985 lines
48 KiB
LLVM
985 lines
48 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --force-update
|
|
; RUN: llc -verify-machineinstrs -mcpu=sapphirerapids -mattr=+false-deps-range -mtriple=x86_64-unknown-unknown < %s | FileCheck %s --check-prefixes=ENABLE
|
|
; RUN: llc -verify-machineinstrs -mcpu=sapphirerapids -mattr=-false-deps-range -mtriple=x86_64-unknown-unknown < %s | FileCheck %s --check-prefixes=DISABLE
|
|
|
|
define <4 x float> @rangeps_128(<4 x float> %a0, <4 x float> %a1) {
|
|
; ENABLE-LABEL: rangeps_128:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
|
; ENABLE-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
|
; ENABLE-NEXT: vrangeps $88, %xmm2, %xmm0, %xmm1
|
|
; ENABLE-NEXT: vaddps %xmm2, %xmm0, %xmm0
|
|
; ENABLE-NEXT: vaddps %xmm0, %xmm1, %xmm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangeps_128:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
|
; DISABLE-NEXT: vrangeps $88, %xmm2, %xmm0, %xmm1
|
|
; DISABLE-NEXT: vaddps %xmm2, %xmm0, %xmm0
|
|
; DISABLE-NEXT: vaddps %xmm0, %xmm1, %xmm0
|
|
; DISABLE-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.avx512.mask.range.ps.128(<4 x float> %a0, <4 x float> %a1, i32 88, <4 x float> undef, i8 -1)
|
|
%3 = fadd <4 x float> %a0, %a1
|
|
%res = fadd <4 x float> %2, %3
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <4 x float> @rangeps_mem_128(<4 x float> %a0, <4 x float>* %p1) {
|
|
; ENABLE-LABEL: rangeps_mem_128:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
|
; ENABLE-NEXT: vxorps %xmm0, %xmm0, %xmm0
|
|
; ENABLE-NEXT: vrangeps $88, (%rdi), %xmm1, %xmm0
|
|
; ENABLE-NEXT: vaddps %xmm1, %xmm0, %xmm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangeps_mem_128:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
|
; DISABLE-NEXT: vrangeps $88, (%rdi), %xmm1, %xmm0
|
|
; DISABLE-NEXT: vaddps %xmm1, %xmm0, %xmm0
|
|
; DISABLE-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}"()
|
|
%a1 = load <4 x float>, <4 x float>* %p1, align 64
|
|
%2 = call <4 x float> @llvm.x86.avx512.mask.range.ps.128(<4 x float> %a0, <4 x float> %a1, i32 88, <4 x float> undef, i8 -1)
|
|
%res = fadd <4 x float> %2, %a0
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <4 x float> @rangeps_broadcast_128(<4 x float> %a0, float* %p1) {
|
|
; ENABLE-LABEL: rangeps_broadcast_128:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
|
; ENABLE-NEXT: vxorps %xmm0, %xmm0, %xmm0
|
|
; ENABLE-NEXT: vrangeps $88, (%rdi){1to4}, %xmm1, %xmm0
|
|
; ENABLE-NEXT: vaddps %xmm1, %xmm0, %xmm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangeps_broadcast_128:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
|
; DISABLE-NEXT: vrangeps $88, (%rdi){1to4}, %xmm1, %xmm0
|
|
; DISABLE-NEXT: vaddps %xmm1, %xmm0, %xmm0
|
|
; DISABLE-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}"()
|
|
%v1 = load float, float* %p1, align 4
|
|
%t0 = insertelement <4 x float> undef, float %v1, i64 0
|
|
%a1 = shufflevector <4 x float> %t0, <4 x float> undef, <4 x i32> zeroinitializer
|
|
%2 = call <4 x float> @llvm.x86.avx512.mask.range.ps.128(<4 x float> %a0, <4 x float> %a1, i32 88, <4 x float> undef, i8 -1)
|
|
%res = fadd <4 x float> %2, %a0
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <4 x float> @rangeps_maskz_128(<4 x float> %a0, <4 x float> %a1, i8* %pmask) {
|
|
; ENABLE-LABEL: rangeps_maskz_128:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: kmovb (%rdi), %k1
|
|
; ENABLE-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
|
; ENABLE-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
|
; ENABLE-NEXT: vrangeps $88, %xmm2, %xmm0, %xmm1 {%k1} {z}
|
|
; ENABLE-NEXT: vaddps %xmm2, %xmm0, %xmm0
|
|
; ENABLE-NEXT: vaddps %xmm0, %xmm1, %xmm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangeps_maskz_128:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: kmovb (%rdi), %k1
|
|
; DISABLE-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
|
; DISABLE-NEXT: vrangeps $88, %xmm2, %xmm0, %xmm1 {%k1} {z}
|
|
; DISABLE-NEXT: vaddps %xmm2, %xmm0, %xmm0
|
|
; DISABLE-NEXT: vaddps %xmm0, %xmm1, %xmm0
|
|
; DISABLE-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}"()
