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
2.3 KiB
LLVM
51 lines
2.3 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 -verify-machineinstrs | FileCheck %s
|
|
; RUN: llc < %s -O0 -mtriple=x86_64-unknown-unknown -mattr=+amx-tile -verify-machineinstrs | FileCheck %s
|
|
; RUN: llc < %s -O0 -mtriple=x86_64-unknown-unknown -mattr=+amx-tile,+egpr -verify-machineinstrs --show-mc-encoding | FileCheck %s --check-prefix=EGPR
|
|
|
|
define void @test_amx(ptr %pointer, ptr %base, i64 %stride) {
|
|
; CHECK-LABEL: test_amx:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: ldtilecfg (%rdi)
|
|
; CHECK-NEXT: sttilecfg (%rdi)
|
|
; CHECK-NEXT: tilerelease
|
|
; CHECK-NEXT: tilezero %tmm3
|
|
; CHECK-NEXT: tileloadd (%rsi,%rdx), %tmm3
|
|
; CHECK-NEXT: tileloaddt1 (%rsi,%rdx), %tmm3
|
|
; CHECK-NEXT: tilestored %tmm3, (%rsi,%rdx)
|
|
; CHECK-NEXT: retq
|
|
;
|
|
; EGPR-LABEL: test_amx:
|
|
; EGPR: # %bb.0:
|
|
; EGPR-NEXT: ldtilecfg (%rdi) # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x78,0x49,0x07]
|
|
; EGPR-NEXT: sttilecfg (%rdi) # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x49,0x07]
|
|
; EGPR-NEXT: tilerelease # encoding: [0xc4,0xe2,0x78,0x49,0xc0]
|
|
; EGPR-NEXT: tilezero %tmm3 # encoding: [0xc4,0xe2,0x7b,0x49,0xd8]
|
|
; EGPR-NEXT: tileloadd (%rsi,%rdx), %tmm3 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7b,0x4b,0x1c,0x16]
|
|
; EGPR-NEXT: tileloaddt1 (%rsi,%rdx), %tmm3 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x4b,0x1c,0x16]
|
|
; EGPR-NEXT: tilestored %tmm3, (%rsi,%rdx) # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7a,0x4b,0x1c,0x16]
|
|
; EGPR-NEXT: retq # encoding: [0xc3]
|
|
call void @llvm.x86.ldtilecfg(ptr %pointer)
|
|
|
|
call void @llvm.x86.sttilecfg(ptr %pointer)
|
|
|
|
call void @llvm.x86.tilerelease()
|
|
|
|
call void @llvm.x86.tilezero(i8 3)
|
|
|
|
call void @llvm.x86.tileloadd64(i8 3, ptr %base, i64 %stride)
|
|
|
|
call void @llvm.x86.tileloaddt164(i8 3, ptr %base, i64 %stride)
|
|
|
|
call void @llvm.x86.tilestored64(i8 3, ptr %base, i64 %stride)
|
|
ret void
|
|
}
|
|
|
|
declare void @llvm.x86.tileloadd64(i8 %tile, ptr %base, i64 %stride)
|
|
declare void @llvm.x86.tileloaddt164(i8 %tile, ptr %base, i64 %stride)
|
|
declare void @llvm.x86.tilestored64(i8 %tile, ptr %base, i64 %stride)
|
|
declare void @llvm.x86.ldtilecfg(ptr %pointer)
|
|
declare void @llvm.x86.sttilecfg(ptr %pointer)
|
|
declare void @llvm.x86.tilerelease()
|
|
declare void @llvm.x86.tilezero(i8 %tile)
|