mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-28 04:33:05 +00:00
5842a037fb
http://llvm.org/bugs/show_bug.cgi?id=18045 Short issue description: For X86 machines with sse < sse4.1 we got failures for some particular load/store vector sequences: $ clang-trunk -m32 -O2 test-case.c fatal error: error in backend: Cannot select: 0x4200920: v4i32,ch = load 0x41d6ab0, 0x4205850, 0x41dcb10<LD16[getelementptr inbounds ([4 x i32]* @e, i32 0, i32 0)](align=4)> [ORD=82] [ID=58] 0x4205850: i32 = X86ISD::Wrapper 0x41d5490 [ORD=26] [ID=43] 0x41d5490: i32 = TargetGlobalAddress<[4 x i32]* @e> 0 [ORD=26] [ID=23] 0x41dcb10: i32 = undef [ID=2] The reason is that EltsFromConsecutiveLoads could emit such load instruction both before and after legalize stage. Though this instruction is not legal for machines with SSSE3 and lower. The fix: In EltsFromConsecutiveLoads, if we have passed legalize stage, we check whether nodes it emits are legal. P.S.: If you get failure in time from 12:00 and till 22:00 (UTC-8), perhaps I'll slow with response, so you better reject this commit. Thanks! git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@197492 91177308-0d34-0410-b5e6-96231b3b80d8
28 lines
1007 B
LLVM
28 lines
1007 B
LLVM
; RUN: llc --mcpu=x86-64 --mattr=ssse3 < %s
|
|
|
|
;PR18045:
|
|
;Issue of selection for 'v4i32 load'.
|
|
;This instruction is not legal for X86 CPUs with sse < 'sse4.1'.
|
|
;This node was generated by X86ISelLowering.cpp, EltsFromConsecutiveLoads
|
|
;static function after legilize stage.
|
|
|
|
@e = external global [4 x i32], align 4
|
|
@f = external global [4 x i32], align 4
|
|
|
|
; Function Attrs: nounwind
|
|
define void @fn3(i32 %el) {
|
|
entry:
|
|
%0 = load i32* getelementptr inbounds ([4 x i32]* @e, i32 0, i32 0)
|
|
%1 = load i32* getelementptr inbounds ([4 x i32]* @e, i32 0, i32 1)
|
|
%2 = load i32* getelementptr inbounds ([4 x i32]* @e, i32 0, i32 2)
|
|
%3 = load i32* getelementptr inbounds ([4 x i32]* @e, i32 0, i32 3)
|
|
%4 = insertelement <4 x i32> undef, i32 %0, i32 0
|
|
%5 = insertelement <4 x i32> %4, i32 %1, i32 1
|
|
%6 = insertelement <4 x i32> %5, i32 %2, i32 2
|
|
%7 = insertelement <4 x i32> %6, i32 %3, i32 3
|
|
%8 = add <4 x i32> %6, %7
|
|
store <4 x i32> %8, <4 x i32>* bitcast ([4 x i32]* @f to <4 x i32>*)
|
|
ret void
|
|
}
|
|
|