|
|
%mask = load i8, i8* %pmask
|
|
%2 = call <4 x float> @llvm.x86.avx512.mask.range.ps.128(<4 x float> %a0, <4 x float> %a1, i32 88, <4 x float> undef, i8 %mask)
|
|
%3 = fadd <4 x float> %a0, %a1
|
|
%res = fadd <4 x float> %2, %3
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
declare <4 x float> @llvm.x86.avx512.mask.range.ps.128(<4 x float>, <4 x float>, i32, <4 x float>, i8) nounwind readnone
|
|
|
|
define <8 x float> @rangeps_256(<8 x float> %a0, <8 x float> %a1) {
|
|
; ENABLE-LABEL: rangeps_256:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm2 # 32-byte Reload
|
|
; ENABLE-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
|
; ENABLE-NEXT: vrangeps $88, %ymm2, %ymm0, %ymm1
|
|
; ENABLE-NEXT: vaddps %ymm2, %ymm0, %ymm0
|
|
; ENABLE-NEXT: vaddps %ymm0, %ymm1, %ymm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangeps_256:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm2 # 32-byte Reload
|
|
; DISABLE-NEXT: vrangeps $88, %ymm2, %ymm0, %ymm1
|
|
; DISABLE-NEXT: vaddps %ymm2, %ymm0, %ymm0
|
|
; DISABLE-NEXT: vaddps %ymm0, %ymm1, %ymm0
|
|
; DISABLE-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 float> @llvm.x86.avx512.mask.range.ps.256(<8 x float> %a0, <8 x float> %a1, i32 88, <8 x float> undef, i8 -1)
|
|
%3 = fadd <8 x float> %a0, %a1
|
|
%res = fadd <8 x float> %2, %3
|
|
ret <8 x float> %res
|
|
}
|
|
|
|
define <8 x float> @rangeps_mem_256(<8 x float> %a0, <8 x float>* %p1) {
|
|
; ENABLE-LABEL: rangeps_mem_256:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
|
|
; ENABLE-NEXT: vxorps %xmm0, %xmm0, %xmm0
|
|
; ENABLE-NEXT: vrangeps $88, (%rdi), %ymm1, %ymm0
|
|
; ENABLE-NEXT: vaddps %ymm1, %ymm0, %ymm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangeps_mem_256:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
|
|
; DISABLE-NEXT: vrangeps $88, (%rdi), %ymm1, %ymm0
|
|
; DISABLE-NEXT: vaddps %ymm1, %ymm0, %ymm0
|
|
; DISABLE-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}"()
|
|
%a1 = load <8 x float>, <8 x float>* %p1, align 64
|
|
%2 = call <8 x float> @llvm.x86.avx512.mask.range.ps.256(<8 x float> %a0, <8 x float> %a1, i32 88, <8 x float> undef, i8 -1)
|
|
%res = fadd <8 x float> %2, %a0
|
|
ret <8 x float> %res
|
|
}
|
|
|
|
define <8 x float> @rangeps_broadcast_256(<8 x float> %a0, float* %p1) {
|
|
; ENABLE-LABEL: rangeps_broadcast_256:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
|
|
; ENABLE-NEXT: vxorps %xmm0, %xmm0, %xmm0
|
|
; ENABLE-NEXT: vrangeps $88, (%rdi){1to8}, %ymm1, %ymm0
|
|
; ENABLE-NEXT: vaddps %ymm1, %ymm0, %ymm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangeps_broadcast_256:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
|
|
; DISABLE-NEXT: vrangeps $88, (%rdi){1to8}, %ymm1, %ymm0
|
|
; DISABLE-NEXT: vaddps %ymm1, %ymm0, %ymm0
|
|
; DISABLE-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}"()
|
|
%v1 = load float, float* %p1, align 4
|
|
%t0 = insertelement <8 x float> undef, float %v1, i64 0
|
|
%a1 = shufflevector <8 x float> %t0, <8 x float> undef, <8 x i32> zeroinitializer
|
|
%2 = call <8 x float> @llvm.x86.avx512.mask.range.ps.256(<8 x float> %a0, <8 x float> %a1, i32 88, <8 x float> undef, i8 -1)
|
|
%res = fadd <8 x float> %2, %a0
|
|
ret <8 x float> %res
|
|
}
|
|
|
|
define <8 x float> @rangeps_maskz_256(<8 x float> %a0, <8 x float> %a1, i8* %pmask) {
|
|
; ENABLE-LABEL: rangeps_maskz_256:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: kmovb (%rdi), %k1
|
|
; ENABLE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm2 # 32-byte Reload
|
|
; ENABLE-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
|
; ENABLE-NEXT: vrangeps $44, %ymm2, %ymm0, %ymm1 {%k1} {z}
|
|
; ENABLE-NEXT: vaddps %ymm2, %ymm0, %ymm0
|
|
; ENABLE-NEXT: vaddps %ymm0, %ymm1, %ymm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangeps_maskz_256:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: kmovb (%rdi), %k1
|
|
; DISABLE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm2 # 32-byte Reload
|
|
; DISABLE-NEXT: vrangeps $44, %ymm2, %ymm0, %ymm1 {%k1} {z}
|
|
; DISABLE-NEXT: vaddps %ymm2, %ymm0, %ymm0
|
|
