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
61 lines
2.5 KiB
LLVM
61 lines
2.5 KiB
LLVM
; RUN: llc < %s -asm-verbose=false -verify-machineinstrs -disable-wasm-fallthrough-return-opt -wasm-disable-explicit-locals -wasm-keep-registers -mattr=+simd128 | FileCheck %s
|
|
|
|
; Test that SIMD shifts can be lowered correctly even with shift
|
|
; values that are more complex than plain splats.
|
|
|
|
target triple = "wasm32-unknown-unknown"
|
|
|
|
; CHECK-LABEL: shl_add:
|
|
; CHECK-NEXT: .functype shl_add (v128, i32, i32) -> (v128)
|
|
; CHECK-NEXT: i32.add $push0=, $1, $2
|
|
; CHECK-NEXT: i8x16.shl $push1=, $0, $pop0
|
|
; CHECK-NEXT: return $pop1
|
|
define <16 x i8> @shl_add(<16 x i8> %v, i8 %a, i8 %b) {
|
|
%t1 = insertelement <16 x i8> undef, i8 %a, i32 0
|
|
%va = shufflevector <16 x i8> %t1, <16 x i8> undef, <16 x i32> zeroinitializer
|
|
%t2 = insertelement <16 x i8> undef, i8 %b, i32 0
|
|
%vb = shufflevector <16 x i8> %t2, <16 x i8> undef, <16 x i32> zeroinitializer
|
|
%shift = add <16 x i8> %va, %vb
|
|
%r = shl <16 x i8> %v, %shift
|
|
ret <16 x i8> %r
|
|
}
|
|
|
|
; CHECK-LABEL: shl_abs:
|
|
; CHECK-NEXT: .functype shl_abs (v128, i32) -> (v128)
|
|
; CHECK-NEXT: i8x16.splat $push0=, $1
|
|
; CHECK-NEXT: i8x16.abs $push1=, $pop0
|
|
; CHECK-NEXT: i8x16.extract_lane_u $push2=, $pop1, 0
|
|
; CHECK-NEXT: i8x16.shl $push3=, $0, $pop2
|
|
; CHECK-NEXT: return $pop3
|
|
define <16 x i8> @shl_abs(<16 x i8> %v, i8 %a) {
|
|
%t1 = insertelement <16 x i8> undef, i8 %a, i32 0
|
|
%va = shufflevector <16 x i8> %t1, <16 x i8> undef, <16 x i32> zeroinitializer
|
|
%nva = sub <16 x i8> zeroinitializer, %va
|
|
%c = icmp sgt <16 x i8> %va, zeroinitializer
|
|
%shift = select <16 x i1> %c, <16 x i8> %va, <16 x i8> %nva
|
|
%r = shl <16 x i8> %v, %shift
|
|
ret <16 x i8> %r
|
|
}
|
|
|
|
; CHECK-LABEL: shl_abs_add:
|
|
; CHECK-NEXT: .functype shl_abs_add (v128, i32, i32) -> (v128)
|
|
; CHECK-NEXT: i32.add $push0=, $1, $2
|
|
; CHECK-NEXT: i8x16.splat $push1=, $pop0
|
|
; CHECK-NEXT: i8x16.abs $push2=, $pop1
|
|
; CHECK-NEXT: i8x16.extract_lane_u $push3=, $pop2, 0
|
|
; CHECK-NEXT: i8x16.shl $push4=, $0, $pop3
|
|
; CHECK-NEXT: return $pop4
|
|
|
|
define <16 x i8> @shl_abs_add(<16 x i8> %v, i8 %a, i8 %b) {
|
|
%t1 = insertelement <16 x i8> undef, i8 %a, i32 0
|
|
%va = shufflevector <16 x i8> %t1, <16 x i8> undef, <16 x i32> zeroinitializer
|
|
%t2 = insertelement <16 x i8> undef, i8 %b, i32 0
|
|
%vb = shufflevector <16 x i8> %t2, <16 x i8> undef, <16 x i32> zeroinitializer
|
|
%vadd = add <16 x i8> %va, %vb
|
|
%nvadd = sub <16 x i8> zeroinitializer, %vadd
|
|
%c = icmp sgt <16 x i8> %vadd, zeroinitializer
|
|
%shift = select <16 x i1> %c, <16 x i8> %vadd, <16 x i8> %nvadd
|
|
%r = shl <16 x i8> %v, %shift
|
|
ret <16 x i8> %r
|
|
}
|