derek.holloway
7502bf64a4
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
102 lines
4.3 KiB
LLVM
102 lines
4.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=knl | FileCheck %s
|
|
|
|
declare <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float>, <4 x float>, <4 x float>, i8, i32)
|
|
declare <4 x float> @llvm.x86.avx512.maskz.vfmadd.ss(<4 x float>, <4 x float>, <4 x float>, i8, i32)
|
|
|
|
define <4 x float>@test_var_mask(<4 x float> %v0, <4 x float> %v1, <4 x float> %v2, i8 %mask) {
|
|
; CHECK-LABEL: test_var_mask:
|
|
; CHECK: ## %bb.0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vfmadd213ss {{.*#+}} xmm0 {%k1} = (xmm1 * xmm0) + xmm2
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %v0,<4 x float> %v1, <4 x float> %v2, i8 %mask, i32 4)
|
|
ret < 4 x float> %res
|
|
}
|
|
|
|
define <4 x float>@test_var_maskz(<4 x float> %v0, <4 x float> %v1, <4 x float> %v2, i8 %mask) {
|
|
; CHECK-LABEL: test_var_maskz:
|
|
; CHECK: ## %bb.0:
|
|
; CHECK-NEXT: kmovw %edi, %k1
|
|
; CHECK-NEXT: vfmadd213ss {{.*#+}} xmm0 {%k1} {z} = (xmm1 * xmm0) + xmm2
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.maskz.vfmadd.ss(<4 x float> %v0,<4 x float> %v1, <4 x float> %v2, i8 %mask, i32 4)
|
|
ret < 4 x float> %res
|
|
}
|
|
|
|
; just return %xmm0 here.
|
|
define <4 x float>@test_const0_mask(<4 x float> %v0, <4 x float> %v1, <4 x float> %v2) {
|
|
; CHECK-LABEL: test_const0_mask:
|
|
; CHECK: ## %bb.0:
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %v0,<4 x float> %v1, <4 x float> %v2, i8 0, i32 4)
|
|
ret < 4 x float> %res
|
|
}
|
|
|
|
; zero the lower element of xmm0 and return it.
|
|
define <4 x float>@test_const0_maskz(<4 x float> %v0, <4 x float> %v1, <4 x float> %v2) {
|
|
; CHECK-LABEL: test_const0_maskz:
|
|
; CHECK: ## %bb.0:
|
|
; CHECK-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
|
; CHECK-NEXT: vblendps {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.maskz.vfmadd.ss(<4 x float> %v0,<4 x float> %v1, <4 x float> %v2, i8 0, i32 4)
|
|
ret < 4 x float> %res
|
|
}
|
|
|
|
; just return %xmm0 here.
|
|
define <4 x float>@test_const2_mask(<4 x float> %v0, <4 x float> %v1, <4 x float> %v2) {
|
|
; CHECK-LABEL: test_const2_mask:
|
|
; CHECK: ## %bb.0:
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %v0,<4 x float> %v1, <4 x float> %v2, i8 2, i32 4)
|
|
ret < 4 x float> %res
|
|
}
|
|
|
|
; zero the lower element of xmm0 and return it.
|
|
define <4 x float>@test_const2_maskz(<4 x float> %v0, <4 x float> %v1, <4 x float> %v2) {
|
|
; CHECK-LABEL: test_const2_maskz:
|
|
; CHECK: ## %bb.0:
|
|
; CHECK-NEXT: vxorps %xmm1, %xmm1, %xmm1
|
|
; CHECK-NEXT: vblendps {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.maskz.vfmadd.ss(<4 x float> %v0,<4 x float> %v1, <4 x float> %v2, i8 2, i32 4)
|
|
ret < 4 x float> %res
|
|
}
|
|
|
|
define <4 x float>@test_const_allone_mask(<4 x float> %v0, <4 x float> %v1, <4 x float> %v2) {
|
|
; CHECK-LABEL: test_const_allone_mask:
|
|
; CHECK: ## %bb.0:
|
|
; CHECK-NEXT: vfmadd213ss {{.*#+}} xmm0 = (xmm1 * xmm0) + xmm2
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %v0,<4 x float> %v1, <4 x float> %v2, i8 -1, i32 4)
|
|
ret < 4 x float> %res
|
|
}
|
|
|
|
define <4 x float>@test_const_allone_maskz(<4 x float> %v0, <4 x float> %v1, <4 x float> %v2) {
|
|
; CHECK-LABEL: test_const_allone_maskz:
|
|
; CHECK: ## %bb.0:
|
|
; CHECK-NEXT: vfmadd213ss {{.*#+}} xmm0 = (xmm1 * xmm0) + xmm2
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.maskz.vfmadd.ss(<4 x float> %v0,<4 x float> %v1, <4 x float> %v2, i8 -1, i32 4)
|
|
ret < 4 x float> %res
|
|
}
|
|
|
|
define <4 x float>@test_const_3_mask(<4 x float> %v0, <4 x float> %v1, <4 x float> %v2) {
|
|
; CHECK-LABEL: test_const_3_mask:
|
|
; CHECK: ## %bb.0:
|
|
; CHECK-NEXT: vfmadd213ss {{.*#+}} xmm0 = (xmm1 * xmm0) + xmm2
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %v0,<4 x float> %v1, <4 x float> %v2, i8 3, i32 4)
|
|
ret < 4 x float> %res
|
|
}
|
|
|
|
define <4 x float>@test_const_3_maskz(<4 x float> %v0, <4 x float> %v1, <4 x float> %v2) {
|
|
; CHECK-LABEL: test_const_3_maskz:
|
|
; CHECK: ## %bb.0:
|
|
; CHECK-NEXT: vfmadd213ss {{.*#+}} xmm0 = (xmm1 * xmm0) + xmm2
|
|
; CHECK-NEXT: retq
|
|
%res = call <4 x float> @llvm.x86.avx512.maskz.vfmadd.ss(<4 x float> %v0,<4 x float> %v1, <4 x float> %v2, i8 3, i32 4)
|
|
ret < 4 x float> %res
|
|
}
|