From ee1c12708a4519361729205168dedb2b61bc2638 Mon Sep 17 00:00:00 2001 From: Florian Hahn Date: Mon, 3 Aug 2020 16:19:06 +0100 Subject: [PATCH] [SCEV] If Start>=RHS, simplify (Start smin RHS) = RHS for trip counts. In some cases, it seems like we can get rid of unnecessary s/umins by using information from the loop guards (unless I am missing something). One place where this seems to be helpful in practice is when computing loop trip counts. This patch just changes howManyGreaterThans for now. Note that this requires a loop for which we can check 'is guarded'. On SPEC2000/SPEC2006/MultiSource, there are some notable changes for some programs in the number of loops unrolled and trip counts computed. ``` Same hash: 179 (filtered out) Remaining: 58 Metric: scalar-evolution.NumTripCountsComputed Program base patch diff test-suite...langs-C/compiler/compiler.test 25.00 31.00 24.0% test-suite.../Applications/SPASS/SPASS.test 2020.00 2323.00 15.0% test-suite...langs-C/allroots/allroots.test 29.00 32.00 10.3% test-suite.../Prolangs-C/loader/loader.test 17.00 18.00 5.9% test-suite...fice-ispell/office-ispell.test 253.00 265.00 4.7% test-suite...006/450.soplex/450.soplex.test 3552.00 3692.00 3.9% test-suite...chmarks/MallocBench/gs/gs.test 453.00 470.00 3.8% test-suite...ngs-C/assembler/assembler.test 29.00 30.00 3.4% test-suite.../Benchmarks/Ptrdist/bc/bc.test 263.00 270.00 2.7% test-suite...rks/FreeBench/pifft/pifft.test 722.00 741.00 2.6% test-suite...count/automotive-bitcount.test 41.00 42.00 2.4% test-suite...0/253.perlbmk/253.perlbmk.test 1417.00 1451.00 2.4% test-suite...000/197.parser/197.parser.test 387.00 396.00 2.3% test-suite...lications/sqlite3/sqlite3.test 1168.00 1189.00 1.8% test-suite...000/255.vortex/255.vortex.test 173.00 176.00 1.7% Metric: loop-unroll.NumUnrolled Program base patch diff test-suite...langs-C/compiler/compiler.test 1.00 3.00 200.0% test-suite.../Applications/SPASS/SPASS.test 134.00 234.00 74.6% test-suite...count/automotive-bitcount.test 3.00 4.00 33.3% test-suite.../Prolangs-C/loader/loader.test 3.00 4.00 33.3% test-suite...langs-C/allroots/allroots.test 3.00 4.00 33.3% test-suite...Source/Benchmarks/sim/sim.test 10.00 12.00 20.0% test-suite...fice-ispell/office-ispell.test 21.00 25.00 19.0% test-suite.../Benchmarks/Ptrdist/bc/bc.test 32.00 38.00 18.8% test-suite...006/450.soplex/450.soplex.test 300.00 352.00 17.3% test-suite...rks/FreeBench/pifft/pifft.test 60.00 69.00 15.0% test-suite...chmarks/MallocBench/gs/gs.test 57.00 63.00 10.5% test-suite...ngs-C/assembler/assembler.test 10.00 11.00 10.0% test-suite...0/253.perlbmk/253.perlbmk.test 145.00 157.00 8.3% test-suite...000/197.parser/197.parser.test 43.00 46.00 7.0% test-suite...TimberWolfMC/timberwolfmc.test 205.00 214.00 4.4% Geomean difference 7.6% ``` Fixes https://bugs.llvm.org/show_bug.cgi?id=46939 Fixes https://bugs.llvm.org/show_bug.cgi?id=46924 on X86. Reviewed By: mkazantsev Differential Revision: https://reviews.llvm.org/D85046 --- llvm/lib/Analysis/ScalarEvolution.cpp | 11 +++++++++-- .../Analysis/ScalarEvolution/pr46939-trip-count-count-down.ll | 8 ++++---- llvm/test/Transforms/HardwareLoops/scalar-while.ll | 8 ++------ 3 files changed, 15 insertions(+), 12 deletions(-) diff --git a/llvm/lib/Analysis/ScalarEvolution.cpp b/llvm/lib/Analysis/ScalarEvolution.cpp index a961be8..23ad77f 100644 --- a/llvm/lib/Analysis/ScalarEvolution.cpp +++ b/llvm/lib/Analysis/ScalarEvolution.cpp @@ -10628,8 +10628,15 @@ ScalarEvolution::howManyGreaterThans(const SCEV *LHS, const SCEV *RHS, const SCEV *Start = IV->getStart(); const SCEV *End = RHS; - if (!isLoopEntryGuardedByCond(L, Cond, getAddExpr(Start, Stride), RHS)) - End = IsSigned ? getSMinExpr(RHS, Start) : getUMinExpr(RHS, Start); + if (!isLoopEntryGuardedByCond(L, Cond, getAddExpr(Start, Stride), RHS)) { + // If we know that Start >= RHS in the context of loop, then we know that + // min(RHS, Start) = RHS at this point. + if (isLoopEntryGuardedByCond( + L, IsSigned ? ICmpInst::ICMP_SGE : ICmpInst::ICMP_UGE, Start, RHS)) + End = RHS; + else + End = IsSigned ? getSMinExpr(RHS, Start) : getUMinExpr(RHS, Start); + } const SCEV *BECount = computeBECount(getMinusSCEV(Start, End), Stride, false); diff --git a/llvm/test/Analysis/ScalarEvolution/pr46939-trip-count-count-down.ll b/llvm/test/Analysis/ScalarEvolution/pr46939-trip-count-count-down.ll index f1001ec..803652e 100644 --- a/llvm/test/Analysis/ScalarEvolution/pr46939-trip-count-count-down.ll +++ b/llvm/test/Analysis/ScalarEvolution/pr46939-trip-count-count-down.ll @@ -6,13 +6,13 @@ define void @reverse_loop(i32 %n) { ; CHECK-LABEL: 'reverse_loop' ; CHECK-NEXT: Classifying expressions for: @reverse_loop ; CHECK-NEXT: %i.011 = phi i32 [ %n, %for.body.lr.ph ], [ %dec, %for.body ] -; CHECK-NEXT: --> {%n,+,-1}<%for.body> U: full-set S: full-set Exits: (0 smin %n) LoopDispositions: { %for.body: Computable } +; CHECK-NEXT: --> {%n,+,-1}<%for.body> U: full-set S: full-set Exits: 0 LoopDispositions: { %for.body: Computable } ; CHECK-NEXT: %dec = add nsw i32 %i.011, -1 -; CHECK-NEXT: --> {(-1 + %n),+,-1}<%for.body> U: full-set S: full-set Exits: (-1 + (0 smin %n)) LoopDispositions: { %for.body: Computable } +; CHECK-NEXT: --> {(-1 + %n),+,-1}<%for.body> U: full-set S: full-set Exits: -1 LoopDispositions: { %for.body: Computable } ; CHECK-NEXT: Determining loop execution counts for: @reverse_loop -; CHECK-NEXT: Loop %for.body: backedge-taken count is ((-1 * (0 smin %n)) + %n) +; CHECK-NEXT: Loop %for.body: backedge-taken count is %n ; CHECK-NEXT: Loop %for.body: max backedge-taken count is 2147483647 -; CHECK-NEXT: Loop %for.body: Predicated backedge-taken count is ((-1 * (0 smin %n)) + %n) +; CHECK-NEXT: Loop %for.body: Predicated backedge-taken count is %n ; CHECK-NEXT: Predicates: ; CHECK: Loop %for.body: Trip multiple is 1 ; diff --git a/llvm/test/Transforms/HardwareLoops/scalar-while.ll b/llvm/test/Transforms/HardwareLoops/scalar-while.ll index aac94ec..0b9847b 100644 --- a/llvm/test/Transforms/HardwareLoops/scalar-while.ll +++ b/llvm/test/Transforms/HardwareLoops/scalar-while.ll @@ -76,18 +76,14 @@ while.end: ; CHECK-GUARD: br i1 %cmp4, label %while.end, label %while.body.preheader ; CHECK-GUARD: while.body.preheader: ; CHECK-GUARD: [[ADD:%[^ ]+]] = add i32 %i, 1 -; CHECK-GUARD: [[SEL:%[^ ]+]] = icmp slt i32 %N, %i -; CHECK-GUARD: [[MIN:%[^ ]+]] = select i1 [[SEL]], i32 %N, i32 %i -; CHECK-GUARD: [[COUNT:%[^ ]+]] = sub i32 [[ADD]], [[MIN]] +; CHECK-GUARD: [[COUNT:%[^ ]+]] = sub i32 [[ADD]], %N ; CHECK-GUARD: call void @llvm.set.loop.iterations.i32(i32 [[COUNT]]) ; CHECK-GUARD: br label %while.body ; CHECK-LABEL: while_gte ; CHECK: while.body.preheader: ; CHECK: [[ADD:%[^ ]+]] = add i32 %i, 1 -; CHECK: [[SEL:%[^ ]+]] = icmp slt i32 %N, %i -; CHECK: [[MIN:%[^ ]+]] = select i1 [[SEL]], i32 %N, i32 %i -; CHECK: [[COUNT:%[^ ]+]] = sub i32 [[ADD]], [[MIN]] +; CHECK: [[COUNT:%[^ ]+]] = sub i32 [[ADD]], %N ; CHECK: call void @llvm.set.loop.iterations.i32(i32 [[COUNT]]) ; CHECK: br label %while.body -- 2.7.4