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
46 lines
1.7 KiB
LLVM
46 lines
1.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
|
|
; RUN: llc -mtriple aarch64-none-linux-gnu < %s | FileCheck %s
|
|
|
|
define i32 @uaddlv_uaddlp_v8i16(<8 x i16> %0) {
|
|
; CHECK-LABEL: uaddlv_uaddlp_v8i16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: uaddlv s0, v0.8h
|
|
; CHECK-NEXT: fmov w0, s0
|
|
; CHECK-NEXT: ret
|
|
%2 = tail call <4 x i32> @llvm.aarch64.neon.uaddlp.v4i32.v8i16(<8 x i16> %0)
|
|
%3 = tail call i64 @llvm.aarch64.neon.uaddlv.i64.v4i32(<4 x i32> %2)
|
|
%4 = trunc i64 %3 to i32
|
|
ret i32 %4
|
|
}
|
|
|
|
define i16 @uaddlv_uaddlp_v16i8(<16 x i8> %0) {
|
|
; CHECK-LABEL: uaddlv_uaddlp_v16i8:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: uaddlv h0, v0.16b
|
|
; CHECK-NEXT: fmov w0, s0
|
|
; CHECK-NEXT: ret
|
|
%2 = tail call <8 x i16> @llvm.aarch64.neon.uaddlp.v8i16.v16i8(<16 x i8> %0)
|
|
%3 = tail call i32 @llvm.aarch64.neon.uaddlv.i32.v8i16(<8 x i16> %2)
|
|
%4 = trunc i32 %3 to i16
|
|
ret i16 %4
|
|
}
|
|
|
|
define i16 @uaddlv_uaddlp_v8i8(<8 x i8> %0) {
|
|
; CHECK-LABEL: uaddlv_uaddlp_v8i8:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: uaddlv h0, v0.8b
|
|
; CHECK-NEXT: fmov w0, s0
|
|
; CHECK-NEXT: ret
|
|
%2 = tail call <4 x i16> @llvm.aarch64.neon.uaddlp.v4i16.v8i8(<8 x i8> %0)
|
|
%3 = tail call i32 @llvm.aarch64.neon.uaddlv.i32.v4i16(<4 x i16> %2)
|
|
%4 = trunc i32 %3 to i16
|
|
ret i16 %4
|
|
}
|
|
|
|
declare i64 @llvm.aarch64.neon.uaddlv.i64.v4i32(<4 x i32>)
|
|
declare i32 @llvm.aarch64.neon.uaddlv.i32.v8i16(<8 x i16>)
|
|
declare i32 @llvm.aarch64.neon.uaddlv.i32.v4i16(<4 x i16>)
|
|
declare <4 x i32> @llvm.aarch64.neon.uaddlp.v4i32.v8i16(<8 x i16>)
|
|
declare <8 x i16> @llvm.aarch64.neon.uaddlp.v8i16.v16i8(<16 x i8>)
|
|
declare <4 x i16> @llvm.aarch64.neon.uaddlp.v4i16.v8i8(<8 x i8>)
|