[llvm] f9c01b5 - [LV] Fix '-1U' bits for smallest type in getSmallestAndWidestTypes (#135783)

[via llvm-commits]

Author: Sander de Smalen
Date: 2025-04-17T13:26:15+01:00
New Revision: f9c01b59e3d5239a4e42f94d5edbeb3698a81032

URL: https://github.com/llvm/llvm-project/commit/f9c01b59e3d5239a4e42f94d5edbeb3698a81032
DIFF: https://github.com/llvm/llvm-project/commit/f9c01b59e3d5239a4e42f94d5edbeb3698a81032.diff

LOG: [LV] Fix '-1U' bits for smallest type in getSmallestAndWidestTypes (#135783)

For loops without loads/stores, where the smallest/widest types are
calculated from the reduction, the smallest type returned is always -1U
and it actually returns the smallest type as the widest type. This PR
fixes the calculation.

This follows from
https://github.com/llvm/llvm-project/pull/132190#discussion_r2044232607

Added: 
    

Modified: 
    llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
    llvm/test/Transforms/LoopVectorize/AArch64/smallest-and-widest-types.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index d8a510f59a59f..4c1ed15ee700f 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -4813,17 +4813,16 @@ LoopVectorizationCostModel::getSmallestAndWidestTypes() {
   // if there are no loads/stores in the loop. In this case, check through the
   // reduction variables to determine the maximum width.
   if (ElementTypesInLoop.empty() && !Legal->getReductionVars().empty()) {
-    // Reset MaxWidth so that we can find the smallest type used by recurrences
-    // in the loop.
-    MaxWidth = -1U;
     for (const auto &PhiDescriptorPair : Legal->getReductionVars()) {
       const RecurrenceDescriptor &RdxDesc = PhiDescriptorPair.second;
       // When finding the min width used by the recurrence we need to account
       // for casts on the input operands of the recurrence.
-      MaxWidth = std::min<unsigned>(
-          MaxWidth, std::min<unsigned>(
+      MinWidth = std::min<unsigned>(
+          MinWidth, std::min<unsigned>(
                         RdxDesc.getMinWidthCastToRecurrenceTypeInBits(),
                         RdxDesc.getRecurrenceType()->getScalarSizeInBits()));
+      MaxWidth = std::max<unsigned>(
+          MaxWidth, RdxDesc.getRecurrenceType()->getScalarSizeInBits());
     }
   } else {
     for (Type *T : ElementTypesInLoop) {

diff  --git a/llvm/test/Transforms/LoopVectorize/AArch64/smallest-and-widest-types.ll b/llvm/test/Transforms/LoopVectorize/AArch64/smallest-and-widest-types.ll
index 269562fa70549..b34ba5e38811a 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/smallest-and-widest-types.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/smallest-and-widest-types.ll
@@ -37,7 +37,7 @@ for.end:
 ; chosen. The following 3 cases check 
diff erent combinations of widths.
 
 ; CHECK-LABEL: Checking a loop in 'no_loads_stores_32'
-; CHECK: The Smallest and Widest types: 4294967295 / 32 bits
+; CHECK: The Smallest and Widest types: 32 / 64 bits
 ; CHECK: Selecting VF: 4
 
 define double @no_loads_stores_32(i32 %n) {
@@ -60,7 +60,7 @@ for.end:
 }
 
 ; CHECK-LABEL: Checking a loop in 'no_loads_stores_16'
-; CHECK: The Smallest and Widest types: 4294967295 / 16 bits
+; CHECK: The Smallest and Widest types: 16 / 64 bits
 ; CHECK: Selecting VF: 8
 
 define double @no_loads_stores_16() {
@@ -82,7 +82,7 @@ for.end:
 }
 
 ; CHECK-LABEL: Checking a loop in 'no_loads_stores_8'
-; CHECK: The Smallest and Widest types: 4294967295 / 8 bits
+; CHECK: The Smallest and Widest types: 8 / 32 bits
 ; CHECK: Selecting VF: 16
 
 define float @no_loads_stores_8() {