maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[X86] Prevent shuffle combining from creating an identical X86ISD::SHUF128. 

This can cause an infinite loop if SimplifiedDemandedElts asks
for the node to replace itself.

A similar protection exists in other places in shuffle combining.

Fixes ISPC https://github.com/ispc/ispc/issues/1864
This commit is contained in:
Craig Topper 2020-09-04 13:52:26 -07:00
parent 35c6d56c04
commit 35b35a373d
2 changed files with 46 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -34909,6 +34909,8 @@ static SDValue combineX86ShuffleChain(ArrayRef<SDValue> Inputs, SDValue Root,
(Mask[1] < 0 || Mask[3] < 0 || Mask[1] == (Mask[3] % 2));
if (!isAnyZero(Mask) && !PreferPERMQ) {
if (Depth == 0 && Root.getOpcode() == X86ISD::SHUF128)
return SDValue(); // Nothing to do!
if (SDValue V = MatchSHUF128(ShuffleVT, DL, Mask, V1, V2, DAG))
return DAG.getBitcast(RootVT, V);
}

44
llvm/test/CodeGen/X86/vector-shuffle-512-v16.ll
View File

@ -764,3 +764,47 @@ define <16 x float> @mask_shuffle_v4f32_v16f32_00_01_02_03_00_01_02_03_00_01_02_
%res = shufflevector <4 x float> %a, <4 x float> undef, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
ret <16 x float> %res
}
%struct.foo = type { [4 x double], [3 x [4 x double]], [4 x double] }
; This test previously hung in shuffle combining. https://github.com/ispc/ispc/issues/1864
define void @ispc_1864(<16 x float>* %arg) {
; ALL-LABEL: ispc_1864:
; ALL: # %bb.0: # %bb
; ALL-NEXT: pushq %rbp
; ALL-NEXT: .cfi_def_cfa_offset 16
; ALL-NEXT: .cfi_offset %rbp, -16
; ALL-NEXT: movq %rsp, %rbp
; ALL-NEXT: .cfi_def_cfa_register %rbp
; ALL-NEXT: andq $-64, %rsp
; ALL-NEXT: subq $4864, %rsp # imm = 0x1300
; ALL-NEXT: vbroadcastss {{.*#+}} ymm0 = [-5.0E+0,-5.0E+0,-5.0E+0,-5.0E+0,-5.0E+0,-5.0E+0,-5.0E+0,-5.0E+0]
; ALL-NEXT: vmulps 32(%rdi), %ymm0, %ymm0
; ALL-NEXT: vcvtps2pd %ymm0, %zmm0
; ALL-NEXT: vshuff64x2 {{.*#+}} zmm0 = zmm0[2,3,4,5,0,1,0,1]
; ALL-NEXT: vmovapd %ymm0, {{[0-9]+}}(%rsp)
; ALL-NEXT: movq %rbp, %rsp
; ALL-NEXT: popq %rbp
; ALL-NEXT: .cfi_def_cfa %rsp, 8
; ALL-NEXT: vzeroupper
; ALL-NEXT: retq
bb:
%tmp = alloca [30 x %struct.foo], align 64
%tmp1 = load <16 x float>, <16 x float>* %arg, align 4
%tmp2 = fmul <16 x float> %tmp1, <float -5.000000e+00, float -5.000000e+00, float -5.000000e+00, float -5.000000e+00, float -5.000000e+00, float -5.000000e+00, float -5.000000e+00, float -5.000000e+00, float -5.000000e+00, float -5.000000e+00, float -5.000000e+00, float -5.000000e+00, float -5.000000e+00, float -5.000000e+00, float -5.000000e+00, float -5.000000e+00>
%tmp3 = fpext <16 x float> %tmp2 to <16 x double>
%tmp4 = getelementptr inbounds [30 x %struct.foo], [30 x %struct.foo]* %tmp, i64 0, i64 3, i32 2, i64 0
%tmp5 = extractelement <16 x double> %tmp3, i32 10
store double %tmp5, double* %tmp4, align 32
%tmp6 = getelementptr inbounds [30 x %struct.foo], [30 x %struct.foo]* %tmp, i64 0, i64 3, i32 2, i64 1
%tmp7 = extractelement <16 x double> %tmp3, i32 11
store double %tmp7, double* %tmp6, align 8
%tmp8 = getelementptr inbounds [30 x %struct.foo], [30 x %struct.foo]* %tmp, i64 0, i64 3, i32 2, i64 2
%tmp9 = extractelement <16 x double> %tmp3, i32 12
store double %tmp9, double* %tmp8, align 16
%tmp10 = getelementptr inbounds [30 x %struct.foo], [30 x %struct.foo]* %tmp, i64 0, i64 3, i32 2, i64 3
%tmp11 = extractelement <16 x double> %tmp3, i32 13
store double %tmp11, double* %tmp10, align 8
ret void
}