6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-01-28 06:32:09 +00:00
Code Issues Projects Releases Wiki Activity

[LV] Statistics numbers for LoopVectorize introduced: a number of analyzed loops & a number of vectorized loops.

Browse Source 
Use -stats to see how many loops were analyzed for possible vectorization and how many of them were actually vectorized.
Patch by Zinovy Nis

Differential Revision: http://reviews.llvm.org/D3438



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@206956 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Alexander Musman 2014-04-23 08:40:37 +00:00
parent 07c2241e45
commit bf255f5d5a
2 changed files with 73 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
lib/Transforms/Vectorize/LoopVectorize.cpp
View File

@ -51,6 +51,7 @@
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/ADT/SmallSet.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/Analysis/BlockFrequencyInfo.h"
@ -98,6 +99,9 @@ using namespace llvm::PatternMatch;
#define LV_NAME "loop-vectorize"
#define DEBUG_TYPE LV_NAME
STATISTIC(LoopsVectorized, "Number of loops vectorized");
STATISTIC(LoopsAnalyzed, "Number of loops analyzed for vectorization");
static cl::opt<unsigned>
VectorizationFactor("force-vector-width", cl::init(0), cl::Hidden,
cl::desc("Sets the SIMD width. Zero is autoselect."));
@ -1080,6 +1084,8 @@ struct LoopVectorize : public FunctionPass {
for (Loop *L : *LI)
addInnerLoop(*L, Worklist);
LoopsAnalyzed += Worklist.size();
// Now walk the identified inner loops.
bool Changed = false;
while (!Worklist.empty())
@ -1182,6 +1188,7 @@ struct LoopVectorize : public FunctionPass {
// If we decided that it is *legal* to vectorize the loop then do it.
InnerLoopVectorizer LB(L, SE, LI, DT, DL, TLI, VF.Width, UF);
LB.vectorize(&LVL);
++LoopsVectorized;
}
// Mark the loop as already vectorized to avoid vectorizing again.

66
test/Transforms/LoopVectorize/vect.stats.ll Normal file
View File

@ -0,0 +1,66 @@
; RUN: opt < %s -loop-vectorize -force-vector-unroll=4 -force-vector-width=4 -debug-only=loop-vectorize -stats -S 2>&1 | FileCheck %s
; REQUIRES: asserts
;
; We have 2 loops, one of them is vectorizable and the second one is not.
;
; CHECK: 2 loop-vectorize - Number of loops analyzed for vectorization
; CHECK: 1 loop-vectorize - Number of loops vectorized
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-unknown-linux-gnu"
define void @vectorized(float* nocapture %a, i64 %size) {
entry:
%cmp1 = icmp sgt i64 %size, 0
br i1 %cmp1, label %for.header, label %for.end
for.header:
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%cmp2 = icmp sgt i64 %indvars.iv, %size
br i1 %cmp2, label %for.end, label %for.body
for.body:
%arrayidx = getelementptr inbounds float* %a, i64 %indvars.iv
%0 = load float* %arrayidx, align 4
%mul = fmul float %0, %0
store float %mul, float* %arrayidx, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
br label %for.header
for.end:
ret void
}
define void @not_vectorized(float* nocapture %a, i64 %size) {
entry:
%cmp1 = icmp sgt i64 %size, 0
br i1 %cmp1, label %for.header, label %for.end
for.header:
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%cmp2 = icmp sgt i64 %indvars.iv, %size
br i1 %cmp2, label %for.end, label %for.body
for.body:
%0 = add nsw i64 %indvars.iv, -5
%arrayidx = getelementptr inbounds float* %a, i64 %0
%1 = load float* %arrayidx, align 4
%2 = add nsw i64 %indvars.iv, 2
%arrayidx2 = getelementptr inbounds float* %a, i64 %2
%3 = load float* %arrayidx2, align 4
%mul = fmul float %1, %3
%arrayidx4 = getelementptr inbounds float* %a, i64 %indvars.iv
store float %mul, float* %arrayidx4, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
br label %for.header
for.end:
ret void
}