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
48 lines
2.1 KiB
LLVM
48 lines
2.1 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-tile,+amx-bf16,+avx512f, \
|
|
; RUN: -mattr=+amx-complex \
|
|
; RUN: -verify-machineinstrs | FileCheck %s
|
|
|
|
define void @test_amx(ptr %pointer, ptr %base, i64 %stride) {
|
|
; CHECK-LABEL: test_amx:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vxorps %xmm0, %xmm0, %xmm0
|
|
; CHECK-NEXT: vmovups %zmm0, -{{[0-9]+}}(%rsp)
|
|
; CHECK-NEXT: movb $1, -{{[0-9]+}}(%rsp)
|
|
; CHECK-NEXT: movb $8, -{{[0-9]+}}(%rsp)
|
|
; CHECK-NEXT: movw $8, -{{[0-9]+}}(%rsp)
|
|
; CHECK-NEXT: movb $8, -{{[0-9]+}}(%rsp)
|
|
; CHECK-NEXT: movw $8, -{{[0-9]+}}(%rsp)
|
|
; CHECK-NEXT: movb $8, -{{[0-9]+}}(%rsp)
|
|
; CHECK-NEXT: movw $8, -{{[0-9]+}}(%rsp)
|
|
; CHECK-NEXT: ldtilecfg -{{[0-9]+}}(%rsp)
|
|
; CHECK-NEXT: movw $8, %ax
|
|
; CHECK-NEXT: tileloadd (%rsi,%rdx), %tmm0
|
|
; CHECK-NEXT: tilezero %tmm1
|
|
; CHECK-NEXT: tilezero %tmm2
|
|
; CHECK-NEXT: tcmmimfp16ps %tmm1, %tmm0, %tmm2
|
|
; CHECK-NEXT: tcmmrlfp16ps %tmm1, %tmm0, %tmm2
|
|
; CHECK-NEXT: tilestored %tmm2, (%rdi,%rdx)
|
|
; CHECK-NEXT: tilerelease
|
|
; CHECK-NEXT: vzeroupper
|
|
; CHECK-NEXT: retq
|
|
|
|
%a = call x86_amx @llvm.x86.tileloadd64.internal(i16 8, i16 8, ptr %base, i64 %stride)
|
|
%b = call x86_amx @llvm.x86.tilezero.internal(i16 8, i16 8)
|
|
%c = call x86_amx @llvm.x86.tilezero.internal(i16 8, i16 8)
|
|
|
|
%c1 = call x86_amx @llvm.x86.tcmmimfp16ps.internal(i16 8, i16 8, i16 8, x86_amx %c, x86_amx %a, x86_amx %b)
|
|
%c2 = call x86_amx @llvm.x86.tcmmrlfp16ps.internal(i16 8, i16 8, i16 8, x86_amx %c1, x86_amx %a, x86_amx %b)
|
|
|
|
call void @llvm.x86.tilestored64.internal(i16 8, i16 8, ptr %pointer, i64 %stride, x86_amx %c2)
|
|
ret void
|
|
}
|
|
|
|
declare x86_amx @llvm.x86.tilezero.internal(i16, i16)
|
|
declare x86_amx @llvm.x86.tileloadd64.internal(i16, i16, ptr, i64)
|
|
declare x86_amx @llvm.x86.tileloaddt164.internal(i16, i16, ptr, i64)
|
|
declare void @llvm.x86.tilestored64.internal(i16, i16, ptr, i64, x86_amx)
|
|
|
|
declare x86_amx @llvm.x86.tcmmimfp16ps.internal(i16, i16, i16, x86_amx, x86_amx, x86_amx)
|
|
declare x86_amx @llvm.x86.tcmmrlfp16ps.internal(i16, i16, i16, x86_amx, x86_amx, x86_amx)
|