maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Transforms/LoopVectorize/if-pred-stores.ll

127 lines
4.5 KiB
LLVM
Raw Normal View History

LoopVectorize: Support conditional stores by scalarizing The vectorizer takes a loop like this and widens all instructions except for the store. The stores are scalarized/unrolled and hidden behind an "if" block. for (i = 0; i < 128; ++i) { if (a[i] < 10) a[i] += val; } for (i = 0; i < 128; i+=2) { v = a[i:i+1]; v0 = (extract v, 0) + 10; v1 = (extract v, 1) + 10; if (v0 < 10) a[i] = v0; if (v1 < 10) a[i] = v1; } The vectorizer relies on subsequent optimizations to sink instructions into the conditional block where they are anticipated. The flag "vectorize-num-stores-pred" controls whether and how many stores to handle this way. Vectorization of conditional stores is disabled per default for now. This patch also adds a change to the heuristic when the flag "enable-loadstore-runtime-unroll" is enabled (off by default). It unrolls small loops until load/store ports are saturated. This heuristic uses TTI's getMaxUnrollFactor as a measure for load/store ports. I also added a second flag -enable-cond-stores-vec. It will enable vectorization of conditional stores. But there is no cost model for vectorization of conditional stores in place yet so this will not do good at the moment. rdar://15892953 Results for x86-64 -O3 -mavx +/- -mllvm -enable-loadstore-runtime-unroll -vectorize-num-stores-pred=1 (before the BFI change): Performance Regressions: Benchmarks/Ptrdist/yacr2/yacr2 7.35% (maze3() is identical but 10% slower) Applications/siod/siod 2.18% Performance improvements: mesa -4.42% libquantum -4.15% With a patch that slightly changes the register heuristics (by subtracting the induction variable on both sides of the register pressure equation, as the induction variable is probably not really unrolled): Performance Regressions: Benchmarks/Ptrdist/yacr2/yacr2 7.73% Applications/siod/siod 1.97% Performance Improvements: libquantum -13.05% (we now also unroll quantum_toffoli) mesa -4.27% llvm-svn: 200270
2014-01-28 09:01:53 +08:00
; RUN: opt -S -vectorize-num-stores-pred=1 -force-vector-width=1 -force-vector-unroll=2 -loop-vectorize < %s | FileCheck %s --check-prefix=UNROLL
; RUN: opt -S -vectorize-num-stores-pred=1 -force-vector-width=2 -force-vector-unroll=1 -loop-vectorize -enable-cond-stores-vec < %s | FileCheck %s --check-prefix=VEC
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.9.0"
; Test predication of stores.
define i32 @test(i32* nocapture %f) #0 {
entry:
br label %for.body
; VEC-LABEL: test
; VEC: %[[v8:.+]] = icmp sgt <2 x i32> %{{.*}}, <i32 100, i32 100>
; VEC: %[[v9:.+]] = add nsw <2 x i32> %{{.*}}, <i32 20, i32 20>
; VEC: %[[v10:.+]] = and <2 x i1> %[[v8]], <i1 true, i1 true>
; VEC: %[[v11:.+]] = extractelement <2 x i1> %[[v10]], i32 0
; VEC: %[[v12:.+]] = icmp eq i1 %[[v11]], true
; VEC: br i1 %[[v12]], label %[[cond:.+]], label %[[else:.+]]
;
; VEC: [[cond]]:
; VEC: %[[v13:.+]] = extractelement <2 x i32> %[[v9]], i32 0
; VEC: %[[v14:.+]] = extractelement <2 x i32*> %{{.*}}, i32 0
; VEC: store i32 %[[v13]], i32* %[[v14]], align 4
; VEC: br label %[[else:.+]]
;
; VEC: [[else]]:
; VEC: %[[v15:.+]] = extractelement <2 x i1> %[[v10]], i32 1
; VEC: %[[v16:.+]] = icmp eq i1 %[[v15]], true
; VEC: br i1 %[[v16]], label %[[cond2:.+]], label %[[else2:.+]]
;
; VEC: [[cond2]]:
; VEC: %[[v17:.+]] = extractelement <2 x i32> %[[v9]], i32 1
; VEC: %[[v18:.+]] = extractelement <2 x i32*> %{{.+}} i32 1
