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
109 lines
4.3 KiB
LLVM
109 lines
4.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -o -| FileCheck %s
|
|
|
|
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
|
|
target triple = "aarch64-unknown-linux-gnu"
|
|
|
|
; This test covers a case where an AArch64 DUP instruction is generated with an
|
|
; invalid encoding, resulting in a crash. We don't care about the specific output
|
|
; here, only that this case no longer causes said crash.
|
|
define dso_local i32 @dupext_crashtest(i32 %e) local_unnamed_addr {
|
|
; CHECK-LABEL: dupext_crashtest:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: dup v0.2s, w0
|
|
; CHECK-NEXT: .LBB0_1: // %vector.body
|
|
; CHECK-NEXT: // =>This Inner Loop Header: Depth=1
|
|
; CHECK-NEXT: ldr d1, [x8]
|
|
; CHECK-NEXT: smull v1.2d, v0.2s, v1.2s
|
|
; CHECK-NEXT: xtn v1.2s, v1.2d
|
|
; CHECK-NEXT: str d1, [x8]
|
|
; CHECK-NEXT: b .LBB0_1
|
|
entry:
|
|
%conv314 = zext i32 %e to i64
|
|
br label %vector.memcheck
|
|
|
|
vector.memcheck: ; preds = %for.body.lr.ph
|
|
br label %vector.ph
|
|
|
|
vector.ph: ; preds = %vector.memcheck
|
|
%broadcast.splatinsert = insertelement <2 x i64> poison, i64 %conv314, i32 0
|
|
%broadcast.splat = shufflevector <2 x i64> %broadcast.splatinsert, <2 x i64> poison, <2 x i32> zeroinitializer
|
|
br label %vector.body
|
|
|
|
vector.body: ; preds = %vector.body, %vector.ph
|
|
%wide.load = load <2 x i32>, ptr undef, align 4
|
|
%0 = zext <2 x i32> %wide.load to <2 x i64>
|
|
%1 = mul nuw <2 x i64> %broadcast.splat, %0
|
|
%2 = trunc <2 x i64> %1 to <2 x i32>
|
|
%3 = select <2 x i1> undef, <2 x i32> undef, <2 x i32> %2
|
|
%4 = bitcast ptr undef to ptr
|
|
store <2 x i32> %3, ptr %4, align 4
|
|
br label %vector.body
|
|
}
|
|
|
|
; This test got stuck in a loop hoisting the and to the load, and sinking it back to the mull
|
|
define i32 @dup_and_load(ptr %p, i1 %c) {
|
|
; CHECK-LABEL: dup_and_load:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: mov x8, x0
|
|
; CHECK-NEXT: ldrb w0, [x0]
|
|
; CHECK-NEXT: tbz w1, #0, .LBB1_3
|
|
; CHECK-NEXT: // %bb.1: // %ph
|
|
; CHECK-NEXT: dup v0.8h, w0
|
|
; CHECK-NEXT: mov w9, wzr
|
|
; CHECK-NEXT: .LBB1_2: // %vector.body
|
|
; CHECK-NEXT: // =>This Inner Loop Header: Depth=1
|
|
; CHECK-NEXT: ldr d1, [x8]
|
|
; CHECK-NEXT: add w9, w9, #1
|
|
; CHECK-NEXT: cmp w9, #100
|
|
; CHECK-NEXT: ushll v1.8h, v1.8b, #0
|
|
; CHECK-NEXT: umull2 v2.4s, v0.8h, v1.8h
|
|
; CHECK-NEXT: umull v1.4s, v0.4h, v1.4h
|
|
; CHECK-NEXT: stp q1, q2, [x8]
|
|
; CHECK-NEXT: b.lt .LBB1_2
|
|
; CHECK-NEXT: .LBB1_3: // %end
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%l = load i32, ptr %p
|
|
%and255 = and i32 %l, 255
|
|
br i1 %c, label %ph, label %end
|
|
|
|
ph:
|
|
%broadcast.splatinsert = insertelement <8 x i32> poison, i32 %and255, i32 0
|
|
%broadcast.splat = shufflevector <8 x i32> %broadcast.splatinsert, <8 x i32> poison, <8 x i32> zeroinitializer
|
|
br label %vector.body
|
|
|
|
vector.body: ; preds = %vector.body, %vector.ph
|
|
%iv = phi i32 [ 0, %ph ], [ %iv.next, %vector.body ]
|
|
%wide.load = load <8 x i8>, ptr %p, align 4
|
|
%0 = zext <8 x i8> %wide.load to <8 x i32>
|
|
%1 = mul <8 x i32> %broadcast.splat, %0
|
|
store <8 x i32> %1, ptr %p, align 4
|
|
%iv.next = add i32 %iv, 1
|
|
%e = icmp slt i32 %iv.next, 100
|
|
br i1 %e, label %vector.body, label %end
|
|
|
|
end:
|
|
ret i32 %and255
|
|
}
|
|
|
|
define <4 x i32> @backsmith_pure_4(<4 x i32> %0, <4 x i16> %conv.i) {
|
|
; CHECK-LABEL: backsmith_pure_4:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: // kill: def $d1 killed $d1 def $q1
|
|
; CHECK-NEXT: shl v2.4s, v0.4s, #16
|
|
; CHECK-NEXT: dup v1.4h, v1.h[2]
|
|
; CHECK-NEXT: sshr v2.4s, v2.4s, #16
|
|
; CHECK-NEXT: sshll v1.4s, v1.4h, #0
|
|
; CHECK-NEXT: trn2 v1.4s, v1.4s, v2.4s
|
|
; CHECK-NEXT: mul v0.4s, v0.4s, v1.4s
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%conv.i19 = trunc <4 x i32> %0 to <4 x i16>
|
|
%shuffle11 = shufflevector <4 x i16> %conv.i19, <4 x i16> %conv.i, <32 x i32> <i32 5, i32 2, i32 5, i32 3, i32 1, i32 6, i32 5, i32 6, i32 5, i32 6, i32 4, i32 6, i32 0, i32 3, i32 5, i32 1, i32 6, i32 7, i32 2, i32 6, i32 3, i32 1, i32 0, i32 4, i32 4, i32 1, i32 2, i32 7, i32 2, i32 2, i32 1, i32 2>
|
|
%conv12 = sext <32 x i16> %shuffle11 to <32 x i32>
|
|
%shuffle14 = shufflevector <32 x i32> %conv12, <32 x i32> zeroinitializer, <4 x i32> <i32 9, i32 25, i32 poison, i32 poison>
|
|
%mul = mul <4 x i32> %0, %shuffle14
|
|
ret <4 x i32> %mul
|
|
}
|