[PATCH] D126503: [SCEV] Use fact that B >u 0 for A <u B in applyLoopGuards.

[Florian Hahn via Phabricator via llvm-commits]

fhahn created this revision.
fhahn added reviewers: efriedma, nikic, reames, mkazantsev.
Herald added a subscriber: hiraditya.
Herald added a project: All.
fhahn requested review of this revision.
Herald added a project: LLVM.

If LHS <u RHS holds, RHS should be guaranteed to be > 0. By using
using 'umax(RHS, 1) -1' instead of 'RHS - 1' the results in
applyLoopGuards can be improved in some cases.

Note that the TODO for the tests mentioned the max BTC being 11, but
unless I am missing something 10 should be correct.

https://alive2.llvm.org/ce/z/44nP7F


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D126503

Files:
  llvm/lib/Analysis/ScalarEvolution.cpp
  llvm/test/Analysis/ScalarEvolution/max-backedge-taken-count-guard-info.ll


Index: llvm/test/Analysis/ScalarEvolution/max-backedge-taken-count-guard-info.ll
===================================================================
--- llvm/test/Analysis/ScalarEvolution/max-backedge-taken-count-guard-info.ll
+++ llvm/test/Analysis/ScalarEvolution/max-backedge-taken-count-guard-info.ll
@@ -299,19 +299,18 @@
   ret void
 }
 
-; TODO: Currently we miss getting the tightest max backedge-taken count (11).
 define void @test_multiple_var_guards_order1(i32* nocapture %a, i64 %i, i64 %N) {
 ; CHECK-LABEL: 'test_multiple_var_guards_order1'
 ; CHECK-NEXT:  Classifying expressions for: @test_multiple_var_guards_order1
 ; CHECK-NEXT:    %iv = phi i64 [ %iv.next, %loop ], [ 0, %guardbb ]
-; CHECK-NEXT:    --> {0,+,1}<nuw><nsw><%loop> U: [0,-9223372036854775808) S: [0,-9223372036854775808) Exits: %i LoopDispositions: { %loop: Computable }
+; CHECK-NEXT:    --> {0,+,1}<nuw><nsw><%loop> U: [0,11) S: [0,11) Exits: %i LoopDispositions: { %loop: Computable }
 ; CHECK-NEXT:    %idx = getelementptr inbounds i32, i32* %a, i64 %iv
 ; CHECK-NEXT:    --> {%a,+,4}<nuw><%loop> U: full-set S: full-set Exits: ((4 * %i) + %a) LoopDispositions: { %loop: Computable }
 ; CHECK-NEXT:    %iv.next = add nuw nsw i64 %iv, 1
-; CHECK-NEXT:    --> {1,+,1}<nuw><%loop> U: [1,0) S: [1,0) Exits: (1 + %i) LoopDispositions: { %loop: Computable }
+; CHECK-NEXT:    --> {1,+,1}<nuw><nsw><%loop> U: [1,12) S: [1,12) Exits: (1 + %i) LoopDispositions: { %loop: Computable }
 ; CHECK-NEXT:  Determining loop execution counts for: @test_multiple_var_guards_order1
 ; CHECK-NEXT:  Loop %loop: backedge-taken count is %i
-; CHECK-NEXT:  Loop %loop: max backedge-taken count is -1
+; CHECK-NEXT:  Loop %loop: max backedge-taken count is 10
 ; CHECK-NEXT:  Loop %loop: Predicated backedge-taken count is %i
 ; CHECK-NEXT:   Predicates:
 ; CHECK:       Loop %loop: Trip multiple is 1
@@ -336,19 +335,18 @@
   ret void
 }
 
