644a965c1e
This patch replaces the tight hard cut-off for the number of runtime checks with a more accurate cost-driven approach. The new approach allows vectorization with a larger number of runtime checks in general, but only executes the vector loop (and runtime checks) if considered profitable at runtime. Profitable here means that the cost-model indicates that the runtime check cost + vector loop cost < scalar loop cost. To do that, LV computes the minimum trip count for which runtime check cost + vector-loop-cost < scalar loop cost. Note that there is still a hard cut-off to avoid excessive compile-time/code-size increases, but it is much larger than the original limit. The performance impact on standard test-suites like SPEC2006/SPEC2006/MultiSource is mostly neutral, but the new approach can give substantial gains in cases where we failed to vectorize before due to the over-aggressive cut-offs. On AArch64 with -O3, I didn't observe any regressions outside the noise level (<0.4%) and there are the following execution time improvements. Both `IRSmk` and `srad` are relatively short running, but the changes are far above the noise level for them on my benchmark system. ``` CFP2006/447.dealII/447.dealII -1.9% CINT2017rate/525.x264_r/525.x264_r -2.2% ASC_Sequoia/IRSmk/IRSmk -9.2% Rodinia/srad/srad -36.1% ``` `size` regressions on AArch64 with -O3 are ``` MultiSource/Applications/hbd/hbd 90256.00 106768.00 18.3% MultiSourc...ks/ASCI_Purple/SMG2000/smg2000 240676.00 257268.00 6.9% MultiSourc...enchmarks/mafft/pairlocalalign 472603.00 489131.00 3.5% External/S...2017rate/525.x264_r/525.x264_r 613831.00 630343.00 2.7% External/S...NT2006/464.h264ref/464.h264ref 818920.00 835448.00 2.0% External/S...te/538.imagick_r/538.imagick_r 1994730.00 2027754.00 1.7% MultiSourc...nchmarks/tramp3d-v4/tramp3d-v4 1236471.00 1253015.00 1.3% MultiSource/Applications/oggenc/oggenc 2108147.00 2124675.00 0.8% External/S.../CFP2006/447.dealII/447.dealII 4742999.00 4759559.00 0.3% External/S...rate/510.parest_r/510.parest_r 14206377.00 14239433.00 0.2% ``` Reviewed By: lebedev.ri, ebrevnov, dmgreen Differential Revision: https://reviews.llvm.org/D109368
90 lines
3.8 KiB
LLVM
90 lines
3.8 KiB
LLVM
; RUN: opt < %s -loop-vectorize -dce -instcombine -pass-remarks=loop-vectorize -pass-remarks-analysis=loop-vectorize -pass-remarks-missed=loop-vectorize -S 2>&1 | FileCheck %s
|
|
|
|
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"
|
|
|
|
; First loop produced diagnostic pass remark.
|
|
;CHECK: remark: {{.*}}:0:0: vectorized loop (vectorization width: 4, interleaved count: 2)
|
|
; Second loop produces diagnostic analysis remark.
|
|
;CHECK: remark: {{.*}}:0:0: vectorized loop (vectorization width: 4, interleaved count: 1)
|
|
|
|
; We are vectorizing with 6 runtime checks.
|
|
;CHECK-LABEL: func1x6(
|
|
;CHECK: <4 x i32>
|
|
;CHECK: ret
|
|
define i32 @func1x6(i32* nocapture %out, i32* nocapture %A, i32* nocapture %B, i32* nocapture %C, i32* nocapture %D, i32* nocapture %E, i32* nocapture %F) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%i.016 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
|
|
%arrayidx = getelementptr inbounds i32, i32* %A, i64 %i.016
|
|
%0 = load i32, i32* %arrayidx, align 4
|
|
%arrayidx1 = getelementptr inbounds i32, i32* %B, i64 %i.016
|
|
%1 = load i32, i32* %arrayidx1, align 4
|
|
%add = add nsw i32 %1, %0
|
|
%arrayidx2 = getelementptr inbounds i32, i32* %C, i64 %i.016
|
|
%2 = load i32, i32* %arrayidx2, align 4
|
|
%add3 = add nsw i32 %add, %2
|
|
%arrayidx4 = getelementptr inbounds i32, i32* %E, i64 %i.016
|
|
%3 = load i32, i32* %arrayidx4, align 4
|
|
%add5 = add nsw i32 %add3, %3
|
|
%arrayidx6 = getelementptr inbounds i32, i32* %F, i64 %i.016
|
|
%4 = load i32, i32* %arrayidx6, align 4
|
|
%add7 = add nsw i32 %add5, %4
|
|
%arrayidx8 = getelementptr inbounds i32, i32* %out, i64 %i.016
|
|
store i32 %add7, i32* %arrayidx8, align 4
|
|
%inc = add i64 %i.016, 1
|
|
%exitcond = icmp eq i64 %inc, 256
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body
|
|
ret i32 undef
|
|
}
|
|
|
|
; We are vectorizing with 12 runtime checks.
|
|
;CHECK-LABEL: func2x6(
|
|
;CHECK: <4 x i32>
|
|
;CHECK: ret
|
|
define i32 @func2x6(i32* nocapture %out, i32* nocapture %out2, i32* nocapture %A, i32* nocapture %B, i32* nocapture %C, i32* nocapture %D, i32* nocapture %E, i32* nocapture %F) {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%i.037 = phi i64 [ 0, %entry ], [ %inc, %for.body ]
|
|
%arrayidx = getelementptr inbounds i32, i32* %A, i64 %i.037
|
|
%0 = load i32, i32* %arrayidx, align 4
|
|
%arrayidx1 = getelementptr inbounds i32, i32* %B, i64 %i.037
|
|
%1 = load i32, i32* %arrayidx1, align 4
|
|
%add = add nsw i32 %1, %0
|
|
%arrayidx2 = getelementptr inbounds i32, i32* %C, i64 %i.037
|
|
%2 = load i32, i32* %arrayidx2, align 4
|
|
%add3 = add nsw i32 %add, %2
|
|
%arrayidx4 = getelementptr inbounds i32, i32* %E, i64 %i.037
|
|
%3 = load i32, i32* %arrayidx4, align 4
|
|
%add5 = add nsw i32 %add3, %3
|
|
%arrayidx6 = getelementptr inbounds i32, i32* %F, i64 %i.037
|
|
%4 = load i32, i32* %arrayidx6, align 4
|
|
%add7 = add nsw i32 %add5, %4
|
|
%arrayidx8 = getelementptr inbounds i32, i32* %out, i64 %i.037
|
|
store i32 %add7, i32* %arrayidx8, align 4
|
|
%5 = load i32, i32* %arrayidx, align 4
|
|
%6 = load i32, i32* %arrayidx1, align 4
|
|
%add11 = add nsw i32 %6, %5
|
|
%7 = load i32, i32* %arrayidx2, align 4
|
|
%add13 = add nsw i32 %add11, %7
|
|
%8 = load i32, i32* %arrayidx4, align 4
|
|
%add15 = add nsw i32 %add13, %8
|
|
%9 = load i32, i32* %arrayidx6, align 4
|
|
%add17 = add nsw i32 %add15, %9
|
|
%arrayidx18 = getelementptr inbounds i32, i32* %out2, i64 %i.037
|
|
store i32 %add17, i32* %arrayidx18, align 4
|
|
%inc = add i64 %i.037, 1
|
|
%exitcond = icmp eq i64 %inc, 256
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body
|
|
ret i32 undef
|
|
}
|