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
42 lines
1.9 KiB
LLVM
42 lines
1.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc -mattr=+sve2,+fp8dot2,+fp8dot4 < %s | FileCheck %s
|
|
; RUN: llc -mattr=+sme,+ssve-fp8dot2,+ssve-fp8dot4 --force-streaming < %s | FileCheck %s
|
|
|
|
target triple = "aarch64-linux"
|
|
|
|
define <vscale x 4 x float> @fdot_4way(<vscale x 4 x float> %a, <vscale x 16 x i8> %s1, <vscale x 16 x i8> %s2) {
|
|
; CHECK-LABEL: fdot_4way:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fdot z0.s, z1.b, z2.b
|
|
; CHECK-NEXT: ret
|
|
%r = call <vscale x 4 x float> @llvm.aarch64.sve.fp8.fdot.nxv4f32(<vscale x 4 x float> %a, <vscale x 16 x i8> %s1, <vscale x 16 x i8> %s2)
|
|
ret <vscale x 4 x float> %r
|
|
}
|
|
|
|
define <vscale x 8 x half> @fdot_2way(<vscale x 8 x half> %a, <vscale x 16 x i8> %s1, <vscale x 16 x i8> %s2) {
|
|
; CHECK-LABEL: fdot_2way:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fdot z0.h, z1.b, z2.b
|
|
; CHECK-NEXT: ret
|
|
%r = call <vscale x 8 x half> @llvm.aarch64.sve.fp8.fdot.nxv8f16(<vscale x 8 x half> %a, <vscale x 16 x i8> %s1, <vscale x 16 x i8> %s2)
|
|
ret <vscale x 8 x half> %r
|
|
}
|
|
|
|
define <vscale x 4 x float> @fdot_4way_lane(<vscale x 4 x float> %a, <vscale x 16 x i8> %s1, <vscale x 16 x i8> %s2) {
|
|
; CHECK-LABEL: fdot_4way_lane:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fdot z0.s, z1.b, z2.b[3]
|
|
; CHECK-NEXT: ret
|
|
%r = call <vscale x 4 x float> @llvm.aarch64.sve.fp8.fdot.lane.nxv4f32(<vscale x 4 x float> %a, <vscale x 16 x i8> %s1, <vscale x 16 x i8> %s2, i32 3)
|
|
ret <vscale x 4 x float> %r
|
|
}
|
|
|
|
define <vscale x 8 x half> @fdot_2way_lane(<vscale x 8 x half> %a, <vscale x 16 x i8> %s1, <vscale x 16 x i8> %s2) {
|
|
; CHECK-LABEL: fdot_2way_lane:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fdot z0.h, z1.b, z2.b[5]
|
|
; CHECK-NEXT: ret
|
|
%r = call <vscale x 8 x half> @llvm.aarch64.sve.fp8.fdot.lane.nxv8f16(<vscale x 8 x half> %a, <vscale x 16 x i8> %s1, <vscale x 16 x i8> %s2, i32 5)
|
|
ret <vscale x 8 x half> %r
|
|
}
|