; VEC: store i32 %[[v17]], i32* %[[v18]], align 4
; VEC: br label %[[else2:.+]]
;
; VEC: [[else2]]:
; UNROLL-LABEL: test
; UNROLL: vector.body:
; UNROLL: %[[IND:[a-zA-Z0-9]+]] = add i64 %{{.*}}, 0
; UNROLL: %[[IND1:[a-zA-Z0-9]+]] = add i64 %{{.*}}, 1
; UNROLL: %[[v0:[a-zA-Z0-9]+]] = getelementptr inbounds i32* %f, i64 %[[IND]]
; UNROLL: %[[v1:[a-zA-Z0-9]+]] = getelementptr inbounds i32* %f, i64 %[[IND1]]
; UNROLL: %[[v2:[a-zA-Z0-9]+]] = load i32* %[[v0]], align 4
; UNROLL: %[[v3:[a-zA-Z0-9]+]] = load i32* %[[v1]], align 4
; UNROLL: %[[v4:[a-zA-Z0-9]+]] = icmp sgt i32 %[[v2]], 100
; UNROLL: %[[v5:[a-zA-Z0-9]+]] = icmp sgt i32 %[[v3]], 100
; UNROLL: %[[v6:[a-zA-Z0-9]+]] = add nsw i32 %[[v2]], 20
; UNROLL: %[[v7:[a-zA-Z0-9]+]] = add nsw i32 %[[v3]], 20
; UNROLL: %[[v8:[a-zA-Z0-9]+]] = icmp eq i1 %[[v4]], true
; UNROLL: br i1 %[[v8]], label %[[cond:[a-zA-Z0-9.]+]], label %[[else:[a-zA-Z0-9.]+]]
;
; UNROLL: [[cond]]:
; UNROLL: store i32 %[[v6]], i32* %[[v0]], align 4
; UNROLL: br label %[[else]]
;
; UNROLL: [[else]]:
; UNROLL: %[[v9:[a-zA-Z0-9]+]] = icmp eq i1 %[[v5]], true
; UNROLL: br i1 %[[v9]], label %[[cond2:[a-zA-Z0-9.]+]], label %[[else2:[a-zA-Z0-9.]+]]
;
; UNROLL: [[cond2]]:
; UNROLL: store i32 %[[v7]], i32* %[[v1]], align 4
; UNROLL: br label %[[else2]]
;
; UNROLL: [[else2]]:
for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.inc ]
%arrayidx = getelementptr inbounds i32* %f, i64 %indvars.iv
%0 = load i32* %arrayidx, align 4
%cmp1 = icmp sgt i32 %0, 100
br i1 %cmp1, label %if.then, label %for.inc
if.then:
%add = add nsw i32 %0, 20
store i32 %add, i32* %arrayidx, align 4
br label %for.inc
for.inc:
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 128
br i1 %exitcond, label %for.end, label %for.body
for.end:
ret i32 0
}
LoopVectorizer: Keep track of conditional store basic blocks Before conditional store vectorization/unrolling we had only one vectorized/unrolled basic block. After adding support for conditional store vectorization this will not only be one block but multiple basic blocks. The last block would have the back-edge. I updated the code to use a vector of basic blocks instead of a single basic block and fixed the users to use the last entry in this vector. But, I forgot to add the basic blocks to this vector! Fixes PR18724. llvm-svn: 201028
2014-02-09 04:41:13 +08:00
; Track basic blocks when unrolling conditional blocks. This code used to assert
; because we did not update the phi nodes with the proper predecessor in the
; vectorized loop body.
; PR18724
; UNROLL-LABEL: bug18724
; UNROLL: store i32
; UNROLL: store i32
define void @bug18724() {
entry:
br label %for.body9
for.body9:
br i1 undef, label %for.inc26, label %for.body14
for.body14:
%indvars.iv3 = phi i64 [ %indvars.iv.next4, %for.inc23 ], [ undef, %for.body9 ]
%iNewChunks.120 = phi i32 [ %iNewChunks.2, %for.inc23 ], [ undef, %for.body9 ]
%arrayidx16 = getelementptr inbounds [768 x i32]* undef, i64 0, i64 %indvars.iv3
%tmp = load i32* %arrayidx16, align 4
br i1 undef, label %if.then18, label %for.inc23
if.then18:
store i32 2, i32* %arrayidx16, align 4
%inc21 = add nsw i32 %iNewChunks.120, 1
br label %for.inc23
for.inc23:
%iNewChunks.2 = phi i32 [ %inc21, %if.then18 ], [ %iNewChunks.120, %for.body14 ]
%indvars.iv.next4 = add nsw i64 %indvars.iv3, 1
%tmp1 = trunc i64 %indvars.iv3 to i32
%cmp13 = icmp slt i32 %tmp1, 0
br i1 %cmp13, label %for.body14, label %for.inc26
for.inc26:
%iNewChunks.1.lcssa = phi i32 [ undef, %for.body9 ], [ %iNewChunks.2, %for.inc23 ]
unreachable
}