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
117 lines
4.5 KiB
LLVM
117 lines
4.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -O0 -verify-machineinstrs -mtriple=x86_64-unknown-unknown --show-mc-encoding -mattr=+amx-tile,+amx-avx512,+avx10.2 | FileCheck %s
|
|
|
|
define <16 x float> @test_tcvtrowd2ps(i32 %A) {
|
|
; CHECK-LABEL: test_tcvtrowd2ps:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: tcvtrowd2ps %edi, %tmm1, %zmm0 # encoding: [0x62,0xf2,0x46,0x48,0x4a,0xc1]
|
|
; CHECK-NEXT: retq # encoding: [0xc3]
|
|
%ret = call <16 x float> @llvm.x86.tcvtrowd2ps(i8 1, i32 %A)
|
|
ret <16 x float> %ret
|
|
}
|
|
|
|
define <16 x float> @test_tcvtrowd2psi() {
|
|
; CHECK-LABEL: test_tcvtrowd2psi:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: tcvtrowd2ps $127, %tmm1, %zmm0 # encoding: [0x62,0xf3,0x7e,0x48,0x07,0xc1,0x7f]
|
|
; CHECK-NEXT: retq # encoding: [0xc3]
|
|
%ret = call <16 x float> @llvm.x86.tcvtrowd2psi(i8 1, i32 127)
|
|
ret <16 x float> %ret
|
|
}
|
|
declare <16 x float> @llvm.x86.tcvtrowd2ps(i8 %A, i32 %B)
|
|
|
|
define <32 x bfloat> @test_tcvtrowps2bf16h(i32 %A) {
|
|
; CHECK-LABEL: test_tcvtrowps2bf16h:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: tcvtrowps2bf16h %edi, %tmm1, %zmm0 # encoding: [0x62,0xf2,0x47,0x48,0x6d,0xc1]
|
|
; CHECK-NEXT: retq # encoding: [0xc3]
|
|
%ret = call <32 x bfloat> @llvm.x86.tcvtrowps2bf16h(i8 1, i32 %A)
|
|
ret <32 x bfloat> %ret
|
|
}
|
|
|
|
define <32 x bfloat> @test_tcvtrowps2bf16hi() {
|
|
; CHECK-LABEL: test_tcvtrowps2bf16hi:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: tcvtrowps2bf16h $127, %tmm1, %zmm0 # encoding: [0x62,0xf3,0x7f,0x48,0x07,0xc1,0x7f]
|
|
; CHECK-NEXT: retq # encoding: [0xc3]
|
|
%ret = call <32 x bfloat> @llvm.x86.tcvtrowps2bf16hi(i8 1, i32 127)
|
|
ret <32 x bfloat> %ret
|
|
}
|
|
declare <32 x bfloat> @llvm.x86.tcvtrowps2bf16h(i8 %A, i32 %B)
|
|
|
|
define <32 x bfloat> @test_tcvtrowps2bf16l(i32 %A) {
|
|
; CHECK-LABEL: test_tcvtrowps2bf16l:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: tcvtrowps2bf16l %edi, %tmm1, %zmm0 # encoding: [0x62,0xf2,0x46,0x48,0x6d,0xc1]
|
|
; CHECK-NEXT: retq # encoding: [0xc3]
|
|
%ret = call <32 x bfloat> @llvm.x86.tcvtrowps2bf16l(i8 1, i32 %A)
|
|
ret <32 x bfloat> %ret
|
|
}
|
|
|
|
define <32 x bfloat> @test_tcvtrowps2bf16li() {
|
|
; CHECK-LABEL: test_tcvtrowps2bf16li:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: tcvtrowps2bf16l $127, %tmm1, %zmm0 # encoding: [0x62,0xf3,0x7e,0x48,0x77,0xc1,0x7f]
|
|
; CHECK-NEXT: retq # encoding: [0xc3]