; DISABLE-NEXT: vaddps %ymm0, %ymm1, %ymm0
|
|
; DISABLE-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}"()
|
|
%mask = load i8, i8* %pmask
|
|
%2 = call <8 x float> @llvm.x86.avx512.mask.range.ps.256(<8 x float> %a0, <8 x float> %a1, i32 44, <8 x float> undef, i8 %mask)
|
|
%3 = fadd <8 x float> %a0, %a1
|
|
%res = fadd <8 x float> %2, %3
|
|
ret <8 x float> %res
|
|
}
|
|
|
|
declare <8 x float> @llvm.x86.avx512.mask.range.ps.256(<8 x float>, <8 x float>, i32, <8 x float>, i8) nounwind readnone
|
|
|
|
define <16 x float> @rangeps_512(<16 x float> %a0, <16 x float> %a1) {
|
|
; ENABLE-LABEL: rangeps_512:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm2 # 64-byte Reload
|
|
; ENABLE-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
|
; ENABLE-NEXT: vrangeps $88, %zmm2, %zmm0, %zmm1
|
|
; ENABLE-NEXT: vaddps %zmm2, %zmm0, %zmm0
|
|
; ENABLE-NEXT: vaddps %zmm0, %zmm1, %zmm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangeps_512:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm2 # 64-byte Reload
|
|
; DISABLE-NEXT: vrangeps $88, %zmm2, %zmm0, %zmm1
|
|
; DISABLE-NEXT: vaddps %zmm2, %zmm0, %zmm0
|
|
; DISABLE-NEXT: vaddps %zmm0, %zmm1, %zmm0
|
|
; DISABLE-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.mask.range.ps.512(<16 x float> %a0, <16 x float> %a1, i32 88, <16 x float> undef, i16 -1, i32 4)
|
|
%3 = fadd <16 x float> %a0, %a1
|
|
%res = fadd <16 x float> %2, %3
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @rangeps_mem_512(<16 x float> %a0, <16 x float>* %p1) {
|
|
; ENABLE-LABEL: rangeps_mem_512:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm1 # 64-byte Reload
|
|
; ENABLE-NEXT: vpxor %xmm0, %xmm0, %xmm0
|
|
; ENABLE-NEXT: vrangeps $88, (%rdi), %zmm1, %zmm0
|
|
; ENABLE-NEXT: vaddps %zmm1, %zmm0, %zmm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangeps_mem_512:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm1 # 64-byte Reload
|
|
; DISABLE-NEXT: vrangeps $88, (%rdi), %zmm1, %zmm0
|
|
; DISABLE-NEXT: vaddps %zmm1, %zmm0, %zmm0
|
|
; DISABLE-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}"()
|
|
%a1 = load <16 x float>, <16 x float>* %p1, align 64
|
|
%2 = call <16 x float> @llvm.x86.avx512.mask.range.ps.512(<16 x float> %a0, <16 x float> %a1, i32 88, <16 x float> undef, i16 -1, i32 4)
|
|
%res = fadd <16 x float> %2, %a0
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @rangeps_broadcast_512(<16 x float> %a0, float* %p1) {
|
|
; ENABLE-LABEL: rangeps_broadcast_512:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm1 # 64-byte Reload
|
|
; ENABLE-NEXT: vpxor %xmm0, %xmm0, %xmm0
|
|
; ENABLE-NEXT: vrangeps $88, (%rdi){1to16}, %zmm1, %zmm0
|
|
; ENABLE-NEXT: vaddps %zmm1, %zmm0, %zmm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangeps_broadcast_512:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm1 # 64-byte Reload
|
|
; DISABLE-NEXT: vrangeps $88, (%rdi){1to16}, %zmm1, %zmm0
|
|
; DISABLE-NEXT: vaddps %zmm1, %zmm0, %zmm0
|
|
; DISABLE-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}"()
|
|
%v1 = load float, float* %p1, align 4
|
|
%t0 = insertelement <16 x float> undef, float %v1, i64 0
|
|
%a1 = shufflevector <16 x float> %t0, <16 x float> undef, <16 x i32> zeroinitializer
|
|
%2 = call <16 x float> @llvm.x86.avx512.mask.range.ps.512(<16 x float> %a0, <16 x float> %a1, i32 88, <16 x float> undef, i16 -1, i32 4)
|
|
%res = fadd <16 x float> %2, %a0
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
define <16 x float> @rangeps_maskz_512(<16 x float> %a0, <16 x float> %a1, i16* %pmask) {
|
|
; ENABLE-LABEL: rangeps_maskz_512:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: kmovw (%rdi), %k1
|
|
; ENABLE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm2 # 64-byte Reload
|
|
; ENABLE-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
|
; ENABLE-NEXT: vrangeps $88, %zmm2, %zmm0, %zmm1 {%k1} {z}
|
|
; ENABLE-NEXT: vaddps %zmm2, %zmm0, %zmm0
|
|
; ENABLE-NEXT: vaddps %zmm0, %zmm1, %zmm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangeps_maskz_512:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: kmovw (%rdi), %k1
|
|
