[llvm] r253482 - [Aarch64] Add cost for missing extensions.

[Matthew Simpson via llvm-commits]

Author: mssimpso
Date: Wed Nov 18 12:03:06 2015
New Revision: 253482

URL: http://llvm.org/viewvc/llvm-project?rev=253482&view=rev
Log:
[Aarch64] Add cost for missing extensions.

This patch adds a cost estimate for some missing sign and zero extensions. The
costs were determined by counting the number of shift instructions generated
without context for each new extension.

Differential Revision: http://reviews.llvm.org/D14730

Modified:
    llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

Modified: llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp?rev=253482&r1=253481&r2=253482&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp (original)
+++ llvm/trunk/lib/Target/AArch64/AArch64TargetTransformInfo.cpp Wed Nov 18 12:03:06 2015
@@ -188,28 +188,29 @@ int AArch64TTIImpl::getCastInstrCost(uns
 
   static const TypeConversionCostTblEntry
   ConversionTbl[] = {
-    { ISD::SIGN_EXTEND, MVT::v4i32, MVT::v4i16, 0 },
-    { ISD::ZERO_EXTEND, MVT::v4i32, MVT::v4i16, 0 },
-    { ISD::SIGN_EXTEND, MVT::v2i64, MVT::v2i32, 1 },
-    { ISD::ZERO_EXTEND, MVT::v2i64, MVT::v2i32, 1 },
-    { ISD::TRUNCATE,    MVT::v4i32, MVT::v4i64, 0 },
-    { ISD::TRUNCATE,    MVT::v4i16, MVT::v4i32, 1 },
+    { ISD::TRUNCATE, MVT::v4i16, MVT::v4i32,  1 },
+    { ISD::TRUNCATE, MVT::v4i32, MVT::v4i64,  0 },
+    { ISD::TRUNCATE, MVT::v8i8,  MVT::v8i32,  3 },
+    { ISD::TRUNCATE, MVT::v16i8, MVT::v16i32, 6 },
 
     // The number of shll instructions for the extension.
-    { ISD::SIGN_EXTEND, MVT::v4i64, MVT::v4i16, 3 },
-    { ISD::ZERO_EXTEND, MVT::v4i64, MVT::v4i16, 3 },
-    { ISD::SIGN_EXTEND, MVT::v8i32, MVT::v8i8, 3 },
-    { ISD::ZERO_EXTEND, MVT::v8i32, MVT::v8i8, 3 },
-    { ISD::SIGN_EXTEND, MVT::v8i64, MVT::v8i8, 7 },
-    { ISD::ZERO_EXTEND, MVT::v8i64, MVT::v8i8, 7 },
-    { ISD::SIGN_EXTEND, MVT::v8i64, MVT::v8i16, 6 },
-    { ISD::ZERO_EXTEND, MVT::v8i64, MVT::v8i16, 6 },
+    { ISD::SIGN_EXTEND, MVT::v4i64,  MVT::v4i16, 3 },
+    { ISD::ZERO_EXTEND, MVT::v4i64,  MVT::v4i16, 3 },
+    { ISD::SIGN_EXTEND, MVT::v4i64,  MVT::v4i32, 2 },
+    { ISD::ZERO_EXTEND, MVT::v4i64,  MVT::v4i32, 2 },
+    { ISD::SIGN_EXTEND, MVT::v8i32,  MVT::v8i8,  3 },
+    { ISD::ZERO_EXTEND, MVT::v8i32,  MVT::v8i8,  3 },
+    { ISD::SIGN_EXTEND, MVT::v8i32,  MVT::v8i16, 2 },
+    { ISD::ZERO_EXTEND, MVT::v8i32,  MVT::v8i16, 2 },
+    { ISD::SIGN_EXTEND, MVT::v8i64,  MVT::v8i8,  7 },
+    { ISD::ZERO_EXTEND, MVT::v8i64,  MVT::v8i8,  7 },
+    { ISD::SIGN_EXTEND, MVT::v8i64,  MVT::v8i16, 6 },
+    { ISD::ZERO_EXTEND, MVT::v8i64,  MVT::v8i16, 6 },
+    { ISD::SIGN_EXTEND, MVT::v16i16, MVT::v16i8, 2 },
+    { ISD::ZERO_EXTEND, MVT::v16i16, MVT::v16i8, 2 },
     { ISD::SIGN_EXTEND, MVT::v16i32, MVT::v16i8, 6 },
     { ISD::ZERO_EXTEND, MVT::v16i32, MVT::v16i8, 6 },
 
-    { ISD::TRUNCATE,    MVT::v16i8, MVT::v16i32, 6 },
-    { ISD::TRUNCATE,    MVT::v8i8, MVT::v8i32, 3 },
-
     // LowerVectorINT_TO_FP:
     { ISD::SINT_TO_FP, MVT::v2f32, MVT::v2i32, 1 },
     { ISD::SINT_TO_FP, MVT::v4f32, MVT::v4i32, 1 },