[AArch64] Add fpext and fpround costs (llvm#119292)

This adds some basic costs for fpext and fpround, many of which were
already handled by the generic costing routines but this does make some
adjustments for larger vector types that can use fcvtn+fcvtn2, as
opposed to fcvtn+fcvtn+concat.

These should now more closely match the codegen from
https://godbolt.org/z/r3P9Mf8ez, for example.

Author: davemgreen

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

@@ -2800,6 +2800,31 @@ InstructionCost AArch64TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst,
       {ISD::SIGN_EXTEND, MVT::v16i32, MVT::v16i8, 6},
       {ISD::ZERO_EXTEND, MVT::v16i32, MVT::v16i8, 6},
 
+      // FP Ext and trunc
+      {ISD::FP_EXTEND, MVT::f64, MVT::f32, 1},     // fcvt
+      {ISD::FP_EXTEND, MVT::v2f64, MVT::v2f32, 1}, // fcvtl
+      {ISD::FP_EXTEND, MVT::v4f64, MVT::v4f32, 2}, // fcvtl+fcvtl2
+      //   FP16
+      {ISD::FP_EXTEND, MVT::f32, MVT::f16, 1},     // fcvt
+      {ISD::FP_EXTEND, MVT::f64, MVT::f16, 1},     // fcvt
+      {ISD::FP_EXTEND, MVT::v4f32, MVT::v4f16, 1}, // fcvtl
+      {ISD::FP_EXTEND, MVT::v8f32, MVT::v8f16, 2}, // fcvtl+fcvtl2
+      {ISD::FP_EXTEND, MVT::v2f64, MVT::v2f16, 2}, // fcvtl+fcvtl
+      {ISD::FP_EXTEND, MVT::v4f64, MVT::v4f16, 3}, // fcvtl+fcvtl2+fcvtl
+      {ISD::FP_EXTEND, MVT::v8f64, MVT::v8f16, 6}, // 2 * fcvtl+fcvtl2+fcvtl
+      // FP Ext and trunc
+      {ISD::FP_ROUND, MVT::f32, MVT::f64, 1},     // fcvt
+      {ISD::FP_ROUND, MVT::v2f32, MVT::v2f64, 1}, // fcvtn
+      {ISD::FP_ROUND, MVT::v4f32, MVT::v4f64, 2}, // fcvtn+fcvtn2
+      //   FP16
+      {ISD::FP_ROUND, MVT::f16, MVT::f32, 1},     // fcvt
+      {ISD::FP_ROUND, MVT::f16, MVT::f64, 1},     // fcvt
+      {ISD::FP_ROUND, MVT::v4f16, MVT::v4f32, 1}, // fcvtn
+      {ISD::FP_ROUND, MVT::v8f16, MVT::v8f32, 2}, // fcvtn+fcvtn2
+      {ISD::FP_ROUND, MVT::v2f16, MVT::v2f64, 2}, // fcvtn+fcvtn
+      {ISD::FP_ROUND, MVT::v4f16, MVT::v4f64, 3}, // fcvtn+fcvtn2+fcvtn
+      {ISD::FP_ROUND, MVT::v8f16, MVT::v8f64, 6}, // 2 * fcvtn+fcvtn2+fcvtn
+
       // LowerVectorINT_TO_FP:
       {ISD::SINT_TO_FP, MVT::v2f32, MVT::v2i32, 1},
       {ISD::SINT_TO_FP, MVT::v4f32, MVT::v4i32, 1},