; DISABLE-NEXT: vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm2 # 64-byte Reload
|
|
; DISABLE-NEXT: vrangeps $88, %zmm2, %zmm0, %zmm1 {%k1} {z}
|
|
; DISABLE-NEXT: vaddps %zmm2, %zmm0, %zmm0
|
|
; DISABLE-NEXT: vaddps %zmm0, %zmm1, %zmm0
|
|
; DISABLE-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}"()
|
|
%mask = load i16, i16* %pmask
|
|
%2 = call <16 x float> @llvm.x86.avx512.mask.range.ps.512(<16 x float> %a0, <16 x float> %a1, i32 88, <16 x float> undef, i16 %mask, i32 4)
|
|
%3 = fadd <16 x float> %a0, %a1
|
|
%res = fadd <16 x float> %2, %3
|
|
ret <16 x float> %res
|
|
}
|
|
|
|
declare <16 x float> @llvm.x86.avx512.mask.range.ps.512(<16 x float>, <16 x float>, i32, <16 x float>, i16, i32) nounwind readnone
|
|
|
|
|
|
define <2 x double> @rangepd_128(<2 x double> %a0, <2 x double> %a1) {
|
|
; ENABLE-LABEL: rangepd_128:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: vmovapd {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
|
; ENABLE-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
|
; ENABLE-NEXT: vrangepd $88, %xmm2, %xmm0, %xmm1
|
|
; ENABLE-NEXT: vaddpd %xmm2, %xmm0, %xmm0
|
|
; ENABLE-NEXT: vaddpd %xmm0, %xmm1, %xmm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangepd_128:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: vmovapd {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
|
; DISABLE-NEXT: vrangepd $88, %xmm2, %xmm0, %xmm1
|
|
; DISABLE-NEXT: vaddpd %xmm2, %xmm0, %xmm0
|
|
; DISABLE-NEXT: vaddpd %xmm0, %xmm1, %xmm0
|
|
; DISABLE-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 <2 x double> @llvm.x86.avx512.mask.range.pd.128(<2 x double> %a0, <2 x double> %a1, i32 88, <2 x double> undef, i8 -1)
|
|
%3 = fadd <2 x double> %a0, %a1
|
|
%res = fadd <2 x double> %2, %3
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
define <2 x double> @rangepd_mem_128(<2 x double> %a0, <2 x double>* %p1) {
|
|
; ENABLE-LABEL: rangepd_mem_128:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: vmovapd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
|
; ENABLE-NEXT: vxorps %xmm0, %xmm0, %xmm0
|
|
; ENABLE-NEXT: vrangepd $88, (%rdi), %xmm1, %xmm0
|
|
; ENABLE-NEXT: vaddpd %xmm1, %xmm0, %xmm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangepd_mem_128:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: vmovapd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
|
; DISABLE-NEXT: vrangepd $88, (%rdi), %xmm1, %xmm0
|
|
; DISABLE-NEXT: vaddpd %xmm1, %xmm0, %xmm0
|
|
; DISABLE-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}"()
|
|
%a1 = load <2 x double>, <2 x double>* %p1, align 64
|
|
%2 = call <2 x double> @llvm.x86.avx512.mask.range.pd.128(<2 x double> %a0, <2 x double> %a1, i32 88, <2 x double> undef, i8 -1)
|
|
%res = fadd <2 x double> %2, %a0
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
define <2 x double> @rangepd_broadcast_128(<2 x double> %a0, double* %p1) {
|
|
; ENABLE-LABEL: rangepd_broadcast_128:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: vmovapd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
|
; ENABLE-NEXT: vxorps %xmm0, %xmm0, %xmm0
|
|
; ENABLE-NEXT: vrangepd $88, (%rdi){1to2}, %xmm1, %xmm0
|
|
; ENABLE-NEXT: vaddpd %xmm1, %xmm0, %xmm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangepd_broadcast_128:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: vmovapd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
|
; DISABLE-NEXT: vrangepd $88, (%rdi){1to2}, %xmm1, %xmm0
|
|
; DISABLE-NEXT: vaddpd %xmm1, %xmm0, %xmm0
|
|
; DISABLE-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}"()
|
|
%v1 = load double, double* %p1, align 4
|
|
%t0 = insertelement <2 x double> undef, double %v1, i64 0
|
|
%a1 = shufflevector <2 x double> %t0, <2 x double> undef, <2 x i32> zeroinitializer
|
|
%2 = call <2 x double> @llvm.x86.avx512.mask.range.pd.128(<2 x double> %a0, <2 x double> %a1, i32 88, <2 x double> undef, i8 -1)
|
|
%res = fadd <2 x double> %2, %a0
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
define <2 x double> @rangepd_maskz_128(<2 x double> %a0, <2 x double> %a1, i8* %pmask) {
|
|
; ENABLE-LABEL: rangepd_maskz_128:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: kmovb (%rdi), %k1
