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
115 lines
4.9 KiB
LLVM
115 lines
4.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s | FileCheck %s
|
|
|
|
target triple = "aarch64-unknown-linux-gnu"
|
|
|
|
; URSRA
|
|
|
|
define <vscale x 16 x i8> @ursra_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
|
|
; CHECK-LABEL: ursra_i8:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ursra z0.b, z1.b, #1
|
|
; CHECK-NEXT: ret
|
|
%pg = call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
|
|
%shift = call <vscale x 16 x i8> @llvm.aarch64.sve.urshr.nxv16i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %b, i32 1)
|
|
%add = add <vscale x 16 x i8> %a, %shift
|
|
ret <vscale x 16 x i8> %add
|
|
}
|
|
|
|
define <vscale x 8 x i16> @ursra_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
|
|
; CHECK-LABEL: ursra_i16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ursra z0.h, z1.h, #2
|
|
; CHECK-NEXT: ret
|
|
%pg = call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
|
|
%shift = call <vscale x 8 x i16> @llvm.aarch64.sve.urshr.nxv8i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %b, i32 2)
|
|
%add = add <vscale x 8 x i16> %a, %shift
|
|
ret <vscale x 8 x i16> %add
|
|
}
|
|
|
|
define <vscale x 4 x i32> @ursra_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
|
|
; CHECK-LABEL: ursra_i32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ursra z0.s, z1.s, #3
|
|
; CHECK-NEXT: ret
|
|
%pg = call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
|
|
%shift = call <vscale x 4 x i32> @llvm.aarch64.sve.urshr.nxv4i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %b, i32 3)
|
|
%add = add <vscale x 4 x i32> %a, %shift
|
|
ret <vscale x 4 x i32> %add
|
|
}
|
|
|
|
define <vscale x 2 x i64> @ursra_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
|
|
; CHECK-LABEL: ursra_i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ursra z0.d, z1.d, #4
|
|
; CHECK-NEXT: ret
|
|
%pg = call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
|
|
%shift = call <vscale x 2 x i64> @llvm.aarch64.sve.urshr.nxv2i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %b, i32 4)
|
|
%add = add <vscale x 2 x i64> %a, %shift
|
|
ret <vscale x 2 x i64> %add
|
|
}
|
|
|
|
; SRSRA
|
|
|
|
define <vscale x 16 x i8> @srsra_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) #0 {
|
|
; CHECK-LABEL: srsra_i8:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: srsra z0.b, z1.b, #1
|
|
; CHECK-NEXT: ret
|
|
%pg = call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
|
|
%shift = call <vscale x 16 x i8> @llvm.aarch64.sve.srshr.nxv16i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %b, i32 1)
|
|
%add = add <vscale x 16 x i8> %a, %shift
|
|
ret <vscale x 16 x i8> %add
|
|
}
|
|
|
|
define <vscale x 8 x i16> @srsra_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) #0 {
|
|
; CHECK-LABEL: srsra_i16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: srsra z0.h, z1.h, #2
|
|
; CHECK-NEXT: ret
|
|
%pg = call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
|
|
%shift = call <vscale x 8 x i16> @llvm.aarch64.sve.srshr.nxv8i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %b, i32 2)
|
|
%add = add <vscale x 8 x i16> %a, %shift
|
|
ret <vscale x 8 x i16> %add
|
|
}
|
|
|
|
define <vscale x 4 x i32> @srsra_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) #0 {
|
|
; CHECK-LABEL: srsra_i32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: srsra z0.s, z1.s, #3
|
|
; CHECK-NEXT: ret
|
|
%pg = call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
|
|
%shift = call <vscale x 4 x i32> @llvm.aarch64.sve.srshr.nxv4i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %b, i32 3)
|
|
%add = add <vscale x 4 x i32> %a, %shift
|
|
ret <vscale x 4 x i32> %add
|
|
}
|
|
|
|
define <vscale x 2 x i64> @srsra_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) #0 {
|
|
; CHECK-LABEL: srsra_i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: srsra z0.d, z1.d, #4
|
|
; CHECK-NEXT: ret
|
|
%pg = call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
|
|
%shift = call <vscale x 2 x i64> @llvm.aarch64.sve.srshr.nxv2i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %b, i32 4)
|
|
%add = add <vscale x 2 x i64> %a, %shift
|
|
ret <vscale x 2 x i64> %add
|
|
}
|
|
|
|
|
|
declare <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 immarg)
|
|
declare <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 immarg)
|
|
declare <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 immarg)
|
|
declare <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 immarg)
|
|
|
|
declare <vscale x 16 x i8> @llvm.aarch64.sve.urshr.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, i32)
|
|
declare <vscale x 8 x i16> @llvm.aarch64.sve.urshr.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, i32)
|
|
declare <vscale x 4 x i32> @llvm.aarch64.sve.urshr.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, i32)
|
|
declare <vscale x 2 x i64> @llvm.aarch64.sve.urshr.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, i32)
|
|
|
|
declare <vscale x 16 x i8> @llvm.aarch64.sve.srshr.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>, i32)
|
|
declare <vscale x 8 x i16> @llvm.aarch64.sve.srshr.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, i32)
|
|
declare <vscale x 4 x i32> @llvm.aarch64.sve.srshr.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, i32)
|
|
declare <vscale x 2 x i64> @llvm.aarch64.sve.srshr.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, i32)
|
|
|
|
attributes #0 = { "target-features"="+sve,+sve2" }
|