[llvm] r277187 - Codegen: MachineBlockPlacement Improve probability layout.
Kyle Butt via llvm-commits
llvm-commits at lists.llvm.org
Fri Jul 29 11:09:28 PDT 2016
Author: iteratee
Date: Fri Jul 29 13:09:28 2016
New Revision: 277187
URL: http://llvm.org/viewvc/llvm-project?rev=277187&view=rev
Log:
Codegen: MachineBlockPlacement Improve probability layout.
The following pattern was being layed out poorly:
A
/ \
B C
/ \ / \
D E ? (Doesn't matter)
Where A->B is far more likely than A->C, and prob(B->D) = prob(B->E)
The current algorithm gives:
A,B,C,E (D goes on worklist)
It does this even if C has a frequency count of 0. This patch
adjusts the layout calculation so that if freq(B->E) >> freq(C->E)
then we go ahead and layout E rather than C. Fallthrough half the time
is better than fallthrough never, or fallthrough very rarely. The
resulting layout is:
A,B,E, (C and D are in a worklist)
Modified:
llvm/trunk/lib/CodeGen/MachineBlockPlacement.cpp
llvm/trunk/test/CodeGen/X86/block-placement.ll
Modified: llvm/trunk/lib/CodeGen/MachineBlockPlacement.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/MachineBlockPlacement.cpp?rev=277187&r1=277186&r2=277187&view=diff
==============================================================================
--- llvm/trunk/lib/CodeGen/MachineBlockPlacement.cpp (original)
+++ llvm/trunk/lib/CodeGen/MachineBlockPlacement.cpp Fri Jul 29 13:09:28 2016
@@ -631,18 +631,46 @@ bool MachineBlockPlacement::hasBetterLay
// BB->Succ. This is equivalent to looking the CFG backward with backward
// edge: Prob(Succ->BB) needs to >= HotProb in order to be selected (without
// profile data).
-
+ // --------------------------------------------------------------------------
+ // Case 3: forked diamond
+ // S
+ // / \
+ // / \
+ // BB Pred
+ // | \ / |
+ // | \ / |
+ // | X |
+ // | / \ |
+ // | / \ |
+ // S1 S2
+ //
+ // The current block is BB and edge BB->S1 is now being evaluated.
+ // As above S->BB was already selected because
+ // prob(S->BB) > prob(S->Pred). Assume that prob(BB->S1) >= prob(BB->S2).
+ //
+ // topo-order:
+ //
+ // S-------| ---S
+ // | | | |
+ // ---BB | | BB
+ // | | | |
+ // | Pred----| | S1----
+ // | | | |
+ // --(S1 or S2) ---Pred--
+ //
+ // topo-cost = freq(S->Pred) + freq(BB->S1) + freq(BB->S2)
+ // + min(freq(Pred->S1), freq(Pred->S2))
+ // Non-topo-order cost:
+ // In the worst case, S2 will not get laid out after Pred.
+ // non-topo-cost = 2 * freq(S->Pred) + freq(BB->S2).
+ // To be conservative, we can assume that min(freq(Pred->S1), freq(Pred->S2))
+ // is 0. Then the non topo layout is better when
+ // freq(S->Pred) < freq(BB->S1).
+ // This is exactly what is checked below.
+ // Note there are other shapes that apply (Pred may not be a single block,
+ // but they all fit this general pattern.)
BranchProbability HotProb = getLayoutSuccessorProbThreshold(BB);
- // Forward checking. For case 2, SuccProb will be 1.
- if (SuccProb < HotProb) {
- DEBUG(dbgs() << " Not a candidate: " << getBlockName(Succ) << " "
- << "Respecting topological ordering because "
- << "probability is less than prob treshold: "
- << SuccProb << "\n");
- return true;
- }
-
// Make sure that a hot successor doesn't have a globally more
// important predecessor.