|
|
; ENABLE-NEXT: vmovapd {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
|
; ENABLE-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
|
; ENABLE-NEXT: vrangepd $88, %xmm2, %xmm0, %xmm1 {%k1} {z}
|
|
; ENABLE-NEXT: vaddpd %xmm2, %xmm0, %xmm0
|
|
; ENABLE-NEXT: vaddpd %xmm0, %xmm1, %xmm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangepd_maskz_128:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: kmovb (%rdi), %k1
|
|
; DISABLE-NEXT: vmovapd {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
|
; DISABLE-NEXT: vrangepd $88, %xmm2, %xmm0, %xmm1 {%k1} {z}
|
|
; DISABLE-NEXT: vaddpd %xmm2, %xmm0, %xmm0
|
|
; DISABLE-NEXT: vaddpd %xmm0, %xmm1, %xmm0
|
|
; DISABLE-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}"()
|
|
%mask = load i8, i8* %pmask
|
|
%2 = call <2 x double> @llvm.x86.avx512.mask.range.pd.128(<2 x double> %a0, <2 x double> %a1, i32 88, <2 x double> undef, i8 %mask)
|
|
%3 = fadd <2 x double> %a0, %a1
|
|
%res = fadd <2 x double> %2, %3
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
declare <2 x double> @llvm.x86.avx512.mask.range.pd.128(<2 x double>, <2 x double>, i32, <2 x double>, i8) nounwind readnone
|
|
|
|
define <4 x double> @rangepd_256(<4 x double> %a0, <4 x double> %a1) {
|
|
; ENABLE-LABEL: rangepd_256:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %ymm2 # 32-byte Reload
|
|
; ENABLE-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
|
; ENABLE-NEXT: vrangepd $88, %ymm2, %ymm0, %ymm1
|
|
; ENABLE-NEXT: vaddpd %ymm2, %ymm0, %ymm0
|
|
; ENABLE-NEXT: vaddpd %ymm0, %ymm1, %ymm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangepd_256:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %ymm2 # 32-byte Reload
|
|
; DISABLE-NEXT: vrangepd $88, %ymm2, %ymm0, %ymm1
|
|
; DISABLE-NEXT: vaddpd %ymm2, %ymm0, %ymm0
|
|
; DISABLE-NEXT: vaddpd %ymm0, %ymm1, %ymm0
|
|
; DISABLE-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 double> @llvm.x86.avx512.mask.range.pd.256(<4 x double> %a0, <4 x double> %a1, i32 88, <4 x double> undef, i8 -1)
|
|
%3 = fadd <4 x double> %a0, %a1
|
|
%res = fadd <4 x double> %2, %3
|
|
ret <4 x double> %res
|
|
}
|
|
|
|
define <4 x double> @rangepd_mem_256(<4 x double> %a0, <4 x double>* %p1) {
|
|
; ENABLE-LABEL: rangepd_mem_256:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
|
|
; ENABLE-NEXT: vxorps %xmm0, %xmm0, %xmm0
|
|
; ENABLE-NEXT: vrangepd $88, (%rdi), %ymm1, %ymm0
|
|
; ENABLE-NEXT: vaddpd %ymm1, %ymm0, %ymm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangepd_mem_256:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
|
|
; DISABLE-NEXT: vrangepd $88, (%rdi), %ymm1, %ymm0
|
|
; DISABLE-NEXT: vaddpd %ymm1, %ymm0, %ymm0
|
|
; DISABLE-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}"()
|
|
%a1 = load <4 x double>, <4 x double>* %p1, align 64
|
|
%2 = call <4 x double> @llvm.x86.avx512.mask.range.pd.256(<4 x double> %a0, <4 x double> %a1, i32 88, <4 x double> undef, i8 -1)
|
|
%res = fadd <4 x double> %2, %a0
|
|
ret <4 x double> %res
|
|
}
|
|
|
|
define <4 x double> @rangepd_broadcast_256(<4 x double> %a0, double* %p1) {
|
|
; ENABLE-LABEL: rangepd_broadcast_256:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
|
|
; ENABLE-NEXT: vxorps %xmm0, %xmm0, %xmm0
|
|
; ENABLE-NEXT: vrangepd $88, (%rdi){1to4}, %ymm1, %ymm0
|
|
; ENABLE-NEXT: vaddpd %ymm1, %ymm0, %ymm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangepd_broadcast_256:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
|
|
; DISABLE-NEXT: vrangepd $88, (%rdi){1to4}, %ymm1, %ymm0
|
|
; DISABLE-NEXT: vaddpd %ymm1, %ymm0, %ymm0
|
|
; DISABLE-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}"()
|
|
%v1 = load double, double* %p1, align 4
|
|
%t0 = insertelement <4 x double> undef, double %v1, i64 0
|
|
%a1 = shufflevector <4 x double> %t0, <4 x double> undef, <4 x i32> zeroinitializer
|
|
%2 = call <4 x double> @llvm.x86.avx512.mask.range.pd.256(<4 x double> %a0, <4 x double> %a1, i32 88, <4 x double> undef, i8 -1)
|
|
%res = fadd <4 x double> %2, %a0
|
|
ret <4 x double> %res
|
|
}
|
|
|
|
