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
58 lines
2.8 KiB
LLVM
58 lines
2.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc < %s -mtriple=riscv64 -mcpu=sifive-p670 | FileCheck %s
|
|
|
|
define void @pr141907(ptr %0) nounwind {
|
|
; CHECK-LABEL: pr141907:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: addi sp, sp, -16
|
|
; CHECK-NEXT: csrr a1, vlenb
|
|
; CHECK-NEXT: slli a1, a1, 2
|
|
; CHECK-NEXT: sub sp, sp, a1
|
|
; CHECK-NEXT: vsetivli zero, 0, e32, m1, ta, ma
|
|
; CHECK-NEXT: vmv.v.i v8, 0
|
|
; CHECK-NEXT: li a1, 0
|
|
; CHECK-NEXT: addi a2, sp, 16
|
|
; CHECK-NEXT: vsetvli zero, zero, e16, mf2, ta, ma
|
|
; CHECK-NEXT: vmv.v.i v10, 0
|
|
; CHECK-NEXT: addi a3, sp, 20
|
|
; CHECK-NEXT: li a4, 12
|
|
; CHECK-NEXT: .LBB0_1: # %vector.body
|
|
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
|
|
; CHECK-NEXT: vs4r.v v8, (a2)
|
|
; CHECK-NEXT: vsetvli a1, a1, e8, mf8, ta, ma
|
|
; CHECK-NEXT: vsetivli zero, 0, e16, mf2, ta, ma
|
|
; CHECK-NEXT: vnsrl.wi v9, v8, 0
|
|
; CHECK-NEXT: vsetvli a5, zero, e32, m1, ta, ma
|
|
; CHECK-NEXT: vlse32.v v8, (a3), a4
|
|
; CHECK-NEXT: vsetivli zero, 0, e16, mf2, ta, ma
|
|
; CHECK-NEXT: vsseg2e16.v v9, (zero)
|
|
; CHECK-NEXT: bnez a1, .LBB0_1
|
|
; CHECK-NEXT: .LBB0_2: # %while.body5
|
|
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
|
|
; CHECK-NEXT: vsetivli zero, 1, e16, m1, ta, ma
|
|
; CHECK-NEXT: vse16.v v8, (a0)
|
|
; CHECK-NEXT: j .LBB0_2
|
|
entry:
|
|
br label %vector.body
|
|
|
|
vector.body: ; preds = %vector.body, %entry
|
|
%evl.based.iv = phi i64 [ 0, %entry ], [ %2, %vector.body ]
|
|
%vector.recur = phi <vscale x 2 x i32> [ zeroinitializer, %entry ], [ %3, %vector.body ]
|
|
%1 = call i32 @llvm.experimental.get.vector.length.i64(i64 %evl.based.iv, i32 1, i1 true)
|
|
%2 = zext i32 %1 to i64
|
|
%wide.masked.load = call <vscale x 6 x i32> @llvm.vp.load.nxv6i32.p0(ptr null, <vscale x 6 x i1> zeroinitializer, i32 0)
|
|
%deinterleaved.results = call { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } @llvm.vector.deinterleave3.nxv6i32(<vscale x 6 x i32> %wide.masked.load)
|
|
%3 = extractvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } %deinterleaved.results, 1
|
|
%vp.cast65 = call <vscale x 2 x i16> @llvm.vp.trunc.nxv2i16.nxv2i32(<vscale x 2 x i32> %vector.recur, <vscale x 2 x i1> zeroinitializer, i32 0)
|
|
%interleaved.vec = call <vscale x 4 x i16> @llvm.vector.interleave2.nxv4i16(<vscale x 2 x i16> %vp.cast65, <vscale x 2 x i16> zeroinitializer)
|
|
call void @llvm.vp.store.nxv4i16.p0(<vscale x 4 x i16> %interleaved.vec, ptr null, <vscale x 4 x i1> splat (i1 true), i32 0)
|
|
%4 = icmp eq i32 %1, 0
|
|
br i1 %4, label %while.body5, label %vector.body
|
|
|
|
while.body5: ; preds = %while.body5, %vector.body
|
|
%5 = bitcast <vscale x 2 x i32> %3 to <vscale x 4 x i16>
|
|
%cond52 = extractelement <vscale x 4 x i16> %5, i64 0
|
|
store i16 %cond52, ptr %0, align 2
|
|
br label %while.body5
|
|
}
|