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
62 lines
3.3 KiB
LLVM
62 lines
3.3 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,+avx10.2, \
|
|
; RUN: -mattr=+amx-avx512 -verify-machineinstrs | FileCheck %s
|
|
|
|
define void @test_amx(i8* %pointer, i8* %base, i32 %index, 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: ldtilecfg -{{[0-9]+}}(%rsp)
|
|
; CHECK-NEXT: movw $8, %ax
|
|
; CHECK-NEXT: tileloadd (%rsi,%rcx), %tmm0
|
|
; CHECK-NEXT: tcvtrowd2ps %edx, %tmm0, %zmm0
|
|
; CHECK-NEXT: tcvtrowd2ps $16, %tmm0, %zmm0
|
|
; CHECK-NEXT: tcvtrowps2bf16h %edx, %tmm0, %zmm0
|
|
; CHECK-NEXT: tcvtrowps2bf16h $16, %tmm0, %zmm0
|
|
; CHECK-NEXT: tcvtrowps2bf16l %edx, %tmm0, %zmm0
|
|
; CHECK-NEXT: tcvtrowps2bf16l $16, %tmm0, %zmm0
|
|
; CHECK-NEXT: tcvtrowps2phh %edx, %tmm0, %zmm0
|
|
; CHECK-NEXT: tcvtrowps2phh $16, %tmm0, %zmm0
|
|
; CHECK-NEXT: tcvtrowps2phl %edx, %tmm0, %zmm0
|
|
; CHECK-NEXT: tcvtrowps2phl $16, %tmm0, %zmm0
|
|
; CHECK-NEXT: tilemovrow %edx, %tmm0, %zmm0
|
|
; CHECK-NEXT: tilemovrow $16, %tmm0, %zmm0
|
|
; CHECK-NEXT: tilestored %tmm0, (%rdi,%rcx)
|
|
; CHECK-NEXT: tilerelease
|
|
; CHECK-NEXT: vzeroupper
|
|
; CHECK-NEXT: retq
|
|
|
|
%a = call x86_amx @llvm.x86.tileloadd64.internal(i16 8, i16 8, i8* %base, i64 %stride)
|
|
call <16 x float> @llvm.x86.tcvtrowd2ps.internal(i16 8, i16 8, x86_amx %a, i32 %index)
|
|
call <16 x float> @llvm.x86.tcvtrowd2ps.internal(i16 8, i16 8, x86_amx %a, i32 16)
|
|
call <32 x bfloat> @llvm.x86.tcvtrowps2bf16h.internal(i16 8, i16 8, x86_amx %a, i32 %index)
|
|
call <32 x bfloat> @llvm.x86.tcvtrowps2bf16h.internal(i16 8, i16 8, x86_amx %a, i32 16)
|
|
call <32 x bfloat> @llvm.x86.tcvtrowps2bf16l.internal(i16 8, i16 8, x86_amx %a, i32 %index)
|
|
call <32 x bfloat> @llvm.x86.tcvtrowps2bf16l.internal(i16 8, i16 8, x86_amx %a, i32 16)
|
|
call <32 x half> @llvm.x86.tcvtrowps2phh.internal(i16 8, i16 8, x86_amx %a, i32 %index)
|
|
call <32 x half> @llvm.x86.tcvtrowps2phh.internal(i16 8, i16 8, x86_amx %a, i32 16)
|
|
call <32 x half> @llvm.x86.tcvtrowps2phl.internal(i16 8, i16 8, x86_amx %a, i32 %index)
|
|
call <32 x half> @llvm.x86.tcvtrowps2phl.internal(i16 8, i16 8, x86_amx %a, i32 16)
|
|
call <16 x i32> @llvm.x86.tilemovrow.internal(i16 8, i16 8, x86_amx %a, i32 %index)
|
|
call <16 x i32> @llvm.x86.tilemovrow.internal(i16 8, i16 8, x86_amx %a, i32 16)
|
|
|
|
call void @llvm.x86.tilestored64.internal(i16 8, i16 8, i8* %pointer, i64 %stride, x86_amx %a)
|
|
ret void
|
|
}
|
|
|
|
declare x86_amx @llvm.x86.tilezero.internal(i16, i16)
|
|
declare x86_amx @llvm.x86.tileloadd64.internal(i16, i16, i8*, i64)
|
|
declare x86_amx @llvm.x86.tileloaddt164.internal(i16, i16, i8*, i64)
|
|
declare void @llvm.x86.tilestored64.internal(i16, i16, i8*, i64, x86_amx)
|
|
|
|
declare <16 x float> @llvm.x86.tcvtrowd2ps.internal(i16, i16, x86_amx, i32)
|
|
declare <32 x bfloat> @llvm.x86.tcvtrowps2bf16h.internal(i16, i16, x86_amx, i32)
|
|
declare <32 x bfloat> @llvm.x86.tcvtrowps2bf16l.internal(i16, i16, x86_amx, i32)
|
|
declare <32 x half> @llvm.x86.tcvtrowps2phh.internal(i16, i16, x86_amx, i32)
|
|
declare <32 x half> @llvm.x86.tcvtrowps2phl.internal(i16, i16, x86_amx, i32)
|
|
declare <16 x i32> @llvm.x86.tilemovrow.internal(i16, i16, x86_amx, i32)
|