6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-07-22 23:24:59 +00:00
Code Issues Projects Releases Wiki Activity

This patch addresses the problem of poor code generation for the zext

Browse Source 
v8i8 -> v8i32 on AVX machines. The codegen often scalarizes ANY_EXTEND nodes.
The DAGCombiner has two optimizations that can mitigate the problem. First,
if all of the operands of a BUILD_VECTOR node are extracted from an ZEXT/ANYEXT
nodes, then it is possible to create a new simplified BUILD_VECTOR which uses
UNDEFS/ZERO values to eliminate the scalar ZEXT/ANYEXT nodes.
Second, another dag combine optimization lowers BUILD_VECTOR into a shuffle
vector instruction.

In the case of zext v8i8->v8i32 on AVX, a value in an XMM register is to be
shuffled into a wide YMM register.

This patch modifes the second optimization and allows the creation of
shuffle vectors even when the newly generated vector and the original vector
from which we extract the values are of different types.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@150340 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Nadav Rotem
2012-02-12 15:05:31 +00:00
parent 61c2c128f7
commit 2ee746b87d
3 changed files with 43 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
test/CodeGen/CellSPU/rotate_ops.ll
View File

@@ -1,5 +1,5 @@
; RUN: llc < %s -march=cellspu -o %t1.s
; RUN: grep rot %t1.s | count 85
; RUN: grep rot %t1.s | count 86
; RUN: grep roth %t1.s | count 8
; RUN: grep roti.*5 %t1.s | count 1
; RUN: grep roti.*27 %t1.s | count 1