define <4 x double> @rangepd_maskz_256(<4 x double> %a0, <4 x double> %a1, i8* %pmask) {
|
|
; ENABLE-LABEL: rangepd_maskz_256:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: kmovb (%rdi), %k1
|
|
; ENABLE-NEXT: vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %ymm2 # 32-byte Reload
|
|
; ENABLE-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
|
; ENABLE-NEXT: vrangepd $88, %ymm2, %ymm0, %ymm1 {%k1} {z}
|
|
; ENABLE-NEXT: vaddpd %ymm2, %ymm0, %ymm0
|
|
; ENABLE-NEXT: vaddpd %ymm0, %ymm1, %ymm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangepd_maskz_256:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: kmovb (%rdi), %k1
|
|
; DISABLE-NEXT: vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %ymm2 # 32-byte Reload
|
|
; DISABLE-NEXT: vrangepd $88, %ymm2, %ymm0, %ymm1 {%k1} {z}
|
|
; DISABLE-NEXT: vaddpd %ymm2, %ymm0, %ymm0
|
|
; DISABLE-NEXT: vaddpd %ymm0, %ymm1, %ymm0
|
|
; DISABLE-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}"()
|
|
%mask = load i8, i8* %pmask
|
|
%2 = call <4 x double> @llvm.x86.avx512.mask.range.pd.256(<4 x double> %a0, <4 x double> %a1, i32 88, <4 x double> undef, i8 %mask)
|
|
%3 = fadd <4 x double> %a0, %a1
|
|
%res = fadd <4 x double> %2, %3
|
|
ret <4 x double> %res
|
|
}
|
|
|
|
declare <4 x double> @llvm.x86.avx512.mask.range.pd.256(<4 x double>, <4 x double>, i32, <4 x double>, i8) nounwind readnone
|
|
|
|
define <8 x double> @rangepd_512(<8 x double> %a0, <8 x double> %a1) {
|
|
; ENABLE-LABEL: rangepd_512:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %zmm2 # 64-byte Reload
|
|
; ENABLE-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
|
; ENABLE-NEXT: vrangepd $88, %zmm2, %zmm0, %zmm1
|
|
; ENABLE-NEXT: vaddpd %zmm2, %zmm0, %zmm0
|
|
; ENABLE-NEXT: vaddpd %zmm0, %zmm1, %zmm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangepd_512:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %zmm2 # 64-byte Reload
|
|
; DISABLE-NEXT: vrangepd $88, %zmm2, %zmm0, %zmm1
|
|
; DISABLE-NEXT: vaddpd %zmm2, %zmm0, %zmm0
|
|
; DISABLE-NEXT: vaddpd %zmm0, %zmm1, %zmm0
|
|
; DISABLE-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.mask.range.pd.512(<8 x double> %a0, <8 x double> %a1, i32 88, <8 x double> undef, i8 -1, i32 4)
|
|
%3 = fadd <8 x double> %a0, %a1
|
|
%res = fadd <8 x double> %2, %3
|
|
ret <8 x double> %res
|
|
}
|
|
|
|
define <8 x double> @rangepd_mem_512(<8 x double> %a0, <8 x double>* %p1) {
|
|
; ENABLE-LABEL: rangepd_mem_512:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %zmm1 # 64-byte Reload
|
|
; ENABLE-NEXT: vpxor %xmm0, %xmm0, %xmm0
|
|
; ENABLE-NEXT: vrangepd $88, (%rdi), %zmm1, %zmm0
|
|
; ENABLE-NEXT: vaddpd %zmm1, %zmm0, %zmm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangepd_mem_512:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %zmm1 # 64-byte Reload
|
|
; DISABLE-NEXT: vrangepd $88, (%rdi), %zmm1, %zmm0
|
|
; DISABLE-NEXT: vaddpd %zmm1, %zmm0, %zmm0
|
|
; DISABLE-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}"()
|
|
%a1 = load <8 x double>, <8 x double>* %p1, align 64
|
|
%2 = call <8 x double> @llvm.x86.avx512.mask.range.pd.512(<8 x double> %a0, <8 x double> %a1, i32 88, <8 x double> undef, i8 -1, i32 4)
|
|
%res = fadd <8 x double> %2, %a0
|
|
ret <8 x double> %res
|
|
}
|
|
|
|
define <8 x double> @rangepd_broadcast_512(<8 x double> %a0, double* %p1) {
|
|
; ENABLE-LABEL: rangepd_broadcast_512:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %zmm1 # 64-byte Reload
|
|
; ENABLE-NEXT: vpxor %xmm0, %xmm0, %xmm0
|
|
; ENABLE-NEXT: vrangepd $88, (%rdi){1to8}, %zmm1, %zmm0
|
|
; ENABLE-NEXT: vaddpd %zmm1, %zmm0, %zmm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangepd_broadcast_512:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %zmm1 # 64-byte Reload
|
|
; DISABLE-NEXT: vrangepd $88, (%rdi){1to8}, %zmm1, %zmm0
|
|
; DISABLE-NEXT: vaddpd %zmm1, %zmm0, %zmm0
|
|
; DISABLE-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}"()
|
|
%v1 = load double, double* %p1, align 4
|
|
%t0 = insertelement <8 x double> undef, double %v1, i64 0
|
|
%a1 = shufflevector <8 x double> %t0, <8 x double> undef, <8 x i32> zeroinitializer
|
|
