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
38 lines
2.3 KiB
LLVM
38 lines
2.3 KiB
LLVM
; RUN: not llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx512f -stop-after=finalize-isel > %t 2> %t.err
|
|
; RUN: FileCheck < %t %s
|
|
; RUN: FileCheck --check-prefix=CHECK-STDERR < %t.err %s
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx512bf16,avx512fp16 -stop-after=finalize-isel | FileCheck --check-prefixes=CHECK,FP16 %s
|
|
|
|
; CHECK-LABEL: name: mask_Yk_i8
|
|
; CHECK: %[[REG1:.*]]:vr512_0_15 = COPY %1
|
|
; CHECK: %[[REG2:.*]]:vr512_0_15 = COPY %2
|
|
; CHECK: INLINEASM &"vpaddq\09$3, $2, $0 {$1}", attdialect, {{.*}}, def %{{.*}}, {{.*}}, %{{.*}}, {{.*}}, %[[REG1]], {{.*}}, %[[REG2]], clobber, implicit-def early-clobber $df, clobber, implicit-def early-clobber $fpsw, clobber, implicit-def early-clobber $eflags
|
|
|
|
define <8 x i64> @mask_Yk_i8(i8 signext %msk, <8 x i64> %x, <8 x i64> %y) {
|
|
entry:
|
|
%0 = tail call <8 x i64> asm "vpaddq\09$3, $2, $0 {$1}", "=x,^Yk,x,x,~{dirflag},~{fpsr},~{flags}"(i8 %msk, <8 x i64> %x, <8 x i64> %y)
|
|
ret <8 x i64> %0
|
|
}
|
|
|
|
; FP16-LABEL: name: mask_Yk_f16
|
|
; FP16: %[[REG1:.*]]:vr512_0_15 = COPY %1
|
|
; FP16: %[[REG2:.*]]:vr512_0_15 = COPY %2
|
|
; FP16: INLINEASM &"vaddph\09$3, $2, $0 {$1}", attdialect, {{.*}}, def %{{.*}}, {{.*}}, %{{.*}}, {{.*}}, %[[REG1]], {{.*}}, %[[REG2]], clobber, implicit-def early-clobber $df, clobber, implicit-def early-clobber $fpsw, clobber, implicit-def early-clobber $eflags
|
|
; CHECK-STDERR: could not allocate output register for constraint 'x'
|
|
define <32 x half> @mask_Yk_f16(i8 signext %msk, <32 x half> %x, <32 x half> %y) {
|
|
entry:
|
|
%0 = tail call <32 x half> asm "vaddph\09$3, $2, $0 {$1}", "=x,^Yk,x,x,~{dirflag},~{fpsr},~{flags}"(i8 %msk, <32 x half> %x, <32 x half> %y)
|
|
ret <32 x half> %0
|
|
}
|
|
|
|
; FP16-LABEL: name: mask_Yk_bf16
|
|
; FP16: %[[REG1:.*]]:vr512_0_15 = COPY %1
|
|
; FP16: %[[REG2:.*]]:vr512_0_15 = COPY %2
|
|
; FP16: INLINEASM &"vaddph\09$3, $2, $0 {$1}", attdialect, {{.*}}, def %{{.*}}, {{.*}}, %{{.*}}, {{.*}}, %[[REG1]], {{.*}}, %[[REG2]], clobber, implicit-def early-clobber $df, clobber, implicit-def early-clobber $fpsw, clobber, implicit-def early-clobber $eflags
|
|
; CHECK-STDERR: could not allocate output register for constraint 'x'
|
|
define <32 x bfloat> @mask_Yk_bf16(i8 signext %msk, <32 x bfloat> %x, <32 x bfloat> %y) {
|
|
entry:
|
|
%0 = tail call <32 x bfloat> asm "vaddph\09$3, $2, $0 {$1}", "=x,^Yk,x,x,~{dirflag},~{fpsr},~{flags}"(i8 %msk, <32 x bfloat> %x, <32 x bfloat> %y)
|
|
ret <32 x bfloat> %0
|
|
}
|