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
119 lines
6.2 KiB
LLVM
119 lines
6.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+v | FileCheck %s
|
|
|
|
; Test for an "Invalid size request on a scalable vector". Attempts to reduce
|
|
; the test faurther were not successful. The failure requires a shuffle with 2
|
|
; scalable->fixed extracts from the same vector. 0 is the only valid index for a
|
|
; scalable->fixed extract so the 2 extract must be the same. Shuffles with the
|
|
; same source are aggressively canonicalized to a unary shuffle so it requires
|
|
; the extracts to become identical through other optimizations without the
|
|
; shuffle being canonicalized before it is lowered.
|
|
|
|
define <2 x i32> @main(ptr %0) {
|
|
; CHECK-LABEL: main:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: vsetivli zero, 16, e32, m4, ta, ma
|
|
; CHECK-NEXT: vmv.v.i v8, 0
|
|
; CHECK-NEXT: vse32.v v8, (zero)
|
|
; CHECK-NEXT: vsetivli zero, 8, e32, m2, ta, ma
|
|
; CHECK-NEXT: vmv.v.i v8, 0
|
|
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
|
|
; CHECK-NEXT: vmv.v.i v10, 0
|
|
; CHECK-NEXT: li a2, 64
|
|
; CHECK-NEXT: sw zero, 80(zero)
|
|
; CHECK-NEXT: lui a1, 7
|
|
; CHECK-NEXT: lui a3, 1
|
|
; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
|
|
; CHECK-NEXT: vid.v v11
|
|
; CHECK-NEXT: li a4, 16
|
|
; CHECK-NEXT: lui a5, 2
|
|
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
|
|
; CHECK-NEXT: vse32.v v10, (a2)
|
|
; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
|
|
; CHECK-NEXT: vmv.v.i v10, 0
|
|
; CHECK-NEXT: li a2, 24
|
|
; CHECK-NEXT: sh zero, -392(a3)
|
|
; CHECK-NEXT: sh zero, 534(a3)
|
|
; CHECK-NEXT: sh zero, 1460(a3)
|
|
; CHECK-NEXT: li a3, 32
|
|
; CHECK-NEXT: vse32.v v10, (a2)
|
|
; CHECK-NEXT: li a2, 40
|
|
; CHECK-NEXT: vsetivli zero, 8, e32, m2, ta, ma
|
|
; CHECK-NEXT: vse32.v v8, (a0)
|
|
; CHECK-NEXT: sh zero, -1710(a5)
|
|
; CHECK-NEXT: sh zero, -784(a5)
|
|
; CHECK-NEXT: sh zero, 142(a5)
|
|
; CHECK-NEXT: lw a5, 1244(a1)
|
|
; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
|
|
; CHECK-NEXT: vse32.v v10, (a3)
|
|
; CHECK-NEXT: lw a3, -188(a1)
|
|
; CHECK-NEXT: sh zero, 0(a0)
|
|
; CHECK-NEXT: lw a0, -304(a1)
|
|
; CHECK-NEXT: vadd.vi v9, v11, -1
|
|
; CHECK-NEXT: vse32.v v10, (a2)
|
|
; CHECK-NEXT: lw a2, -188(a1)
|
|
; CHECK-NEXT: vmv.v.x v8, a3
|
|
; CHECK-NEXT: lw a3, 1244(a1)
|
|
; CHECK-NEXT: lw a1, -304(a1)
|
|
; CHECK-NEXT: vmv.v.x v10, a5
|
|
; CHECK-NEXT: vmv.v.x v11, a0
|
|
; CHECK-NEXT: vslide1down.vx v8, v8, zero
|
|
; CHECK-NEXT: vslide1down.vx v10, v10, zero
|
|
; CHECK-NEXT: vmin.vv v8, v10, v8
|
|
; CHECK-NEXT: vmv.s.x v10, a3
|
|
; CHECK-NEXT: vslide1down.vx v11, v11, zero
|
|
; CHECK-NEXT: vmin.vx v10, v10, a2
|
|
; CHECK-NEXT: vmin.vx v10, v10, a1
|
|
; CHECK-NEXT: vmin.vv v11, v8, v11
|
|
; CHECK-NEXT: vmv1r.v v8, v10
|
|
; CHECK-NEXT: vand.vv v9, v11, v9
|
|
; CHECK-NEXT: vslideup.vi v8, v10, 1
|
|
; CHECK-NEXT: vse32.v v9, (a4)
|
|
; CHECK-NEXT: sh zero, 0(zero)
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
store <16 x i32> zeroinitializer, ptr null, align 4
|
|
store <8 x i32> zeroinitializer, ptr %0, align 4
|
|
store <4 x i32> zeroinitializer, ptr getelementptr inbounds nuw (i8, ptr null, i64 64), align 4
|
|
store i32 0, ptr getelementptr inbounds nuw (i8, ptr null, i64 80), align 4
