CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
120 lines
6.2 KiB
LLVM
120 lines
6.2 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=+avxifma < %s | FileCheck %s
|
|
|
|
declare <2 x i64> @llvm.x86.avx512.vpmadd52h.uq.128(<2 x i64>, <2 x i64>, <2 x i64>)
|
|
declare <4 x i64> @llvm.x86.avx512.vpmadd52h.uq.256(<4 x i64>, <4 x i64>, <4 x i64>)
|
|
declare <2 x i64> @llvm.x86.avx512.vpmadd52l.uq.128(<2 x i64>, <2 x i64>, <2 x i64>)
|
|
declare <4 x i64> @llvm.x86.avx512.vpmadd52l.uq.256(<4 x i64>, <4 x i64>, <4 x i64>)
|
|
|
|
define <2 x i64> @stack_fold_vpmadd52huq(<2 x i64> %a0, <2 x i64> %a1, <2 x i64> %a2) {
|
|
; CHECK-LABEL: stack_fold_vpmadd52huq:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: {vex} vpmadd52huq {{[-0-9]+}}(%r{{[sb]}}p), %xmm1, %xmm0 # 16-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},~{flags}"()
|
|
%2 = call <2 x i64> @llvm.x86.avx512.vpmadd52h.uq.128(<2 x i64> %a0, <2 x i64> %a1, <2 x i64> %a2)
|
|
ret <2 x i64> %2
|
|
}
|
|
|
|
define <2 x i64> @stack_fold_vpmadd52huq_commuted(<2 x i64> %a0, <2 x i64> %a1, <2 x i64> %a2) {
|
|
; CHECK-LABEL: stack_fold_vpmadd52huq_commuted:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: {vex} vpmadd52huq {{[-0-9]+}}(%r{{[sb]}}p), %xmm1, %xmm0 # 16-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},~{flags}"()
|
|
%2 = call <2 x i64> @llvm.x86.avx512.vpmadd52h.uq.128(<2 x i64> %a0, <2 x i64> %a2, <2 x i64> %a1)
|
|
ret <2 x i64> %2
|
|
}
|
|
|
|
define <4 x i64> @stack_fold_vpmadd52huq_256(<4 x i64> %a0, <4 x i64> %a1, <4 x i64> %a2) {
|
|
; CHECK-LABEL: stack_fold_vpmadd52huq_256:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %ymm2, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: {vex} vpmadd52huq {{[-0-9]+}}(%r{{[sb]}}p), %ymm1, %ymm0 # 32-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},~{flags}"()
|
|
%2 = call <4 x i64> @llvm.x86.avx512.vpmadd52h.uq.256(<4 x i64> %a0, <4 x i64> %a1, <4 x i64> %a2)
|
|
ret <4 x i64> %2
|
|
}
|
|
|
|
define <4 x i64> @stack_fold_vpmadd52huq_256_commuted(<4 x i64> %a0, <4 x i64> %a1, <4 x i64> %a2) {
|
|
; CHECK-LABEL: stack_fold_vpmadd52huq_256_commuted:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %ymm2, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: {vex} vpmadd52huq {{[-0-9]+}}(%r{{[sb]}}p), %ymm1, %ymm0 # 32-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},~{flags}"()
|
|
%2 = call <4 x i64> @llvm.x86.avx512.vpmadd52h.uq.256(<4 x i64> %a0, <4 x i64> %a2, <4 x i64> %a1)
|
|
ret <4 x i64> %2
|
|
}
|
|
|
|
define <2 x i64> @stack_fold_vpmadd52luq(<2 x i64> %a0, <2 x i64> %a1, <2 x i64> %a2) {
|
|
; CHECK-LABEL: stack_fold_vpmadd52luq:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: {vex} vpmadd52luq {{[-0-9]+}}(%r{{[sb]}}p), %xmm1, %xmm0 # 16-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},~{flags}"()
|
|
%2 = call <2 x i64> @llvm.x86.avx512.vpmadd52l.uq.128(<2 x i64> %a0, <2 x i64> %a1, <2 x i64> %a2)
|
|
ret <2 x i64> %2
|
|
}
|
|
|
|
define <2 x i64> @stack_fold_vpmadd52luq_commuted(<2 x i64> %a0, <2 x i64> %a1, <2 x i64> %a2) {
|
|
; CHECK-LABEL: stack_fold_vpmadd52luq_commuted:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: {vex} vpmadd52luq {{[-0-9]+}}(%r{{[sb]}}p), %xmm1, %xmm0 # 16-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},~{flags}"()
|
|
%2 = call <2 x i64> @llvm.x86.avx512.vpmadd52l.uq.128(<2 x i64> %a0, <2 x i64> %a2, <2 x i64> %a1)
|
|
ret <2 x i64> %2
|
|
}
|
|
|
|
define <4 x i64> @stack_fold_vpmadd52luq_256(<4 x i64> %a0, <4 x i64> %a1, <4 x i64> %a2) {
|
|
; CHECK-LABEL: stack_fold_vpmadd52luq_256:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %ymm2, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: {vex} vpmadd52luq {{[-0-9]+}}(%r{{[sb]}}p), %ymm1, %ymm0 # 32-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},~{flags}"()
|
|
%2 = call <4 x i64> @llvm.x86.avx512.vpmadd52l.uq.256(<4 x i64> %a0, <4 x i64> %a1, <4 x i64> %a2)
|
|
ret <4 x i64> %2
|
|
}
|
|
|
|
define <4 x i64> @stack_fold_vpmadd52luq_256_commuted(<4 x i64> %a0, <4 x i64> %a1, <4 x i64> %a2) {
|
|
; CHECK-LABEL: stack_fold_vpmadd52luq_256_commuted:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmovups %ymm2, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
|
|
; CHECK-NEXT: #APP
|
|
; CHECK-NEXT: nop
|
|
; CHECK-NEXT: #NO_APP
|
|
; CHECK-NEXT: {vex} vpmadd52luq {{[-0-9]+}}(%r{{[sb]}}p), %ymm1, %ymm0 # 32-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},~{flags}"()
|
|
%2 = call <4 x i64> @llvm.x86.avx512.vpmadd52l.uq.256(<4 x i64> %a0, <4 x i64> %a2, <4 x i64> %a1)
|
|
ret <4 x i64> %2
|
|
}
|