-; TODO: Currently we miss getting the tightest max backedge-taken count (11).
 define void @test_multiple_var_guards_order2(i32* nocapture %a, i64 %i, i64 %N) {
 ; CHECK-LABEL: 'test_multiple_var_guards_order2'
 ; CHECK-NEXT:  Classifying expressions for: @test_multiple_var_guards_order2
 ; CHECK-NEXT:    %iv = phi i64 [ %iv.next, %loop ], [ 0, %guardbb ]
-; CHECK-NEXT:    --> {0,+,1}<nuw><nsw><%loop> U: [0,-9223372036854775808) S: [0,-9223372036854775808) Exits: %i LoopDispositions: { %loop: Computable }
+; CHECK-NEXT:    --> {0,+,1}<nuw><nsw><%loop> U: [0,11) S: [0,11) Exits: %i LoopDispositions: { %loop: Computable }
 ; CHECK-NEXT:    %idx = getelementptr inbounds i32, i32* %a, i64 %iv
 ; CHECK-NEXT:    --> {%a,+,4}<nuw><%loop> U: full-set S: full-set Exits: ((4 * %i) + %a) LoopDispositions: { %loop: Computable }
 ; CHECK-NEXT:    %iv.next = add nuw nsw i64 %iv, 1
-; CHECK-NEXT:    --> {1,+,1}<nuw><%loop> U: [1,0) S: [1,0) Exits: (1 + %i) LoopDispositions: { %loop: Computable }
+; CHECK-NEXT:    --> {1,+,1}<nuw><nsw><%loop> U: [1,12) S: [1,12) Exits: (1 + %i) LoopDispositions: { %loop: Computable }
 ; CHECK-NEXT:  Determining loop execution counts for: @test_multiple_var_guards_order2
 ; CHECK-NEXT:  Loop %loop: backedge-taken count is %i
-; CHECK-NEXT:  Loop %loop: max backedge-taken count is -1
+; CHECK-NEXT:  Loop %loop: max backedge-taken count is 10
 ; CHECK-NEXT:  Loop %loop: Predicated backedge-taken count is %i
 ; CHECK-NEXT:   Predicates:
 ; CHECK:       Loop %loop: Trip multiple is 1
@@ -382,10 +380,10 @@
 ; CHECK-NEXT:    %idx = getelementptr inbounds i32, i32* %a, i64 %iv
 ; CHECK-NEXT:    --> {%a,+,4}<nuw><%loop> U: full-set S: full-set Exits: ((4 * %N) + %a) LoopDispositions: { %loop: Computable }
 ; CHECK-NEXT:    %iv.next = add nuw nsw i64 %iv, 1
-; CHECK-NEXT:    --> {1,+,1}<nuw><%loop> U: [1,0) S: [1,0) Exits: (1 + %N) LoopDispositions: { %loop: Computable }
+; CHECK-NEXT:    --> {1,+,1}<nuw><%loop> U: [1,-1) S: [1,-1) Exits: (1 + %N) LoopDispositions: { %loop: Computable }
 ; CHECK-NEXT:  Determining loop execution counts for: @test_multiple_var_guards_cycle
 ; CHECK-NEXT:  Loop %loop: backedge-taken count is %N
-; CHECK-NEXT:  Loop %loop: max backedge-taken count is -1
+; CHECK-NEXT:  Loop %loop: max backedge-taken count is -3
 ; CHECK-NEXT:  Loop %loop: Predicated backedge-taken count is %N
 ; CHECK-NEXT:   Predicates:
 ; CHECK:       Loop %loop: Trip multiple is 1
Index: llvm/lib/Analysis/ScalarEvolution.cpp
===================================================================
--- llvm/lib/Analysis/ScalarEvolution.cpp
+++ llvm/lib/Analysis/ScalarEvolution.cpp
@@ -14472,8 +14472,9 @@
     const SCEV *RewrittenRHS = nullptr;
     switch (Predicate) {
     case CmpInst::ICMP_ULT:
-      RewrittenRHS =
-          getUMinExpr(RewrittenLHS, getMinusSCEV(RHS, getOne(RHS->getType())));
+      RewrittenRHS = getUMinExpr(
+          RewrittenLHS, getMinusSCEV(getUMaxExpr(RHS, getOne(RHS->getType())),
+                                     getOne(RHS->getType())));
       break;
     case CmpInst::ICMP_SLT:
       RewrittenRHS =


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D126503.432394.patch
Type: text/x-patch
Size: 5003 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220526/90b5db81/attachment.bin>