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
2.7 KiB
LLVM
62 lines
2.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
|
|
; RUN: llc -mtriple aarch64 -mattr=+f16f32dot %s -o - | FileCheck %s
|
|
|
|
define <2 x float> @test_vdot_f32(<2 x float> %r, <4 x half> %a, <4 x half> %b) {
|
|
; CHECK-LABEL: test_vdot_f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fdot v0.2s, v1.4h, v2.4h
|
|
; CHECK-NEXT: ret
|
|
%res = call <2 x float> @llvm.aarch64.neon.fdot.v2f32.v4f16(<2 x float> %r, <4 x half> %a, <4 x half> %b)
|
|
ret <2 x float> %res
|
|
}
|
|
|
|
define <4 x float> @test_vdotq_f32(<4 x float> %r, <8 x half> %a, <8 x half> %b) {
|
|
; CHECK-LABEL: test_vdotq_f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fdot v0.4s, v1.8h, v2.8h
|
|
; CHECK-NEXT: ret
|
|
%res = call <4 x float> @llvm.aarch64.neon.fdot.v4f32.v8f16(<4 x float> %r, <8 x half> %a, <8 x half> %b)
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <2 x float> @test_vdot_lane_f32(<2 x float> %r, <4 x half> %a, <4 x half> %b) {
|
|
; CHECK-LABEL: test_vdot_lane_f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: // kill: def $d2 killed $d2 def $q2
|
|
; CHECK-NEXT: fdot v0.2s, v1.4h, v2.2h[0]
|
|
; CHECK-NEXT: ret
|
|
%lane = shufflevector <4 x half> %b, <4 x half> poison, <4 x i32> zeroinitializer
|
|
%res = call <2 x float> @llvm.aarch64.neon.fdot.v2f32.v4f16(<2 x float> %r, <4 x half> %a, <4 x half> %lane)
|
|
ret <2 x float> %res
|
|
}
|
|
|
|
define <4 x float> @test_vdotq_laneq_f32(<4 x float> %r, <8 x half> %a, <8 x half> %b) {
|
|
; CHECK-LABEL: test_vdotq_laneq_f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fdot v0.4s, v1.8h, v2.2h[3]
|
|
; CHECK-NEXT: ret
|
|
%lane = shufflevector <8 x half> %b, <8 x half> poison, <8 x i32> <i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3>
|
|
%res = call <4 x float> @llvm.aarch64.neon.fdot.v4f32.v8f16(<4 x float> %r, <8 x half> %a, <8 x half> %lane)
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define <2 x float> @test_vdot_laneq_f32(<2 x float> %r, <4 x half> %a, <8 x half> %b) {
|
|
; CHECK-LABEL: test_vdot_laneq_f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fdot v0.2s, v1.4h, v2.2h[3]
|
|
; CHECK-NEXT: ret
|
|
%lane = shufflevector <8 x half> %b, <8 x half> poison, <4 x i32> <i32 3, i32 3, i32 3, i32 3>
|
|
%res = call <2 x float> @llvm.aarch64.neon.fdot.v2f32.v4f16(<2 x float> %r, <4 x half> %a, <4 x half> %lane)
|
|
ret <2 x float> %res
|
|
}
|
|
|
|
define <4 x float> @test_vdotq_lane_f32(<4 x float> %r, <8 x half> %a, <4 x half> %b) {
|
|
; CHECK-LABEL: test_vdotq_lane_f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: // kill: def $d2 killed $d2 def $q2
|
|
; CHECK-NEXT: fdot v0.4s, v1.8h, v2.2h[0]
|
|
; CHECK-NEXT: ret
|
|
%lane = shufflevector <4 x half> %b, <4 x half> poison, <8 x i32> zeroinitializer
|
|
%res = call <4 x float> @llvm.aarch64.neon.fdot.v4f32.v8f16(<4 x float> %r, <8 x half> %a, <8 x half> %lane)
|
|
ret <4 x float> %res
|
|
} |