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
75 lines
3.7 KiB
LLVM
75 lines
3.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve2p1 -mattr=+sve-b16b16 -mattr=+use-experimental-zeroing-pseudos -verify-machineinstrs < %s \
|
|
; RUN: | FileCheck %s
|
|
|
|
define <vscale x 8 x bfloat> @bfmax_pred(<vscale x 8 x i1> %pg, <vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b){
|
|
; CHECK-LABEL: bfmax_pred:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: bfmax z0.h, p0/m, z0.h, z1.h
|
|
; CHECK-NEXT: ret
|
|
%res = call <vscale x 8 x bfloat> @llvm.aarch64.sve.fmax.nxv8bf16(<vscale x 8 x i1> %pg, <vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b)
|
|
ret <vscale x 8 x bfloat> %res
|
|
}
|
|
|
|
define <vscale x 8 x bfloat> @bfmax(<vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b){
|
|
; CHECK-LABEL: bfmax:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.h
|
|
; CHECK-NEXT: bfmax z0.h, p0/m, z0.h, z1.h
|
|
; CHECK-NEXT: ret
|
|
%elt = call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
|
|
%res = call <vscale x 8 x bfloat> @llvm.aarch64.sve.fmax.nxv8bf16(<vscale x 8 x i1> %elt, <vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b)
|
|
ret <vscale x 8 x bfloat> %res
|
|
}
|
|
|
|
define <vscale x 8 x bfloat> @bfmax_zeroing(<vscale x 8 x i1> %pg, <vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b) {
|
|
; CHECK-LABEL: bfmax_zeroing:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: movprfx z0.h, p0/z, z0.h
|
|
; CHECK-NEXT: bfmax z0.h, p0/m, z0.h, z1.h
|
|
; CHECK-NEXT: ret
|
|
%a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> zeroinitializer
|
|
%out = call <vscale x 8 x bfloat> @llvm.aarch64.sve.fmax.nxv8bf16(<vscale x 8 x i1> %pg,
|
|
<vscale x 8 x bfloat> %a_z,
|
|
<vscale x 8 x bfloat> %b)
|
|
ret <vscale x 8 x bfloat> %out
|
|
}
|
|
|
|
define <vscale x 8 x bfloat> @bfmax_u_pred(<vscale x 8 x i1> %pg, <vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b){
|
|
; CHECK-LABEL: bfmax_u_pred:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: bfmax z0.h, p0/m, z0.h, z1.h
|
|
; CHECK-NEXT: ret
|
|
%res = call <vscale x 8 x bfloat> @llvm.aarch64.sve.fmax.u.nxv8bf16(<vscale x 8 x i1> %pg, <vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b)
|
|
ret <vscale x 8 x bfloat> %res
|
|
}
|
|
|
|
define <vscale x 8 x bfloat> @bfmax_u(<vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b){
|
|
; CHECK-LABEL: bfmax_u:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.h
|
|
; CHECK-NEXT: bfmax z0.h, p0/m, z0.h, z1.h
|
|
; CHECK-NEXT: ret
|
|
%elt = call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
|
|
%res = call <vscale x 8 x bfloat> @llvm.aarch64.sve.fmax.u.nxv8bf16(<vscale x 8 x i1> %elt, <vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b)
|
|
ret <vscale x 8 x bfloat> %res
|
|
}
|
|
|
|
define <vscale x 8 x bfloat> @bfmax_u_zeroing(<vscale x 8 x i1> %pg, <vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b) {
|
|
; CHECK-LABEL: bfmax_u_zeroing:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: movi v2.2d, #0000000000000000
|
|
; CHECK-NEXT: sel z0.h, p0, z0.h, z2.h
|
|
; CHECK-NEXT: bfmax z0.h, p0/m, z0.h, z1.h
|
|
; CHECK-NEXT: ret
|
|
%a_z = select <vscale x 8 x i1> %pg, <vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> zeroinitializer
|
|
%out = call <vscale x 8 x bfloat> @llvm.aarch64.sve.fmax.u.nxv8bf16(<vscale x 8 x i1> %pg,
|
|
<vscale x 8 x bfloat> %a_z,
|
|
<vscale x 8 x bfloat> %b)
|
|
ret <vscale x 8 x bfloat> %out
|
|
}
|
|
|
|
declare <vscale x 8 x bfloat> @llvm.aarch64.sve.fmax.nxv8bf16(<vscale x 8 x i1>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>)
|
|
declare <vscale x 8 x bfloat> @llvm.aarch64.sve.fmax.u.nxv8bf16(<vscale x 8 x i1>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>)
|
|
declare <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 immarg)
|