[PATCH] D134732: fix vectorization of library calls

[Tim Schmielau via Phabricator via llvm-commits]

tim.schmielau updated this revision to Diff 463848.
tim.schmielau added a comment.

Re-uploading patch after follow-on patch got mixed in


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D134732/new/

https://reviews.llvm.org/D134732

Files:
  llvm/lib/Analysis/LoopAccessAnalysis.cpp
  llvm/test/Transforms/LoopVectorize/X86/libm-vector-calls-VF2-VF8.ll
  llvm/test/Transforms/LoopVectorize/X86/libm-vector-calls.ll


Index: llvm/test/Transforms/LoopVectorize/X86/libm-vector-calls.ll
===================================================================
--- llvm/test/Transforms/LoopVectorize/X86/libm-vector-calls.ll
+++ llvm/test/Transforms/LoopVectorize/X86/libm-vector-calls.ll
@@ -356,7 +356,8 @@
 !132 = !{!"llvm.loop.vectorize.width", i32 4}
 !133 = !{!"llvm.loop.vectorize.enable", i1 true}
 
-attributes #0 = { nounwind readnone }
+; functions are in fact "readnone" but clang only emits the weaker "writeonly" as other math functions may write errno.
+attributes #0 = { nounwind writeonly }
 
 declare double @sin(double) #0
 declare float @sinf(float) #0
Index: llvm/test/Transforms/LoopVectorize/X86/libm-vector-calls-VF2-VF8.ll
===================================================================
--- llvm/test/Transforms/LoopVectorize/X86/libm-vector-calls-VF2-VF8.ll
+++ llvm/test/Transforms/LoopVectorize/X86/libm-vector-calls-VF2-VF8.ll
@@ -356,7 +356,8 @@
 !132 = !{!"llvm.loop.vectorize.width", i32 8}
 !133 = !{!"llvm.loop.vectorize.enable", i1 true}
 
-attributes #0 = { nounwind readnone }
+; functions are in fact "readnone" but clang only emits the weaker "writeonly" as other math functions may write errno.
+attributes #0 = { nounwind writeonly }
 
 declare double @sin(double) #0
 declare float @sinf(float) #0
Index: llvm/lib/Analysis/LoopAccessAnalysis.cpp
===================================================================
--- llvm/lib/Analysis/LoopAccessAnalysis.cpp
+++ llvm/lib/Analysis/LoopAccessAnalysis.cpp
@@ -2189,8 +2189,8 @@
     // Scan the BB and collect legal loads and stores. Also detect any
     // convergent instructions.
     for (Instruction &I : *BB) {
-      if (auto *Call = dyn_cast<CallBase>(&I)) {
-        if (Call->isConvergent())
+      if (auto *CB = dyn_cast<CallBase>(&I)) {
+        if (CB->isConvergent())
           HasConvergentOp = true;
       }
 
@@ -2205,23 +2205,24 @@
       if (HasComplexMemInst)
         continue;
 
-      // If this is a load, save it. If this instruction can read from memory
-      // but is not a load, then we quit. Notice that we don't handle function
-      // calls that read or write.
-      if (I.mayReadFromMemory()) {
+      if (auto *Call = dyn_cast<CallInst>(&I)) {
         // Many math library functions read the rounding mode. We will only
         // vectorize a loop if it contains known function calls that don't set
         // the flag. Therefore, it is safe to ignore this read from memory.
-        auto *Call = dyn_cast<CallInst>(&I);
-        if (Call && getVectorIntrinsicIDForCall(Call, TLI))
+        if (getVectorIntrinsicIDForCall(Call, TLI))
           continue;
 
         // If the function has an explicit vectorized counterpart, we can safely
         // assume that it can be vectorized.
-        if (Call && !Call->isNoBuiltin() && Call->getCalledFunction() &&
+        if (!Call->isNoBuiltin() && Call->getCalledFunction() &&
             !VFDatabase::getMappings(*Call).empty())
           continue;
+      }
 
+      // If this is a load, save it. If this instruction can read from memory
+      // but is not a load, then we quit. Notice that we don't handle function
+      // calls that read or write.
+      if (I.mayReadFromMemory()) {
         auto *Ld = dyn_cast<LoadInst>(&I);
         if (!Ld) {
           recordAnalysis("CantVectorizeInstruction", Ld)


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D134732.463848.patch
Type: text/x-patch
Size: 3377 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220929/4a28a95d/attachment.bin>