mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-08-23 17:29:19 +00:00
[X86] Teach 'getTargetShuffleMask' how to look through ISD::WrapperRIP when decoding a PSHUFB mask.
The function 'getTargetShuffleMask' already knows how to deal with PSHUFB nodes where the mask node is a load from constant pool, and the constant pool node is wrapped by a X86ISD::Wrapper node. This patch extends that logic by teaching it how to also look through X86ISD::WrapperRIP. This helps function combineX86ShufflesRecusively to combine more shuffle sequences containing PSHUFB nodes if we are in RIPRel PIC mode. Before this change, llc (with -relocation-model=pic -march=x86-64) was unable to decode a pshufb where the mask was loaded from a constant pool. For example, the no-op shuffle from test 'x86-fold-pshufb.ll' was not folded into its operand, so instead of generating a single 'movaps' the backend always generated a sub-optimal 'movdqa + pshufb' sequence. Added test x86-fold-pshufb.ll. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@236863 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
parent
5081399663
commit
405e5f276b
@ -4352,7 +4352,8 @@ static bool getTargetShuffleMask(SDNode *N, MVT VT,
|
||||
return false;
|
||||
|
||||
SDValue Ptr = MaskLoad->getBasePtr();
|
||||
if (Ptr->getOpcode() == X86ISD::Wrapper)
|
||||
if (Ptr->getOpcode() == X86ISD::Wrapper ||
|
||||
Ptr->getOpcode() == X86ISD::WrapperRIP)
|
||||
Ptr = Ptr->getOperand(0);
|
||||
|
||||
auto *MaskCP = dyn_cast<ConstantPoolSDNode>(Ptr);
|
||||
|
17
test/CodeGen/X86/x86-fold-pshufb.ll
Normal file
17
test/CodeGen/X86/x86-fold-pshufb.ll
Normal file
@ -0,0 +1,17 @@
|
||||
; RUN: llc -relocation-model=pic -march=x86-64 -mtriple=x86_64-unknown-unknown -mattr=+ssse3 < %s | FileCheck %s
|
||||
|
||||
; Verify that the backend correctly folds the shuffle in function 'fold_pshufb'
|
||||
; into a simple load from constant pool.
|
||||
|
||||
define <2 x i64> @fold_pshufb() {
|
||||
; CHECK-LABEL: fold_pshufb:
|
||||
; CHECK: # BB#0:
|
||||
; CHECK-NEXT: movaps {{.*#+}} xmm0 = [0,0,0,0,1,0,0,0,2,0,0,0,3,0,0,0]
|
||||
; CHECK-NEXT: retq
|
||||
entry:
|
||||
%0 = tail call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> <i8 0, i8 0, i8 0, i8 0, i8 1, i8 0, i8 0, i8 0, i8 2, i8 0, i8 0, i8 0, i8 3, i8 0, i8 0, i8 0>, <16 x i8> <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15>)
|
||||
%1 = bitcast <16 x i8> %0 to <2 x i64>
|
||||
ret <2 x i64> %1
|
||||
}
|
||||
|
||||
declare <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8>, <16 x i8>)
|
Loading…
Reference in New Issue
Block a user