BlockFrequency CandidateEdgeFreq = MBFI->getBlockFreq(BB) * RealSuccProb;
@@ -653,11 +681,11 @@ bool MachineBlockPlacement::hasBetterLay
(BlockFilter && !BlockFilter->count(Pred)) ||
BlockToChain[Pred] == &Chain)
continue;
- // Do backward checking. For case 1, it is actually redundant check. For
- // case 2 above, we need a backward checking to filter out edges that are
- // not 'strongly' biased. With profile data available, the check is mostly
- // redundant too (when threshold prob is set at 50%) unless S has more than
- // two successors.
+ // Do backward checking.
+ // For all cases above, we need a backward checking to filter out edges that
+ // are not 'strongly' biased. With profile data available, the check is
+ // mostly redundant for case 2 (when threshold prob is set at 50%) unless S
+ // has more than two successors.
// BB Pred
// \ /
// Succ
@@ -666,6 +694,8 @@ bool MachineBlockPlacement::hasBetterLay
// i.e. freq(BB->Succ) > freq(BB->Succ) * HotProb + freq(Pred->Succ) *
// HotProb
// i.e. freq((BB->Succ) * (1 - HotProb) > freq(Pred->Succ) * HotProb
+ // Case 1 is covered too, because the first equation reduces to:
+ // prob(BB->Succ) > HotProb. (freq(Succ) = freq(BB) for a triangle)
BlockFrequency PredEdgeFreq =
MBFI->getBlockFreq(Pred) * MBPI->getEdgeProbability(Pred, Succ);
if (PredEdgeFreq * HotProb >= CandidateEdgeFreq * HotProb.getCompl()) {
Modified: llvm/trunk/test/CodeGen/X86/block-placement.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/block-placement.ll?rev=277187&r1=277186&r2=277187&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/block-placement.ll (original)
+++ llvm/trunk/test/CodeGen/X86/block-placement.ll Fri Jul 29 13:09:28 2016
@@ -1283,6 +1283,174 @@ exit:
ret void
}
+declare void @a()
+declare void @b()
+
+define void @test_forked_hot_diamond(i32* %a) {
+; Test that a hot-branch with probability > 80% followed by a 50/50 branch
+; will not place the cold predecessor if the probability for the fallthrough
+; remains above 80%
+; CHECK-LABEL: test_forked_hot_diamond
+; CHECK: %entry
+; CHECK: %then
+; CHECK: %fork1
+; CHECK: %else
+; CHECK: %fork2
+; CHECK: %exit
+entry:
+ %gep1 = getelementptr i32, i32* %a, i32 1
+ %val1 = load i32, i32* %gep1
+ %cond1 = icmp ugt i32 %val1, 1
+ br i1 %cond1, label %then, label %else, !prof !5
+
+then:
+ call void @hot_function()
+ %gep2 = getelementptr i32, i32* %a, i32 2
+ %val2 = load i32, i32* %gep2
+ %cond2 = icmp ugt i32 %val2, 2
+ br i1 %cond2, label %fork1, label %fork2, !prof !8
+
+else:
+ call void @cold_function()
+ %gep3 = getelementptr i32, i32* %a, i32 3
+ %val3 = load i32, i32* %gep3
+ %cond3 = icmp ugt i32 %val3, 3
+ br i1 %cond3, label %fork1, label %fork2, !prof !8
+
+fork1:
+ call void @a()
+ br label %exit
+
+fork2:
+ call void @b()
+ br label %exit
+
+exit:
+ call void @hot_function()
+ ret void
+}
+
+define void @test_forked_hot_diamond_gets_cold(i32* %a) {
+; Test that a hot-branch with probability > 80% followed by a 50/50 branch
+; will place the cold predecessor if the probability for the fallthrough
+; falls below 80%
+; The probability for both branches is 85%. For then2 vs else1
+; this results in a compounded probability of 83%.
+; Neither then2->fork1 nor then2->fork2 has a large enough relative
+; probability to break the CFG.
