[PATCH] D147434: [LV] Improve register pressure estimation if MaxLocalUsers is zero

[Yevgeny Rouban via Phabricator via llvm-commits]

yrouban updated this revision to Diff 520930.
yrouban added a comment.

just rebased over the updated D147588 <https://reviews.llvm.org/D147588>


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D147434/new/

https://reviews.llvm.org/D147434

Files:
  llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
  llvm/test/Transforms/LoopVectorize/X86/interleave-count.ll


Index: llvm/test/Transforms/LoopVectorize/X86/interleave-count.ll
===================================================================
--- llvm/test/Transforms/LoopVectorize/X86/interleave-count.ll
+++ llvm/test/Transforms/LoopVectorize/X86/interleave-count.ll
@@ -5,15 +5,15 @@
 ; RUN:     -force-target-max-vector-interleave=16 -force-target-num-vector-regs=16 \
 ; RUN:     %s 2>&1 | FileCheck %s
 
-; Check that the interleave count is limited by 8 even if there is no
+; Check that the interleave count is not limited by 8 if there is no
 ; register use except one induction variable.
 define void @test(ptr %dst, i64 %size) {
 ; CHECK-LABEL: LV: Checking a loop in 'test'
-; CHECK:       LV: IC is 8
+; CHECK:       LV: IC is 16
 ;
 ; CHECK-LABEL: define void @test
 ;
-; Number of @llvm.masked.scatter() calls is 8.
+; Number of @llvm.masked.scatter() calls is 16.
 ; CHECK:         call void @llvm.masked.scatter.v4f64.v4p0(<4 x double>
 ; CHECK-NEXT:    call void @llvm.masked.scatter.v4f64.v4p0(<4 x double>
 ; CHECK-NEXT:    call void @llvm.masked.scatter.v4f64.v4p0(<4 x double>
@@ -22,6 +22,14 @@
 ; CHECK-NEXT:    call void @llvm.masked.scatter.v4f64.v4p0(<4 x double>
 ; CHECK-NEXT:    call void @llvm.masked.scatter.v4f64.v4p0(<4 x double>
 ; CHECK-NEXT:    call void @llvm.masked.scatter.v4f64.v4p0(<4 x double>
+; CHECK-NEXT:    call void @llvm.masked.scatter.v4f64.v4p0(<4 x double>
+; CHECK-NEXT:    call void @llvm.masked.scatter.v4f64.v4p0(<4 x double>
+; CHECK-NEXT:    call void @llvm.masked.scatter.v4f64.v4p0(<4 x double>
+; CHECK-NEXT:    call void @llvm.masked.scatter.v4f64.v4p0(<4 x double>
+; CHECK-NEXT:    call void @llvm.masked.scatter.v4f64.v4p0(<4 x double>
+; CHECK-NEXT:    call void @llvm.masked.scatter.v4f64.v4p0(<4 x double>
+; CHECK-NEXT:    call void @llvm.masked.scatter.v4f64.v4p0(<4 x double>
+; CHECK-NEXT:    call void @llvm.masked.scatter.v4f64.v4p0(<4 x double>
 ; CHECK-NOT:     call void @llvm.masked.scatter.v4f64.v4p0(<4 x double>
 ;
 entry:
Index: llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
===================================================================
--- llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -5814,15 +5814,17 @@
     if (R.LoopInvariantRegs.find(pair.first) != R.LoopInvariantRegs.end())
       LoopInvariantRegs = R.LoopInvariantRegs[pair.first];
 
-    unsigned TmpIC = llvm::bit_floor((TargetNumRegisters - LoopInvariantRegs) /
-                                     MaxLocalUsers);
-    // Don't count the induction variable as interleaved.
     if (EnableIndVarRegisterHeur) {
-      TmpIC = llvm::bit_floor((TargetNumRegisters - LoopInvariantRegs - 1) /
-                              std::max(1U, (MaxLocalUsers - 1)));
+      // Treat the induction variable as a LoopInvariantReg.
+      assert(MaxLocalUsers);
+      --MaxLocalUsers;
+      ++LoopInvariantRegs;
+    }
+    if (MaxLocalUsers > 0) {
+      unsigned TmpIC = llvm::bit_floor(
+          (TargetNumRegisters - LoopInvariantRegs) / MaxLocalUsers);
+      IC = std::min(IC, TmpIC);
     }
-
-    IC = std::min(IC, TmpIC);
   }
 
   // Clamp the interleave ranges to reasonable counts.


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D147434.520930.patch
Type: text/x-patch
Size: 3189 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230510/f3215f94/attachment.bin>