[llvm] 28865da - [LSR][term-fold] Adjust expansion budget based on trip count (#80304)
via llvm-commits
llvm-commits at lists.llvm.org
Fri Feb 2 08:57:30 PST 2024
Author: Philip Reames
Date: 2024-02-02T08:57:26-08:00
New Revision: 28865da37451904c4654f20cdaddee815fdeff1d
URL: https://github.com/llvm/llvm-project/commit/28865da37451904c4654f20cdaddee815fdeff1d
DIFF: https://github.com/llvm/llvm-project/commit/28865da37451904c4654f20cdaddee815fdeff1d.diff
LOG: [LSR][term-fold] Adjust expansion budget based on trip count (#80304)
Follow up to https://github.com/llvm/llvm-project/pull/74747
This change extends the previously added fixed expansion threshold by
scaling down the cost allowed for an expansion for a loop with either a
small known trip count or a profile which indicates the trip count is
likely small. The goal here is to improve code generation for a loop
nest where the outer loop has a high trip count, and the inner loop runs
only a handful of iterations.
---------
Co-authored-by: Nikita Popov <github at npopov.com>
Added:
Modified:
llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp
llvm/test/Transforms/LoopStrengthReduce/lsr-term-fold.ll
Removed:
################################################################################
diff --git a/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp b/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp
index 831911ab21c22..6f6d1f9c76068 100644
--- a/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp
+++ b/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp
@@ -6813,6 +6813,18 @@ canFoldTermCondOfLoop(Loop *L, ScalarEvolution &SE, DominatorTree &DT,
if (!isAlmostDeadIV(ToFold, LoopLatch, TermCond))
return std::nullopt;
+ // Inserting instructions in the preheader has a runtime cost, scale
+ // the allowed cost with the loops trip count as best we can.
+ const unsigned ExpansionBudget = [&]() {
+ unsigned Budget = 2 * SCEVCheapExpansionBudget;
+ if (unsigned SmallTC = SE.getSmallConstantMaxTripCount(L))
+ return std::min(Budget, SmallTC);
+ if (std::optional<unsigned> SmallTC = getLoopEstimatedTripCount(L))
+ return std::min(Budget, *SmallTC);
+ // Unknown trip count, assume long running by default.
+ return Budget;
+ }();
+
const SCEV *BECount = SE.getBackedgeTakenCount(L);
const DataLayout &DL = L->getHeader()->getModule()->getDataLayout();
SCEVExpander Expander(SE, DL, "lsr_fold_term_cond");
@@ -6862,8 +6874,7 @@ canFoldTermCondOfLoop(Loop *L, ScalarEvolution &SE, DominatorTree &DT,
continue;
}
- if (Expander.isHighCostExpansion(TermValueSLocal, L,
- 2*SCEVCheapExpansionBudget,
+ if (Expander.isHighCostExpansion(TermValueSLocal, L, ExpansionBudget,
&TTI, InsertPt)) {
LLVM_DEBUG(
dbgs() << "Is too expensive to expand terminating value for phi node"
diff --git a/llvm/test/Transforms/LoopStrengthReduce/lsr-term-fold.ll b/llvm/test/Transforms/LoopStrengthReduce/lsr-term-fold.ll
index be24ecf112e30..7299a014b7983 100644
--- a/llvm/test/Transforms/LoopStrengthReduce/lsr-term-fold.ll
+++ b/llvm/test/Transforms/LoopStrengthReduce/lsr-term-fold.ll
@@ -482,20 +482,15 @@ define void @profiled_short_tc(ptr %a, i32 %offset, i32 %n) {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[OFFSET_NONZERO:%.*]] = or i32 [[OFFSET:%.*]], 1
; CHECK-NEXT: [[UGLYGEP:%.*]] = getelementptr i8, ptr [[A:%.*]], i64 84
-; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[N:%.*]], -1
-; CHECK-NEXT: [[TMP1:%.*]] = zext i32 [[TMP0]] to i64
-; CHECK-NEXT: [[TMP2:%.*]] = add nuw nsw i64 [[TMP1]], 1
-; CHECK-NEXT: [[TMP3:%.*]] = sext i32 [[OFFSET_NONZERO]] to i64
-; CHECK-NEXT: [[TMP4:%.*]] = mul i64 [[TMP2]], [[TMP3]]
-; CHECK-NEXT: [[TMP5:%.*]] = add nsw i64 [[TMP4]], 84
-; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, ptr [[A]], i64 [[TMP5]]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[LSR_IV1:%.*]] = phi ptr [ [[UGLYGEP2:%.*]], [[FOR_BODY]] ], [ [[UGLYGEP]], [[ENTRY:%.*]] ]
+; CHECK-NEXT: [[LSR_IV:%.*]] = phi i32 [ [[LSR_IV_NEXT:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY]] ]
; CHECK-NEXT: store i32 1, ptr [[LSR_IV1]], align 4
+; CHECK-NEXT: [[LSR_IV_NEXT]] = add nsw i32 [[LSR_IV]], 1
; CHECK-NEXT: [[UGLYGEP2]] = getelementptr i8, ptr [[LSR_IV1]], i32 [[OFFSET_NONZERO]]
-; CHECK-NEXT: [[LSR_FOLD_TERM_COND_REPLACED_TERM_COND:%.*]] = icmp eq ptr [[UGLYGEP2]], [[SCEVGEP]]
-; CHECK-NEXT: br i1 [[LSR_FOLD_TERM_COND_REPLACED_TERM_COND]], label [[FOR_END:%.*]], label [[FOR_BODY]], !prof [[PROF0:![0-9]+]]
+; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i32 [[LSR_IV_NEXT]], [[N:%.*]]
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END:%.*]], label [[FOR_BODY]], !prof [[PROF0:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
@@ -637,16 +632,15 @@ define void @small_tc_trivial_loop(ptr %a, i32 %offset) {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[OFFSET_NONZERO:%.*]] = or i32 [[OFFSET:%.*]], 1
; CHECK-NEXT: [[UGLYGEP:%.*]] = getelementptr i8, ptr [[A:%.*]], i64 84
-; CHECK-NEXT: [[TMP0:%.*]] = sext i32 [[OFFSET_NONZERO]] to i64
-; CHECK-NEXT: [[TMP1:%.*]] = add nsw i64 [[TMP0]], 84
-; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, ptr [[A]], i64 [[TMP1]]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[LSR_IV1:%.*]] = phi ptr [ [[UGLYGEP2:%.*]], [[FOR_BODY]] ], [ [[UGLYGEP]], [[ENTRY:%.*]] ]
+; CHECK-NEXT: [[LSR_IV:%.*]] = phi i32 [ [[LSR_IV_NEXT:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY]] ]
; CHECK-NEXT: store i32 1, ptr [[LSR_IV1]], align 4
+; CHECK-NEXT: [[LSR_IV_NEXT]] = add nsw i32 [[LSR_IV]], 1
; CHECK-NEXT: [[UGLYGEP2]] = getelementptr i8, ptr [[LSR_IV1]], i32 [[OFFSET_NONZERO]]
-; CHECK-NEXT: [[LSR_FOLD_TERM_COND_REPLACED_TERM_COND:%.*]] = icmp eq ptr [[UGLYGEP2]], [[SCEVGEP]]
-; CHECK-NEXT: br i1 [[LSR_FOLD_TERM_COND_REPLACED_TERM_COND]], label [[FOR_END:%.*]], label [[FOR_BODY]]
+; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i32 [[LSR_IV_NEXT]], 1
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END:%.*]], label [[FOR_BODY]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
@@ -673,17 +667,15 @@ define void @small_tc_below_threshold(ptr %a, i32 %offset) {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[OFFSET_NONZERO:%.*]] = or i32 [[OFFSET:%.*]], 1
; CHECK-NEXT: [[UGLYGEP:%.*]] = getelementptr i8, ptr [[A:%.*]], i64 84
-; CHECK-NEXT: [[TMP0:%.*]] = sext i32 [[OFFSET_NONZERO]] to i64
-; CHECK-NEXT: [[TMP1:%.*]] = shl nsw i64 [[TMP0]], 1
-; CHECK-NEXT: [[TMP2:%.*]] = add nsw i64 [[TMP1]], 84
-; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, ptr [[A]], i64 [[TMP2]]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[LSR_IV1:%.*]] = phi ptr [ [[UGLYGEP2:%.*]], [[FOR_BODY]] ], [ [[UGLYGEP]], [[ENTRY:%.*]] ]
+; CHECK-NEXT: [[LSR_IV:%.*]] = phi i32 [ [[LSR_IV_NEXT:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY]] ]
; CHECK-NEXT: store i32 1, ptr [[LSR_IV1]], align 4
+; CHECK-NEXT: [[LSR_IV_NEXT]] = add nsw i32 [[LSR_IV]], 1
; CHECK-NEXT: [[UGLYGEP2]] = getelementptr i8, ptr [[LSR_IV1]], i32 [[OFFSET_NONZERO]]
-; CHECK-NEXT: [[LSR_FOLD_TERM_COND_REPLACED_TERM_COND:%.*]] = icmp eq ptr [[UGLYGEP2]], [[SCEVGEP]]
-; CHECK-NEXT: br i1 [[LSR_FOLD_TERM_COND_REPLACED_TERM_COND]], label [[FOR_END:%.*]], label [[FOR_BODY]]
+; CHECK-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i32 [[LSR_IV_NEXT]], 2
+; CHECK-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_END:%.*]], label [[FOR_BODY]]
; CHECK: for.end:
; CHECK-NEXT: ret void
;
More information about the llvm-commits
mailing list