+; Relative probs:
+; then2 -> fork1 vs else1 -> fork1 = 71%
+; then2 -> fork2 vs else2 -> fork2 = 74%
+; CHECK-LABEL: test_forked_hot_diamond_gets_cold
+; CHECK: %entry
+; CHECK: %then1
+; CHECK: %then2
+; CHECK: %else1
+; CHECK: %fork1
+; CHECK: %else2
+; CHECK: %fork2
+; CHECK: %exit
+entry:
+ %gep1 = getelementptr i32, i32* %a, i32 1
+ %val1 = load i32, i32* %gep1
+ %cond1 = icmp ugt i32 %val1, 1
+ br i1 %cond1, label %then1, label %else1, !prof !9
+
+then1:
+ call void @hot_function()
+ %gep2 = getelementptr i32, i32* %a, i32 2
+ %val2 = load i32, i32* %gep2
+ %cond2 = icmp ugt i32 %val2, 2
+ br i1 %cond2, label %then2, label %else2, !prof !9
+
+else1:
+ call void @cold_function()
+ br label %fork1
+
+then2:
+ call void @hot_function()
+ %gep3 = getelementptr i32, i32* %a, i32 3
+ %val3 = load i32, i32* %gep2
+ %cond3 = icmp ugt i32 %val2, 3
+ br i1 %cond3, label %fork1, label %fork2, !prof !8
+
+else2:
+ call void @cold_function()
+ br label %fork2
+
+fork1:
+ call void @a()
+ br label %exit
+
+fork2:
+ call void @b()
+ br label %exit
+
+exit:
+ call void @hot_function()
+ ret void
+}
+
+define void @test_forked_hot_diamond_stays_hot(i32* %a) {
+; Test that a hot-branch with probability > 88.88% (1:8) followed by a 50/50
+; branch will not place the cold predecessor as the probability for the
+; fallthrough stays above 80%
+; (1:8) followed by (1:1) is still (1:4)
+; Here we use 90% probability because two in a row
+; have a 89 % probability vs the original branch.
+; CHECK-LABEL: test_forked_hot_diamond_stays_hot
+; CHECK: %entry
+; CHECK: %then1
+; CHECK: %then2
+; CHECK: %fork1
+; CHECK: %else1
+; CHECK: %else2
+; CHECK: %fork2
+; CHECK: %exit
+entry:
+ %gep1 = getelementptr i32, i32* %a, i32 1
+ %val1 = load i32, i32* %gep1
+ %cond1 = icmp ugt i32 %val1, 1
+ br i1 %cond1, label %then1, label %else1, !prof !10
+
+then1:
+ call void @hot_function()
+ %gep2 = getelementptr i32, i32* %a, i32 2
+ %val2 = load i32, i32* %gep2
+ %cond2 = icmp ugt i32 %val2, 2
+ br i1 %cond2, label %then2, label %else2, !prof !10
+
+else1:
+ call void @cold_function()
+ br label %fork1
+
+then2:
+ call void @hot_function()
+ %gep3 = getelementptr i32, i32* %a, i32 3
+ %val3 = load i32, i32* %gep2
+ %cond3 = icmp ugt i32 %val2, 3
+ br i1 %cond3, label %fork1, label %fork2, !prof !8
+
+else2:
+ call void @cold_function()
+ br label %fork2
+
+fork1:
+ call void @a()
+ br label %exit
+
+fork2:
+ call void @b()
+ br label %exit
+
+exit:
+ call void @hot_function()
+ ret void
+}
+
!5 = !{!"branch_weights", i32 84, i32 16}
!6 = !{!"function_entry_count", i32 10}
!7 = !{!"branch_weights", i32 60, i32 40}
+!8 = !{!"branch_weights", i32 5001, i32 4999}
+!9 = !{!"branch_weights", i32 85, i32 15}
+!10 = !{!"branch_weights", i32 90, i32 10}
More information about the llvm-commits
mailing list