%2 = call <8 x double> @llvm.x86.avx512.mask.range.pd.512(<8 x double> %a0, <8 x double> %a1, i32 88, <8 x double> undef, i8 -1, i32 4)
|
|
%res = fadd <8 x double> %2, %a0
|
|
ret <8 x double> %res
|
|
}
|
|
|
|
define <8 x double> @rangepd_maskz_512(<8 x double> %a0, <8 x double> %a1, i8* %pmask) {
|
|
; ENABLE-LABEL: rangepd_maskz_512:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: kmovb (%rdi), %k1
|
|
; ENABLE-NEXT: vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %zmm2 # 64-byte Reload
|
|
; ENABLE-NEXT: vpxor %xmm1, %xmm1, %xmm1
|
|
; ENABLE-NEXT: vrangepd $88, %zmm2, %zmm0, %zmm1 {%k1} {z}
|
|
; ENABLE-NEXT: vaddpd %zmm2, %zmm0, %zmm0
|
|
; ENABLE-NEXT: vaddpd %zmm0, %zmm1, %zmm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangepd_maskz_512:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: kmovb (%rdi), %k1
|
|
; DISABLE-NEXT: vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %zmm2 # 64-byte Reload
|
|
; DISABLE-NEXT: vrangepd $88, %zmm2, %zmm0, %zmm1 {%k1} {z}
|
|
; DISABLE-NEXT: vaddpd %zmm2, %zmm0, %zmm0
|
|
; DISABLE-NEXT: vaddpd %zmm0, %zmm1, %zmm0
|
|
; DISABLE-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}"()
|
|
%mask = load i8, i8* %pmask
|
|
%2 = call <8 x double> @llvm.x86.avx512.mask.range.pd.512(<8 x double> %a0, <8 x double> %a1, i32 88, <8 x double> undef, i8 %mask, i32 4)
|
|
%3 = fadd <8 x double> %a0, %a1
|
|
%res = fadd <8 x double> %2, %3
|
|
ret <8 x double> %res
|
|
}
|
|
|
|
declare <8 x double> @llvm.x86.avx512.mask.range.pd.512(<8 x double>, <8 x double>, i32, <8 x double>, i8, i32) nounwind readnone
|
|
|
|
define <4 x float> @rangess(<4 x float> %a0, <4 x float> %a1) {
|
|
; ENABLE-LABEL: rangess:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
|
; ENABLE-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
|
; ENABLE-NEXT: vrangess $4, %xmm2, %xmm0, %xmm1
|
|
; ENABLE-NEXT: vaddps %xmm0, %xmm2, %xmm0
|
|
; ENABLE-NEXT: vaddps %xmm0, %xmm1, %xmm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangess:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
|
; DISABLE-NEXT: vrangess $4, %xmm2, %xmm0, %xmm1
|
|
; DISABLE-NEXT: vaddps %xmm0, %xmm2, %xmm0
|
|
; DISABLE-NEXT: vaddps %xmm0, %xmm1, %xmm0
|
|
; DISABLE-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.avx512.mask.range.ss(<4 x float> %a0, <4 x float> %a1, <4 x float> undef, i8 -1, i32 4, i32 4)
|
|
%3 = fadd <4 x float> %a1, %a0
|
|
%res = fadd <4 x float> %2, %3
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <4 x float> @rangess_mem(<4 x float> %a0, <4 x float>* %p1) {
|
|
; ENABLE-LABEL: rangess_mem:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
|
; ENABLE-NEXT: vrangess $4, (%rdi), %xmm0, %xmm1
|
|
; ENABLE-NEXT: vaddps %xmm0, %xmm1, %xmm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangess_mem:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: vrangess $4, (%rdi), %xmm0, %xmm1
|
|
; DISABLE-NEXT: vaddps %xmm0, %xmm1, %xmm0
|
|
; DISABLE-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}"()
|
|
%a1 = load <4 x float>, <4 x float>* %p1, align 64
|
|
%2 = call <4 x float> @llvm.x86.avx512.mask.range.ss(<4 x float> %a0, <4 x float> %a1, <4 x float> undef, i8 -1, i32 4, i32 4)
|
|
%res = fadd <4 x float> %2, %a0
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <4 x float> @rangess_maskz(<4 x float> %a0, <4 x float> %a1, i8* %pmask) {
|
|
; ENABLE-LABEL: rangess_maskz:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: kmovb (%rdi), %k1
|
|
; ENABLE-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
|
; ENABLE-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
|
; ENABLE-NEXT: vrangess $4, %xmm2, %xmm0, %xmm1 {%k1} {z}
|
|
; ENABLE-NEXT: vaddps %xmm2, %xmm0, %xmm0
|
|
; ENABLE-NEXT: vaddps %xmm0, %xmm1, %xmm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangess_maskz:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: kmovb (%rdi), %k1
|
|
; DISABLE-NEXT: vmovaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
|
; DISABLE-NEXT: vrangess $4, %xmm2, %xmm0, %xmm1 {%k1} {z}
|
|
; DISABLE-NEXT: vaddps %xmm2, %xmm0, %xmm0
|
|
; DISABLE-NEXT: vaddps %xmm0, %xmm1, %xmm0
|
|
