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
199 lines
7.5 KiB
LLVM
199 lines
7.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=aarch64-linux-gnu < %s | FileCheck %s --check-prefixes=CHECK,CHECK-SD
|
|
; RUN: llc -mtriple=aarch64 -global-isel -verify-machineinstrs %s -o - | FileCheck %s --check-prefixes=CHECK,CHECK-GI
|
|
|
|
define <2 x i32> @and_extract_zext_idx0(<4 x i16> %vec) nounwind {
|
|
; CHECK-SD-LABEL: and_extract_zext_idx0:
|
|
; CHECK-SD: // %bb.0:
|
|
; CHECK-SD-NEXT: ushll v0.4s, v0.4h, #0
|
|
; CHECK-SD-NEXT: // kill: def $d0 killed $d0 killed $q0
|
|
; CHECK-SD-NEXT: ret
|
|
;
|
|
; CHECK-GI-LABEL: and_extract_zext_idx0:
|
|
; CHECK-GI: // %bb.0:
|
|
; CHECK-GI-NEXT: movi d1, #0x00ffff0000ffff
|
|
; CHECK-GI-NEXT: ushll v0.4s, v0.4h, #0
|
|
; CHECK-GI-NEXT: and v0.8b, v0.8b, v1.8b
|
|
; CHECK-GI-NEXT: ret
|
|
%zext = zext <4 x i16> %vec to <4 x i32>
|
|
%extract = call <2 x i32> @llvm.vector.extract.v2i32.v4i32(<4 x i32> %zext, i64 0)
|
|
%and = and <2 x i32> %extract, <i32 65535, i32 65535>
|
|
ret <2 x i32> %and
|
|
}
|
|
|
|
define <4 x i16> @and_extract_sext_idx0(<8 x i8> %vec) nounwind {
|
|
; CHECK-SD-LABEL: and_extract_sext_idx0:
|
|
; CHECK-SD: // %bb.0:
|
|
; CHECK-SD-NEXT: ushll v0.8h, v0.8b, #0
|
|
; CHECK-SD-NEXT: // kill: def $d0 killed $d0 killed $q0
|
|
; CHECK-SD-NEXT: ret
|
|
;
|
|
; CHECK-GI-LABEL: and_extract_sext_idx0:
|
|
; CHECK-GI: // %bb.0:
|
|
; CHECK-GI-NEXT: movi d1, #0xff00ff00ff00ff
|
|
; CHECK-GI-NEXT: sshll v0.8h, v0.8b, #0
|
|
; CHECK-GI-NEXT: and v0.8b, v0.8b, v1.8b
|
|
; CHECK-GI-NEXT: ret
|
|
%sext = sext <8 x i8> %vec to <8 x i16>
|
|
%extract = call <4 x i16> @llvm.vector.extract.v4i16.v8i16(<8 x i16> %sext, i64 0)
|
|
%and = and <4 x i16> %extract, <i16 255, i16 255, i16 255, i16 255>
|
|
ret <4 x i16> %and
|
|
}
|
|
|
|
define <2 x i32> @and_extract_zext_idx2(<4 x i16> %vec) nounwind {
|
|
; CHECK-SD-LABEL: and_extract_zext_idx2:
|
|
; CHECK-SD: // %bb.0:
|
|
; CHECK-SD-NEXT: ushll v0.4s, v0.4h, #0
|
|
; CHECK-SD-NEXT: mov d0, v0.d[1]
|
|
; CHECK-SD-NEXT: ret
|
|
;
|
|
; CHECK-GI-LABEL: and_extract_zext_idx2:
|
|
; CHECK-GI: // %bb.0:
|
|
; CHECK-GI-NEXT: ushll v0.4s, v0.4h, #0
|
|
; CHECK-GI-NEXT: movi d1, #0x00ffff0000ffff
|
|
; CHECK-GI-NEXT: mov d0, v0.d[1]
|
|
; CHECK-GI-NEXT: and v0.8b, v0.8b, v1.8b
|
|
; CHECK-GI-NEXT: ret
|
|
%zext = zext <4 x i16> %vec to <4 x i32>
|
|
%extract = call <2 x i32> @llvm.vector.extract.v2i32.v4i32(<4 x i32> %zext, i64 2)
|
|
%and = and <2 x i32> %extract, <i32 65535, i32 65535>
|
|
ret <2 x i32> %and
|
|
}
|
|
|
|
define <4 x i16> @and_extract_sext_idx4(<8 x i8> %vec) nounwind {
|
|
; CHECK-SD-LABEL: and_extract_sext_idx4:
|
|
; CHECK-SD: // %bb.0:
