llvm-for-llvmta/test/CodeGen/AMDGPU/extract-subvector-equal-len...

29 lines
1.2 KiB
LLVM
Raw Normal View History

2022-04-25 10:02:23 +02:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -march=amdgcn -mtriple=amdgcn-- -verify-machineinstrs < %s | FileCheck %s
; Test for ICE in SelectionDAG::computeKnownBits when visiting EXTRACT_SUBVECTOR
; with DemandedElts already as wide as the source vector.
define <3 x i32> @quux() {
; CHECK-LABEL: quux:
; CHECK: ; %bb.0: ; %bb
; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; CHECK-NEXT: v_mov_b32_e32 v0, 0
; CHECK-NEXT: v_mov_b32_e32 v1, 1
; CHECK-NEXT: v_mov_b32_e32 v2, 1
; CHECK-NEXT: s_setpc_b64 s[30:31]
bb:
%tmp = shufflevector <4 x i8> <i8 1, i8 2, i8 3, i8 4>, <4 x i8> undef, <3 x i32> <i32 0, i32 1, i32 2>
%tmp1 = extractelement <3 x i8> %tmp, i64 0
%tmp2 = zext i8 %tmp1 to i32
%tmp3 = insertelement <3 x i32> undef, i32 %tmp2, i32 0
%tmp4 = extractelement <3 x i8> %tmp, i64 1
%tmp5 = zext i8 %tmp4 to i32
%tmp6 = insertelement <3 x i32> %tmp3, i32 %tmp5, i32 1
%tmp7 = extractelement <3 x i8> %tmp, i64 2
%tmp8 = zext i8 %tmp7 to i32
%tmp9 = insertelement <3 x i32> %tmp6, i32 %tmp8, i32 2
%tmp10 = lshr <3 x i32> %tmp9, <i32 1, i32 1, i32 1>
ret <3 x i32> %tmp10
}