[PATCH] D66008: [ARM] MVE sext of a load is also free.

[Dave Green via Phabricator via llvm-commits]

dmgreen created this revision.
dmgreen added reviewers: t.p.northover, samparker, SjoerdMeijer, simon_tatham, ostannard.
Herald added subscribers: hiraditya, kristof.beyls, javed.absar.
Herald added a project: LLVM.

MVE also has some sext of loads, which will be free.


https://reviews.llvm.org/D66008

Files:
  llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
  llvm/test/Analysis/CostModel/ARM/cast.ll


Index: llvm/test/Analysis/CostModel/ARM/cast.ll
===================================================================
--- llvm/test/Analysis/CostModel/ARM/cast.ll
+++ llvm/test/Analysis/CostModel/ARM/cast.ll
@@ -862,14 +862,14 @@
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r9 = zext i16 %loadi16 to i64
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r10 = sext i32 %loadi32 to i64
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r11 = zext i32 %loadi32 to i64
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v0 = sext <8 x i8> %loadv8i8 to <8 x i16>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v1 = zext <8 x i8> %loadv8i8 to <8 x i16>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v2 = sext <4 x i8> %loadv4i8 to <4 x i32>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v3 = zext <4 x i8> %loadv4i8 to <4 x i32>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v0 = sext <8 x i8> %loadv8i8 to <8 x i16>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v1 = zext <8 x i8> %loadv8i8 to <8 x i16>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v2 = sext <4 x i8> %loadv4i8 to <4 x i32>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v3 = zext <4 x i8> %loadv4i8 to <4 x i32>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4 = sext <2 x i8> %loadv2i8 to <2 x i64>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v5 = zext <2 x i8> %loadv2i8 to <2 x i64>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v6 = sext <4 x i16> %loadv4i16 to <4 x i32>
-; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v7 = zext <4 x i16> %loadv4i16 to <4 x i32>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v6 = sext <4 x i16> %loadv4i16 to <4 x i32>
+; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %v7 = zext <4 x i16> %loadv4i16 to <4 x i32>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8 = sext <2 x i16> %loadv2i16 to <2 x i64>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %v9 = zext <2 x i16> %loadv2i16 to <2 x i64>
 ; CHECK-MVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v10 = sext <2 x i32> %loadv2i32 to <2 x i64>
Index: llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
===================================================================
--- llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
+++ llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
@@ -180,6 +180,21 @@
     if (const auto *Entry = ConvertCostTableLookup(
             LoadConversionTbl, ISD, DstTy.getSimpleVT(), SrcTy.getSimpleVT()))
       return Entry->Cost;
+
+    static const TypeConversionCostTblEntry MVELoadConversionTbl[] = {
+        {ISD::SIGN_EXTEND, MVT::v4i32, MVT::v4i16, 0},
+        {ISD::ZERO_EXTEND, MVT::v4i32, MVT::v4i16, 0},
+        {ISD::SIGN_EXTEND, MVT::v4i32, MVT::v4i8, 0},
+        {ISD::ZERO_EXTEND, MVT::v4i32, MVT::v4i8, 0},
+        {ISD::SIGN_EXTEND, MVT::v8i16, MVT::v8i8, 0},
+        {ISD::ZERO_EXTEND, MVT::v8i16, MVT::v8i8, 0},
+    };
+    if (SrcTy.isVector() && ST->hasMVEIntegerOps()) {
+      if (const auto *Entry =
+              ConvertCostTableLookup(MVELoadConversionTbl, ISD,
+                                     DstTy.getSimpleVT(), SrcTy.getSimpleVT()))
+        return Entry->Cost;
+    }
   }
 
   // Some arithmetic, load and store operations have specific instructions


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D66008.214357.patch
Type: text/x-patch
Size: 3799 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190809/649e739f/attachment.bin>