|
|
; CHECK-SD-NEXT: ushll v0.8h, v0.8b, #0
|
|
; CHECK-SD-NEXT: mov d0, v0.d[1]
|
|
; CHECK-SD-NEXT: ret
|
|
;
|
|
; CHECK-GI-LABEL: and_extract_sext_idx4:
|
|
; CHECK-GI: // %bb.0:
|
|
; CHECK-GI-NEXT: sshll v0.8h, v0.8b, #0
|
|
; CHECK-GI-NEXT: movi d1, #0xff00ff00ff00ff
|
|
; CHECK-GI-NEXT: mov d0, v0.d[1]
|
|
; CHECK-GI-NEXT: and v0.8b, v0.8b, v1.8b
|
|
; CHECK-GI-NEXT: ret
|
|
%sext = sext <8 x i8> %vec to <8 x i16>
|
|
%extract = call <4 x i16> @llvm.vector.extract.v4i16.v8i16(<8 x i16> %sext, i64 4)
|
|
%and = and <4 x i16> %extract, <i16 255, i16 255, i16 255, i16 255>
|
|
ret <4 x i16> %and
|
|
}
|
|
|
|
define <2 x i32> @sext_extract_zext_idx0(<4 x i16> %vec) nounwind {
|
|
; CHECK-SD-LABEL: sext_extract_zext_idx0:
|
|
; CHECK-SD: // %bb.0:
|
|
; CHECK-SD-NEXT: sshll v0.4s, v0.4h, #0
|
|
; CHECK-SD-NEXT: // kill: def $d0 killed $d0 killed $q0
|
|
; CHECK-SD-NEXT: ret
|
|
;
|
|
; CHECK-GI-LABEL: sext_extract_zext_idx0:
|
|
; CHECK-GI: // %bb.0:
|
|
; CHECK-GI-NEXT: ushll v0.4s, v0.4h, #0
|
|
; CHECK-GI-NEXT: shl v0.2s, v0.2s, #16
|
|
; CHECK-GI-NEXT: sshr v0.2s, v0.2s, #16
|
|
; CHECK-GI-NEXT: ret
|
|
%zext = zext <4 x i16> %vec to <4 x i32>
|
|
%extract = call <2 x i32> @llvm.vector.extract.v2i32.v4i32(<4 x i32> %zext, i64 0)
|
|
%sext_inreg_step0 = shl <2 x i32> %extract, <i32 16, i32 16>
|
|
%sext_inreg = ashr <2 x i32> %sext_inreg_step0, <i32 16, i32 16>
|
|
ret <2 x i32> %sext_inreg
|
|
}
|
|
|
|
; Negative test, combine should not fire if sign extension is for a different width.
|
|
define <2 x i32> @sext_extract_zext_idx0_negtest(<4 x i16> %vec) nounwind {
|
|
; CHECK-SD-LABEL: sext_extract_zext_idx0_negtest:
|
|
; CHECK-SD: // %bb.0:
|
|
; CHECK-SD-NEXT: zip1 v0.4h, v0.4h, v0.4h
|
|
; CHECK-SD-NEXT: shl v0.2s, v0.2s, #17
|
|
; CHECK-SD-NEXT: sshr v0.2s, v0.2s, #17
|
|
; CHECK-SD-NEXT: ret
|
|
;
|
|
; CHECK-GI-LABEL: sext_extract_zext_idx0_negtest:
|
|
; CHECK-GI: // %bb.0:
|
|
; CHECK-GI-NEXT: ushll v0.4s, v0.4h, #0
|
|
; CHECK-GI-NEXT: shl v0.2s, v0.2s, #17
|
|
; CHECK-GI-NEXT: sshr v0.2s, v0.2s, #17
|
|
; CHECK-GI-NEXT: ret
|
|
%zext = zext <4 x i16> %vec to <4 x i32>
|
|
%extract = call <2 x i32> @llvm.vector.extract.v2i32.v4i32(<4 x i32> %zext, i64 0)
|
|
%sext_inreg_step0 = shl <2 x i32> %extract, <i32 17, i32 17>
|
|
%sext_inreg = ashr <2 x i32> %sext_inreg_step0, <i32 17, i32 17>
|
|
ret <2 x i32> %sext_inreg
|
|
}
|
|
|
|
define <4 x i16> @sext_extract_sext_idx0(<8 x i8> %vec) nounwind {
|
|
; CHECK-SD-LABEL: sext_extract_sext_idx0:
|
|
; CHECK-SD: // %bb.0:
|
|
; CHECK-SD-NEXT: sshll v0.8h, v0.8b, #0
|
|
; CHECK-SD-NEXT: // kill: def $d0 killed $d0 killed $q0
|
|
; CHECK-SD-NEXT: ret
|
|
;
|
|
; CHECK-GI-LABEL: sext_extract_sext_idx0:
