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
51 lines
3.7 KiB
LLVM
51 lines
3.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
|
|
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sme2 -mattr=+sve-bfscale -force-streaming -verify-machineinstrs < %s | FileCheck %s
|
|
|
|
define { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @multi_vec_scale_single_x2_bf16(<vscale x 8 x bfloat> %zdn1, <vscale x 8 x bfloat> %zdn2, <vscale x 8 x i16> %zm) {
|
|
; CHECK-LABEL: multi_vec_scale_single_x2_bf16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: bfscale { z0.h, z1.h }, { z0.h, z1.h }, z2.h
|
|
; CHECK-NEXT: ret
|
|
%res = call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sve.fscale.single.x2.nxv8bf16(<vscale x 8 x bfloat> %zdn1, <vscale x 8 x bfloat> %zdn2, <vscale x 8 x i16> %zm)
|
|
ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } %res
|
|
}
|
|
|
|
define { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @multi_vec_scale_single_x4_bf16(<vscale x 8 x bfloat> %zdn1, <vscale x 8 x bfloat> %zdn2, <vscale x 8 x bfloat> %zdn3, <vscale x 8 x bfloat> %zdn4, <vscale x 8 x i16> %zm) {
|
|
; CHECK-LABEL: multi_vec_scale_single_x4_bf16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: bfscale { z0.h - z3.h }, { z0.h - z3.h }, z4.h
|
|
; CHECK-NEXT: ret
|
|
%res = call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sve.fscale.single.x4.nxv8bf16(<vscale x 8 x bfloat> %zdn1, <vscale x 8 x bfloat> %zdn2, <vscale x 8 x bfloat> %zdn3, <vscale x 8 x bfloat> %zdn4, <vscale x 8 x i16> %zm)
|
|
ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } %res
|
|
}
|
|
|
|
define { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @multi_vec_scale_x2_bf16(<vscale x 8 x bfloat> %zdn1, <vscale x 8 x bfloat> %zdn2, <vscale x 8 x i16> %zm1, <vscale x 8 x i16> %zm2) {
|
|
; CHECK-LABEL: multi_vec_scale_x2_bf16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: bfscale { z0.h, z1.h }, { z0.h, z1.h }, { z2.h, z3.h }
|
|
; CHECK-NEXT: ret
|
|
%res = call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sve.fscale.x2.nxv8bf16(<vscale x 8 x bfloat> %zdn1, <vscale x 8 x bfloat> %zdn2, <vscale x 8 x i16> %zm1, <vscale x 8 x i16> %zm2)
|
|
ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } %res
|
|
}
|
|
|
|
define { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @multi_vec_scale_x4_bf16(<vscale x 8 x bfloat> %zdn1, <vscale x 8 x bfloat> %zdn2, <vscale x 8 x bfloat> %zdn3, <vscale x 8 x bfloat> %zdn4, <vscale x 8 x i16> %zm1, <vscale x 8 x i16> %zm2, <vscale x 8 x i16> %zm3, <vscale x 8 x i16> %zm4) {
|
|
; CHECK-LABEL: multi_vec_scale_x4_bf16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: bfscale { z0.h - z3.h }, { z0.h - z3.h }, { z4.h - z7.h }
|
|
; CHECK-NEXT: ret
|
|
%res = call { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } @llvm.aarch64.sve.fscale.x4.nxv8bf16(<vscale x 8 x bfloat> %zdn1, <vscale x 8 x bfloat> %zdn2, <vscale x 8 x bfloat> %zdn3, <vscale x 8 x bfloat> %zdn4, <vscale x 8 x i16> %zm1, <vscale x 8 x i16> %zm2, <vscale x 8 x i16> %zm3, <vscale x 8 x i16> %zm4)
|
|
ret { <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } %res
|
|
}
|
|
|
|
define <vscale x 8 x bfloat> @bfscale_h(<vscale x 8 x i1> %pg, <vscale x 8 x bfloat> %a, <vscale x 8 x i16> %b) {
|
|
; CHECK-LABEL: bfscale_h:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: bfscale z0.h, p0/m, z0.h, z1.h
|
|
; CHECK-NEXT: ret
|
|
%out = call <vscale x 8 x bfloat> @llvm.aarch64.sve.fscale.nxv8bf16(<vscale x 8 x i1> %pg,
|
|
<vscale x 8 x bfloat> %a,
|
|
<vscale x 8 x i16> %b)
|
|
ret <vscale x 8 x bfloat> %out
|
|
}
|
|
|