File: vector-legalizer-divergence.ll

package info (click to toggle)
llvm-toolchain-17 1%3A17.0.6-22
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 1,799,624 kB
  • sloc: cpp: 6,428,607; ansic: 1,383,196; asm: 793,408; python: 223,504; objc: 75,364; f90: 60,502; lisp: 33,869; pascal: 15,282; sh: 9,684; perl: 7,453; ml: 4,937; awk: 3,523; makefile: 2,889; javascript: 2,149; xml: 888; fortran: 619; cs: 573
file content (30 lines) | stat: -rw-r--r-- 1,456 bytes parent folder | download | duplicates (4)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
; RUN: llc -march=amdgcn < %s

; Tests for a bug in SelectionDAG::UpdateNodeOperands exposed by VectorLegalizer
; where divergence information is not updated.

declare i32 @llvm.amdgcn.workitem.id.x()

define amdgpu_kernel void @spam(ptr addrspace(1) noalias %arg) {
  %tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
  %tmp1 = zext i32 %tmp to i64
  %tmp2 = getelementptr inbounds double, ptr addrspace(1) %arg, i64 %tmp1
  %tmp3 = load double, ptr addrspace(1) %tmp2, align 8
  %tmp4 = fadd double undef, 0.000000e+00
  %tmp5 = insertelement <2 x double> undef, double %tmp4, i64 0
  %tmp6 = insertelement <2 x double> %tmp5, double %tmp3, i64 1
  %tmp7 = insertelement <2 x double> %tmp6, double 0.000000e+00, i64 1
  %tmp8 = fadd <2 x double> zeroinitializer, undef
  %tmp9 = fadd <2 x double> %tmp7, zeroinitializer
  %tmp10 = extractelement <2 x double> %tmp8, i64 0
  %tmp11 = getelementptr inbounds double, ptr addrspace(1) %tmp2, i64 2
  store double %tmp10, ptr addrspace(1) %tmp11, align 8
  %tmp12 = getelementptr inbounds double, ptr addrspace(1) %tmp2, i64 3
  store double undef, ptr addrspace(1) %tmp12, align 8
  %tmp13 = extractelement <2 x double> %tmp9, i64 0
  %tmp14 = getelementptr inbounds double, ptr addrspace(1) %tmp2, i64 6
  store double %tmp13, ptr addrspace(1) %tmp14, align 8
  %tmp15 = getelementptr inbounds double, ptr addrspace(1) %tmp2, i64 7
  store double 0.000000e+00, ptr addrspace(1) %tmp15, align 8
  ret void
}