|
|
%1 = load i32, ptr getelementptr inbounds nuw (i8, ptr null, i64 29916), align 4
|
|
%broadcast.splatinsert53 = insertelement <4 x i32> zeroinitializer, i32 %1, i64 0
|
|
%2 = load i32, ptr getelementptr inbounds nuw (i8, ptr null, i64 28484), align 4
|
|
%broadcast.splatinsert55 = insertelement <4 x i32> zeroinitializer, i32 %2, i64 0
|
|
%3 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> %broadcast.splatinsert53, <4 x i32> %broadcast.splatinsert55)
|
|
%4 = load i32, ptr getelementptr inbounds nuw (i8, ptr null, i64 28368), align 4
|
|
%broadcast.splatinsert57 = insertelement <4 x i32> zeroinitializer, i32 %4, i64 0
|
|
%5 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> %3, <4 x i32> %broadcast.splatinsert57)
|
|
store i16 0, ptr getelementptr inbounds nuw (i8, ptr null, i64 3704), align 2
|
|
store i16 0, ptr getelementptr inbounds nuw (i8, ptr null, i64 4630), align 2
|
|
%6 = shufflevector <4 x i32> %5, <4 x i32> zeroinitializer, <2 x i32> <i32 0, i32 4>
|
|
store <2 x i32> %6, ptr getelementptr inbounds nuw (i8, ptr null, i64 16), align 4
|
|
store i16 0, ptr getelementptr inbounds nuw (i8, ptr null, i64 5556), align 2
|
|
store i16 0, ptr getelementptr inbounds nuw (i8, ptr null, i64 6482), align 2
|
|
store <2 x i32> zeroinitializer, ptr getelementptr inbounds nuw (i8, ptr null, i64 24), align 4
|
|
store i16 0, ptr getelementptr inbounds nuw (i8, ptr null, i64 7408), align 2
|
|
store i16 0, ptr getelementptr inbounds nuw (i8, ptr null, i64 8334), align 2
|
|
store <2 x i32> zeroinitializer, ptr getelementptr inbounds nuw (i8, ptr null, i64 32), align 4
|
|
store i16 0, ptr %0, align 2
|
|
store <2 x i32> zeroinitializer, ptr getelementptr inbounds nuw (i8, ptr null, i64 40), align 4
|
|
%7 = load i32, ptr getelementptr inbounds nuw (i8, ptr null, i64 29916), align 4
|
|
%broadcast.splatinsert165 = insertelement <4 x i32> poison, i32 %7, i64 0
|
|
%8 = load i32, ptr getelementptr inbounds nuw (i8, ptr null, i64 28484), align 4
|
|
%broadcast.splatinsert167 = insertelement <4 x i32> poison, i32 %8, i64 0
|
|
%9 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> %broadcast.splatinsert165, <4 x i32> %broadcast.splatinsert167)
|
|
%10 = load i32, ptr getelementptr inbounds nuw (i8, ptr null, i64 28368), align 4
|
|
%broadcast.splatinsert169 = insertelement <4 x i32> poison, i32 %10, i64 0
|
|
%11 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> %9, <4 x i32> %broadcast.splatinsert169)
|
|
store i16 0, ptr null, align 2
|
|
%12 = load i32, ptr getelementptr inbounds nuw (i8, ptr null, i64 29916), align 4
|
|
%broadcast.splatinsert179 = insertelement <4 x i32> poison, i32 %12, i64 0
|
|
%13 = load i32, ptr getelementptr inbounds nuw (i8, ptr null, i64 28484), align 4
|
|
%broadcast.splatinsert181 = insertelement <4 x i32> poison, i32 %13, i64 0
|
|
%14 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> %broadcast.splatinsert179, <4 x i32> %broadcast.splatinsert181)
|
|
%15 = load i32, ptr getelementptr inbounds nuw (i8, ptr null, i64 28368), align 4
|
|
%broadcast.splatinsert183 = insertelement <4 x i32> poison, i32 %15, i64 0
|
|
%16 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> %14, <4 x i32> %broadcast.splatinsert183)
|
|
%17 = shufflevector <4 x i32> %11, <4 x i32> %16, <2 x i32> <i32 0, i32 4>
|
|
ret <2 x i32> %17
|
|
}
|