|
; CHECK-LABEL: stack_fold_permilps_zmm:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vpermilps $27, {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: # zmm0 = mem[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12]
|
|
; CHECK-NEXT: retq
|
|
%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 <16 x float> %a0, <16 x float> undef, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
|
|
ret <16 x float> %2
|
|
}
|
|
|
|
define <16 x float> @stack_fold_permilps_zmm_mask(<16 x float>* %passthru, <16 x float> %a0, i16 %mask) {
|
|
; CHECK-LABEL: stack_fold_permilps_zmm_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vmovaps (%rdi), %zmm1
|
|
; CHECK-NEXT: vpermilps $27, {{[-0-9]+}}(%r{{[sb]}}p), %zmm1 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: # zmm1 {%k1} = mem[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12]
|
|
; CHECK-NEXT: vmovaps %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 <16 x float> %a0, <16 x float> undef, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
|
|
%3 = bitcast i16 %mask to <16 x i1>
|
|
; load needed to keep the operation from being scheduled above the asm block
|
|
%4 = load <16 x float>, <16 x float>* %passthru
|
|
%5 = select <16 x i1> %3, <16 x float> %2, <16 x float> %4
|
|
ret <16 x float> %5
|
|
}
|
|
|
|
define <16 x float> @stack_fold_permilps_zmm_maskz(<16 x float> %a0, i16 %mask) {
|
|
; CHECK-LABEL: stack_fold_permilps_zmm_maskz:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpermilps $27, {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 {%k1} {z} # 64-byte Folded Reload
|
|
; CHECK-NEXT: # zmm0 {%k1} {z} = mem[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12]
|
|
; CHECK-NEXT: retq
|
|
%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 <16 x float> %a0, <16 x float> undef, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
|
|
%3 = bitcast i16 %mask to <16 x i1>
|
|
%4 = select <16 x i1> %3, <16 x float> %2, <16 x float> zeroinitializer
|
|
ret <16 x float> %4
|
|
}
|
|
|
|
define <16 x float> @stack_fold_permilpsvar_zmm(<16 x float> %a0, <16 x i32> %a1) {
|
|
; CHECK-LABEL: stack_fold_permilpsvar_zmm:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: vpermilps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = call <16 x float> @llvm.x86.avx512.vpermilvar.ps.512(<16 x float> %a0, <16 x i32> %a1)
|
|
ret <16 x float> %2
|
|
}
|
|
declare <16 x float> @llvm.x86.avx512.vpermilvar.ps.512(<16 x float>, <16 x i32>) nounwind readnone
|
|
|
|
define <16 x float> @stack_fold_permilpsvar_zmm_mask(<16 x float>* %passthru, <16 x float> %a0, <16 x i32> %a1, i16 %mask) {
|
|
; CHECK-LABEL: stack_fold_permilpsvar_zmm_mask:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %esi, %k1
|
|
; CHECK-NEXT: vmovaps (%rdi), %zmm2
|
|
; CHECK-NEXT: vpermilps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm2 {%k1} # 64-byte Folded Reload
|
|
; CHECK-NEXT: vmovaps %zmm2, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%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 = call <16 x float> @llvm.x86.avx512.vpermilvar.ps.512(<16 x float> %a0, <16 x i32> %a1)
|
|
%3 = bitcast i16 %mask to <16 x i1>
|
|
; load needed to keep the operation from being scheduled above the asm block
|
|
%4 = load <16 x float>, <16 x float>* %passthru
|
|
%5 = select <16 x i1> %3, <16 x float> %2, <16 x float> %4
|
|
ret <16 x float> %5
|
|
}
|
|
|
|
define <16 x float> @stack_fold_permilpsvar_zmm_maskz(<16 x float> %a0, <16 x i32> %a1, i16 %mask) {
|
|
; CHECK-LABEL: stack_fold_permilpsvar_zmm_maskz:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vpermilps {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm0 {%k1} {z} # 64-byte Folded Reload
|
|
; CHECK-NEXT: retq
|
|
%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 = call <16 x float> @llvm.x86.avx512.vpermilvar.ps.512(<16 x float> %a0, <16 x i32> %a1)
|
|
%3 = bitcast i16 %mask to <16 x i1>
|
|
%4 = select <16 x i1> %3, <16 x float> %2, <16 x float> zeroinitializer
|
|
ret <16 x float> %4
|
|
}
|
|
|
|
attributes #0 = { "unsafe-fp-math"="false" }
|
|
attributes #1 = { "unsafe-fp-math"="true" }
|