llvm/test/Analysis/CostModel/AArch64/cast.ll

@@ -274,34 +274,34 @@ define i32 @casts_no_users() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r69 = uitofp i64 undef to double
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r80 = fptrunc double undef to float
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r81 = fptrunc <2 x double> undef to <2 x float>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %r82 = fptrunc <4 x double> undef to <4 x float>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %r83 = fptrunc <8 x double> undef to <8 x float>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %r84 = fptrunc <16 x double> undef to <16 x float>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r82 = fptrunc <4 x double> undef to <4 x float>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %r83 = fptrunc <8 x double> undef to <8 x float>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %r84 = fptrunc <16 x double> undef to <16 x float>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %truncf64f16 = fptrunc double undef to half
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %truncv2f64f16 = fptrunc <2 x double> undef to <2 x half>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %truncv2f64f16 = fptrunc <2 x double> undef to <2 x half>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %truncv4f64f16 = fptrunc <4 x double> undef to <4 x half>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %truncv8f64f16 = fptrunc <8 x double> undef to <8 x half>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %truncv16f64f16 = fptrunc <16 x double> undef to <16 x half>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %truncv8f64f16 = fptrunc <8 x double> undef to <8 x half>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %truncv16f64f16 = fptrunc <16 x double> undef to <16 x half>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %truncv32f16 = fptrunc float undef to half
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %truncv2f32f16 = fptrunc <2 x float> undef to <2 x half>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %truncv4f32f16 = fptrunc <4 x float> undef to <4 x half>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %truncv8f32f16 = fptrunc <8 x float> undef to <8 x half>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %truncv16f32f16 = fptrunc <16 x float> undef to <16 x half>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %truncv8f32f16 = fptrunc <8 x float> undef to <8 x half>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %truncv16f32f16 = fptrunc <16 x float> undef to <16 x half>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r85 = fpext float undef to double
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r86 = fpext <2 x float> undef to <2 x double>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %r87 = fpext <4 x float> undef to <4 x double>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %r88 = fpext <8 x float> undef to <8 x double>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %r89 = fpext <16 x float> undef to <16 x double>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r87 = fpext <4 x float> undef to <4 x double>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %r88 = fpext <8 x float> undef to <8 x double>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %r89 = fpext <16 x float> undef to <16 x double>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %extf16f32 = fpext half undef to float
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %extv2f16f32 = fpext <2 x half> undef to <2 x float>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %extv4f16f32 = fpext <4 x half> undef to <4 x float>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %extv8f16f32 = fpext <8 x half> undef to <8 x float>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %extv16f16f32 = fpext <16 x half> undef to <16 x float>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %extv8f16f32 = fpext <8 x half> undef to <8 x float>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %extv16f16f32 = fpext <16 x half> undef to <16 x float>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %extf16f64 = fpext half undef to double
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %extv2f16f64 = fpext <2 x half> undef to <2 x double>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %extv2f16f64 = fpext <2 x half> undef to <2 x double>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %extv4f16f64 = fpext <4 x half> undef to <4 x double>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %extv8f16f64 = fpext <8 x half> undef to <8 x double>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %extv16f16f64 = fpext <16 x half> undef to <16 x double>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %extv8f16f64 = fpext <8 x half> undef to <8 x double>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %extv16f16f64 = fpext <16 x half> undef to <16 x double>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r90 = fptoui <2 x float> undef to <2 x i1>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r91 = fptosi <2 x float> undef to <2 x i1>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r92 = fptoui <2 x float> undef to <2 x i8>

llvm/test/Analysis/CostModel/AArch64/sve-cast.ll

@@ -600,14 +600,14 @@ define i32 @casts_no_users() {
 ; CHECK-SVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r69 = uitofp i64 undef to double
 ; CHECK-SVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r80 = fptrunc double undef to float
 ; CHECK-SVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r81 = fptrunc <2 x double> undef to <2 x float>
-; CHECK-SVE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %r82 = fptrunc <4 x double> undef to <4 x float>
-; CHECK-SVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %r83 = fptrunc <8 x double> undef to <8 x float>
-; CHECK-SVE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %r84 = fptrunc <16 x double> undef to <16 x float>
+; CHECK-SVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r82 = fptrunc <4 x double> undef to <4 x float>
+; CHECK-SVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %r83 = fptrunc <8 x double> undef to <8 x float>
+; CHECK-SVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %r84 = fptrunc <16 x double> undef to <16 x float>
 ; CHECK-SVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r85 = fpext float undef to double
 ; CHECK-SVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r86 = fpext <2 x float> undef to <2 x double>
-; CHECK-SVE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %r87 = fpext <4 x float> undef to <4 x double>
-; CHECK-SVE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %r88 = fpext <8 x float> undef to <8 x double>
-; CHECK-SVE-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %r89 = fpext <16 x float> undef to <16 x double>
+; CHECK-SVE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r87 = fpext <4 x float> undef to <4 x double>
+; CHECK-SVE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %r88 = fpext <8 x float> undef to <8 x double>
+; CHECK-SVE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %r89 = fpext <16 x float> undef to <16 x double>
 ; CHECK-SVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r90 = fptoui <2 x float> undef to <2 x i1>
 ; CHECK-SVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r91 = fptosi <2 x float> undef to <2 x i1>
 ; CHECK-SVE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %r92 = fptoui <2 x float> undef to <2 x i8>