|
|
; CHECK-GI: // %bb.0:
|
|
; CHECK-GI-NEXT: sshll v0.8h, v0.8b, #0
|
|
; CHECK-GI-NEXT: shl v0.4h, v0.4h, #8
|
|
; CHECK-GI-NEXT: sshr v0.4h, v0.4h, #8
|
|
; CHECK-GI-NEXT: ret
|
|
%sext = sext <8 x i8> %vec to <8 x i16>
|
|
%extract = call <4 x i16> @llvm.vector.extract.v4i16.v8i16(<8 x i16> %sext, i64 0)
|
|
%sext_inreg_step0 = shl <4 x i16> %extract, <i16 8, i16 8, i16 8, i16 8>
|
|
%sext_inreg = ashr <4 x i16> %sext_inreg_step0, <i16 8, i16 8, i16 8, i16 8>
|
|
ret <4 x i16> %sext_inreg
|
|
}
|
|
|
|
define <2 x i32> @sext_extract_zext_idx2(<4 x i16> %vec) nounwind {
|
|
; CHECK-SD-LABEL: sext_extract_zext_idx2:
|
|
; CHECK-SD: // %bb.0:
|
|
; CHECK-SD-NEXT: sshll v0.4s, v0.4h, #0
|
|
; CHECK-SD-NEXT: mov d0, v0.d[1]
|
|
; CHECK-SD-NEXT: ret
|
|
;
|
|
; CHECK-GI-LABEL: sext_extract_zext_idx2:
|
|
; CHECK-GI: // %bb.0:
|
|
; CHECK-GI-NEXT: ushll v0.4s, v0.4h, #0
|
|
; CHECK-GI-NEXT: mov d0, v0.d[1]
|
|
; CHECK-GI-NEXT: shl v0.2s, v0.2s, #16
|
|
; CHECK-GI-NEXT: sshr v0.2s, v0.2s, #16
|
|
; CHECK-GI-NEXT: ret
|
|
%zext = zext <4 x i16> %vec to <4 x i32>
|
|
%extract = call <2 x i32> @llvm.vector.extract.v2i32.v4i32(<4 x i32> %zext, i64 2)
|
|
%sext_inreg_step0 = shl <2 x i32> %extract, <i32 16, i32 16>
|
|
%sext_inreg = ashr <2 x i32> %sext_inreg_step0, <i32 16, i32 16>
|
|
ret <2 x i32> %sext_inreg
|
|
}
|
|
|
|
define <4 x i16> @sext_extract_sext_idx4(<8 x i8> %vec) nounwind {
|
|
; CHECK-SD-LABEL: sext_extract_sext_idx4:
|
|
; CHECK-SD: // %bb.0:
|
|
; CHECK-SD-NEXT: sshll v0.8h, v0.8b, #0
|
|
; CHECK-SD-NEXT: mov d0, v0.d[1]
|
|
; CHECK-SD-NEXT: ret
|
|
;
|
|
; CHECK-GI-LABEL: sext_extract_sext_idx4:
|
|
; CHECK-GI: // %bb.0:
|
|
; CHECK-GI-NEXT: sshll v0.8h, v0.8b, #0
|
|
; CHECK-GI-NEXT: mov d0, v0.d[1]
|
|
; CHECK-GI-NEXT: shl v0.4h, v0.4h, #8
|
|
; CHECK-GI-NEXT: sshr v0.4h, v0.4h, #8
|
|
; CHECK-GI-NEXT: ret
|
|
%sext = sext <8 x i8> %vec to <8 x i16>
|
|
%extract = call <4 x i16> @llvm.vector.extract.v4i16.v8i16(<8 x i16> %sext, i64 4)
|
|
%sext_inreg_step0 = shl <4 x i16> %extract, <i16 8, i16 8, i16 8, i16 8>
|
|
%sext_inreg = ashr <4 x i16> %sext_inreg_step0, <i16 8, i16 8, i16 8, i16 8>
|
|
ret <4 x i16> %sext_inreg
|
|
}
|
|
|
|
define <8 x i8> @sext_extract_idx(<16 x i8> %vec) nounwind {
|
|
; CHECK-LABEL: sext_extract_idx:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $q0
|
|
; CHECK-NEXT: ret
|
|
%extract = call <8 x i8> @llvm.vector.extract.v8i8.v16i8(<16 x i8> %vec, i64 0)
|
|
ret <8 x i8> %extract
|
|
}
|
|
|
|
declare <2 x i32> @llvm.vector.extract.v2i32.v4i32(<4 x i32>, i64)
|
|
declare <4 x i16> @llvm.vector.extract.v4i16.v8i16(<8 x i16>, i64)
|
|
declare <8 x i8> @llvm.vector.extract.v8i8.v16i8(<16 x i8>, i64)
|