6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-08-05 13:26:55 +00:00
Code Issues Projects Releases Wiki Activity

LoopVectorizer:

Browse Source 
1. Add code to estimate register pressure.
2. Add code to select the unroll factor based on register pressure.
3. Add bits to TargetTransformInfo to provide the number of registers.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@171469 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Nadav Rotem
2013-01-04 17:48:25 +00:00
parent e12bf18754
commit e503319874
9 changed files with 279 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
test/Transforms/LoopVectorize/X86/gcc-examples.ll
View File

@@ -1,4 +1,5 @@
; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7 -dce -instcombine -licm -S | FileCheck %s
; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7 -force-vector-unroll=0 -dce -instcombine -licm -S | FileCheck %s -check-prefix=UNROLL
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.8.0"
@@ -13,6 +14,15 @@ target triple = "x86_64-apple-macosx10.8.0"
;CHECK: add nsw <4 x i32>
;CHECK: store <4 x i32>
;CHECK: ret void
;UNROLL: @example1
;UNROLL: load <4 x i32>
;UNROLL: load <4 x i32>
;UNROLL: add nsw <4 x i32>
;UNROLL: add nsw <4 x i32>
;UNROLL: store <4 x i32>
;UNROLL: store <4 x i32>
;UNROLL: ret void
define void @example1() nounwind uwtable ssp {
br label %1
@@ -34,13 +44,20 @@ define void @example1() nounwind uwtable ssp {
ret void
}
; Select VF=4 because sext <8 x i1> to <8 x i32> is expensive.
; Select VF=4 because sext <8 x i1> to <8 x i32> is expensive.
;CHECK: @example10b
;CHECK: load <4 x i16>
;CHECK: sext <4 x i16>
;CHECK: store <4 x i32>
;CHECK: ret void
;UNROLL: @example10b
;UNROLL: load <4 x i16>
;UNROLL: load <4 x i16>
;UNROLL: load <4 x i16>
;UNROLL: store <4 x i32>
;UNROLL: store <4 x i32>
;UNROLL: store <4 x i32>
;UNROLL: ret void
define void @example10b(i16* noalias nocapture %sa, i16* noalias nocapture %sb, i16* noalias nocapture %sc, i32* noalias nocapture %ia, i32* noalias nocapture %ib, i32* noalias nocapture %ic) nounwind uwtable ssp {
br label %1