RPCS3/llvm
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm.git synced 2025-03-04 08:37:45 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

[Hexagon] Fix wrong order of operands for vmux

Browse Source 
Shuffle generation uses vmux to collapse vectors resulting from two
individual shuffles into one. The indexes of the elements selected
from the first operand were indicated by 0xFF in the constant vector
used in the compare instruction, but the compare (veqb) set the bits
corresponding to the 0x00 elements, thus inverting the selection.

Reverse the order of operands to vmux to get the correct output.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@320516 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Krzysztof Parzyszek 2017-12-12 19:32:41 +00:00
parent 1feb97a12b
commit 206ac235d7
2 changed files with 16 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
lib/Target/Hexagon/HexagonISelDAGToDAGHVX.cpp
View File

@ -1147,7 +1147,7 @@ OpRef HvxSelector::vmuxs(ArrayRef<uint8_t> Bytes, OpRef Va, OpRef Vb,
SDValue B = getVectorConstant(Bytes, dl);
Results.push(Hexagon::V6_vd0, ByteTy, {});
Results.push(Hexagon::V6_veqb, BoolTy, {OpRef(B), OpRef::res(-1)});
Results.push(Hexagon::V6_vmux, ByteTy, {OpRef::res(-1), Va, Vb});
Results.push(Hexagon::V6_vmux, ByteTy, {OpRef::res(-1), Vb, Va});
return OpRef::res(Results.top());
}

15
test/CodeGen/Hexagon/autohvx/vmux-order.ll Normal file
View File

@ -0,0 +1,15 @@
; RUN: llc -march=hexagon < %s | FileCheck %s
; The generated code isn't great, the vdeltas are no-ops (controls are all 0).
; Check for the correct order of vmux operands as is, when the code improves
; fix the checking as well.
; CHECK-DAG: v[[V0:[0-9]+]] = vdelta(v0,v{{[0-9]+}})
; CHECK-DAG: v[[V1:[0-9]+]] = vdelta(v1,v{{[0-9]+}})
; CHECK: vmux(q{{[0-3]+}},v[[V1]],v[[V0]])
define <16 x i32> @fred(<16 x i32> %v0, <16 x i32> %v1) #0 {
%p = shufflevector <16 x i32> %v0, <16 x i32> %v1, <16 x i32> <i32 0,i32 17,i32 2,i32 19,i32 4,i32 21,i32 6,i32 23,i32 8,i32 25,i32 10,i32 27,i32 12,i32 29,i32 14,i32 31>
ret <16 x i32> %p
}
attributes #0 = { nounwind readnone "target-cpu"="hexagonv60" "target-features"="+hvx,+hvx-length64b" }