[PATCH] D138591: [AAch64] Don't treat SVE scalable extends as free widening instructions

[Dave Green via Phabricator via llvm-commits]

This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rGf2a92db29eb7: [AArch64] Don't treat SVE scalable extends as free widening instructions (authored by dmgreen).

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D138591/new/

https://reviews.llvm.org/D138591

Files:
  llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
  llvm/test/Analysis/CostModel/AArch64/sve-widening-instruction.ll


Index: llvm/test/Analysis/CostModel/AArch64/sve-widening-instruction.ll
===================================================================
--- llvm/test/Analysis/CostModel/AArch64/sve-widening-instruction.ll
+++ llvm/test/Analysis/CostModel/AArch64/sve-widening-instruction.ll
@@ -20,8 +20,8 @@
 
 define <vscale x 8 x i32> @widening_nxv8i16(<vscale x 8 x i16> %in1, <vscale x 8 x i16> %in2) {
 ; CHECK-LABEL: 'widening_nxv8i16'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %in1.ext = zext <vscale x 8 x i16> %in2 to <vscale x 8 x i32>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %in2.ext = zext <vscale x 8 x i16> %in2 to <vscale x 8 x i32>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %in1.ext = zext <vscale x 8 x i16> %in2 to <vscale x 8 x i32>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %in2.ext = zext <vscale x 8 x i16> %in2 to <vscale x 8 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %in.add = add <vscale x 8 x i32> %in1.ext, %in2.ext
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <vscale x 8 x i32> %in.add
 ;
@@ -33,8 +33,8 @@
 
 define <8 x i32> @widening_v8i16_svevl2(<8 x i16> %in1, <8 x i16> %in2) vscale_range(2,16) {
 ; CHECK-LABEL: 'widening_v8i16_svevl2'
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %in1.ext = zext <8 x i16> %in2 to <8 x i32>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %in2.ext = zext <8 x i16> %in2 to <8 x i32>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %in1.ext = zext <8 x i16> %in2 to <8 x i32>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %in2.ext = zext <8 x i16> %in2 to <8 x i32>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %in.add = add <8 x i32> %in1.ext, %in2.ext
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i32> %in.add
 ;
Index: llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
===================================================================
--- llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -1563,8 +1563,11 @@
   };
 
   // Exit early if DstTy is not a vector type whose elements are at least
-  // 16-bits wide.
-  if (!DstTy->isVectorTy() || DstTy->getScalarSizeInBits() < 16)
+  // 16-bits wide. SVE doesn't generally have the same set of instructions to
+  // perform an extend with the add/sub/mul. There are SMULLB style
+  // instructions, but they operate on top/bottom, requiring some sort of lane
+  // interleaving to be used with zext/sext.
+  if (!useNeonVector(DstTy) || DstTy->getScalarSizeInBits() < 16)
     return false;
 
   // Determine if the operation has a widening variant. We consider both the


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D138591.478905.patch
Type: text/x-patch
Size: 2930 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20221130/192e1b4c/attachment-0001.bin>