; DISABLE-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}"()
|
|
%mask = load i8, i8* %pmask
|
|
%2 = call <4 x float> @llvm.x86.avx512.mask.range.ss(<4 x float> %a0, <4 x float> %a1, <4 x float> undef, i8 %mask, i32 4, i32 4)
|
|
%3 = fadd <4 x float> %a0, %a1
|
|
%res = fadd <4 x float> %2, %3
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
declare <4 x float> @llvm.x86.avx512.mask.range.ss(<4 x float>, <4 x float>, <4 x float>, i8, i32, i32)
|
|
|
|
define <2 x double> @rangesd(<2 x double> %a0, <2 x double> %a1) {
|
|
; ENABLE-LABEL: rangesd:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: vmovapd {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
|
; ENABLE-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
|
; ENABLE-NEXT: vrangesd $4, %xmm2, %xmm0, %xmm1
|
|
; ENABLE-NEXT: vaddpd %xmm2, %xmm0, %xmm0
|
|
; ENABLE-NEXT: vaddpd %xmm0, %xmm1, %xmm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangesd:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: vmovapd {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
|
; DISABLE-NEXT: vrangesd $4, %xmm2, %xmm0, %xmm1
|
|
; DISABLE-NEXT: vaddpd %xmm2, %xmm0, %xmm0
|
|
; DISABLE-NEXT: vaddpd %xmm0, %xmm1, %xmm0
|
|
; DISABLE-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 <2 x double> @llvm.x86.avx512.mask.range.sd(<2 x double> %a0, <2 x double> %a1, <2 x double> undef, i8 -1, i32 4, i32 4)
|
|
%3 = fadd <2 x double> %a0, %a1
|
|
%res = fadd <2 x double> %2, %3
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
define <2 x double> @rangesd_mem(<2 x double> %a0, <2 x double>* %p1) {
|
|
; ENABLE-LABEL: rangesd_mem:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: vmovapd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
|
; ENABLE-NEXT: vxorps %xmm0, %xmm0, %xmm0
|
|
; ENABLE-NEXT: vrangesd $4, (%rdi), %xmm1, %xmm0
|
|
; ENABLE-NEXT: vaddpd %xmm1, %xmm0, %xmm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangesd_mem:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: vmovapd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
|
|
; DISABLE-NEXT: vrangesd $4, (%rdi), %xmm1, %xmm0
|
|
; DISABLE-NEXT: vaddpd %xmm1, %xmm0, %xmm0
|
|
; DISABLE-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}"()
|
|
%a1 = load <2 x double>, <2 x double>* %p1, align 64
|
|
%2 = call <2 x double> @llvm.x86.avx512.mask.range.sd(<2 x double> %a0, <2 x double> %a1, <2 x double> undef, i8 -1, i32 4, i32 4)
|
|
%res = fadd <2 x double> %2, %a0
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
define <2 x double> @rangesd_maskz(<2 x double> %a0, <2 x double> %a1, i8* %pmask) {
|
|
; ENABLE-LABEL: rangesd_maskz:
|
|
; ENABLE: # %bb.0:
|
|
; ENABLE-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; ENABLE-NEXT: #APP
|
|
; ENABLE-NEXT: nop
|
|
; ENABLE-NEXT: #NO_APP
|
|
; ENABLE-NEXT: kmovb (%rdi), %k1
|
|
; ENABLE-NEXT: vmovapd {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
|
; ENABLE-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
|
; ENABLE-NEXT: vrangesd $4, %xmm2, %xmm0, %xmm1 {%k1} {z}
|
|
; ENABLE-NEXT: vaddpd %xmm2, %xmm0, %xmm0
|
|
; ENABLE-NEXT: vaddpd %xmm0, %xmm1, %xmm0
|
|
; ENABLE-NEXT: retq
|
|
;
|
|
; DISABLE-LABEL: rangesd_maskz:
|
|
; DISABLE: # %bb.0:
|
|
; DISABLE-NEXT: vmovaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; DISABLE-NEXT: #APP
|
|
; DISABLE-NEXT: nop
|
|
; DISABLE-NEXT: #NO_APP
|
|
; DISABLE-NEXT: kmovb (%rdi), %k1
|
|
; DISABLE-NEXT: vmovapd {{[-0-9]+}}(%r{{[sb]}}p), %xmm2 # 16-byte Reload
|
|
; DISABLE-NEXT: vrangesd $4, %xmm2, %xmm0, %xmm1 {%k1} {z}
|
|
; DISABLE-NEXT: vaddpd %xmm2, %xmm0, %xmm0
|
|
; DISABLE-NEXT: vaddpd %xmm0, %xmm1, %xmm0
|
|
; DISABLE-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}"()
|
|
%mask = load i8, i8* %pmask
|
|
%2 = call <2 x double> @llvm.x86.avx512.mask.range.sd(<2 x double> %a0, <2 x double> %a1, <2 x double> undef, i8 %mask, i32 4, i32 4)
|
|
%3 = fadd <2 x double> %a0, %a1
|
|
%res = fadd <2 x double> %2, %3
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
declare <2 x double> @llvm.x86.avx512.mask.range.sd(<2 x double>, <2 x double>, <2 x double>, i8, i32, i32)
|