|
|
%ret = call <32 x bfloat> @llvm.x86.tcvtrowps2bf16li(i8 1, i32 127)
|
|
ret <32 x bfloat> %ret
|
|
}
|
|
declare <32 x bfloat> @llvm.x86.tcvtrowps2bf16l(i8 %A, i32 %B)
|
|
|
|
define <32 x half> @test_tcvtrowps2phh(i32 %A) {
|
|
; CHECK-LABEL: test_tcvtrowps2phh:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: tcvtrowps2phh %edi, %tmm1, %zmm0 # encoding: [0x62,0xf2,0x44,0x48,0x6d,0xc1]
|
|
; CHECK-NEXT: retq # encoding: [0xc3]
|
|
%ret = call <32 x half> @llvm.x86.tcvtrowps2phh(i8 1, i32 %A)
|
|
ret <32 x half> %ret
|
|
}
|
|
|
|
define <32 x half> @test_tcvtrowps2phhi() {
|
|
; CHECK-LABEL: test_tcvtrowps2phhi:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: tcvtrowps2phh $127, %tmm1, %zmm0 # encoding: [0x62,0xf3,0x7c,0x48,0x07,0xc1,0x7f]
|
|
; CHECK-NEXT: retq # encoding: [0xc3]
|
|
%ret = call <32 x half> @llvm.x86.tcvtrowps2phhi(i8 1, i32 127)
|
|
ret <32 x half> %ret
|
|
}
|
|
declare <32 x half> @llvm.x86.tcvtrowps2phh(i8 %A, i32 %B)
|
|
|
|
define <32 x half> @test_tcvtrowps2phl(i32 %A) {
|
|
; CHECK-LABEL: test_tcvtrowps2phl:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: tcvtrowps2phl %edi, %tmm1, %zmm0 # encoding: [0x62,0xf2,0x45,0x48,0x6d,0xc1]
|
|
; CHECK-NEXT: retq # encoding: [0xc3]
|
|
%ret = call <32 x half> @llvm.x86.tcvtrowps2phl(i8 1, i32 %A)
|
|
ret <32 x half> %ret
|
|
}
|
|
|
|
define <32 x half> @test_tcvtrowps2phli() {
|
|
; CHECK-LABEL: test_tcvtrowps2phli:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: tcvtrowps2phl $127, %tmm1, %zmm0 # encoding: [0x62,0xf3,0x7f,0x48,0x77,0xc1,0x7f]
|
|
; CHECK-NEXT: retq # encoding: [0xc3]
|
|
%ret = call <32 x half> @llvm.x86.tcvtrowps2phli(i8 1, i32 127)
|
|
ret <32 x half> %ret
|
|
}
|
|
declare <32 x half> @llvm.x86.tcvtrowps2phl(i8 %A, i32 %B)
|
|
|
|
define <16 x i32> @test_tilemovrow(i32 %A) {
|
|
; CHECK-LABEL: test_tilemovrow:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: tilemovrow %edi, %tmm1, %zmm0 # encoding: [0x62,0xf2,0x45,0x48,0x4a,0xc1]
|
|
; CHECK-NEXT: retq # encoding: [0xc3]
|
|
%ret = call <16 x i32> @llvm.x86.tilemovrow(i8 1, i32 %A)
|
|
ret <16 x i32> %ret
|
|
}
|
|
|
|
define <16 x i32> @test_tilemovrowi() {
|
|
; CHECK-LABEL: test_tilemovrowi:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: tilemovrow $127, %tmm1, %zmm0 # encoding: [0x62,0xf3,0x7d,0x48,0x07,0xc1,0x7f]
|
|
; CHECK-NEXT: retq # encoding: [0xc3]
|
|
%ret = call <16 x i32> @llvm.x86.tilemovrowi(i8 1, i32 127)
|
|
ret <16 x i32> %ret
|
|
}
|
|
declare <16 x i32> @llvm.x86.tilemovrow(i8 %A, i32 %B)
|