[Aarch64] Add cost for missing extensions.

[dewen]

Summary

This patch adds a cost estimate for some missing sign extensions.
ref: https://reviews.llvm.org/D14730

[dmgreen]

Sounds OK. Can you add UINT_TO_FP too, to keep them symmetrical.

[dewen]

In D130565#3681549, @dmgreen wrote:

Sounds OK. Can you add UINT_TO_FP too, to keep them symmetrical.

Thank you for your review. I'll revise it, thank you.

[dewen]

for example:

define <4 x double> @test_unsigned_v4i32_to_v4f64(<4 x i32> %v) nounwind readnone {
  %conv = uitofp <4 x i32> %v to <4 x double>
  ret <4 x double> %conv
}

define <4 x double> @test_signed_v4i32_to_v4f64(<4 x i32> %v) nounwind readnone {
  %conv = sitofp <4 x i32> %v to <4 x double>
  ret <4 x double> %conv
}

to

.text
        .file   "585_1.ll"
        .globl  test_unsigned_v4i32_to_v4f64    // -- Begin function test_unsigned_v4i32_to_v4f64
        .p2align        2
        .type   test_unsigned_v4i32_to_v4f64,@function
test_unsigned_v4i32_to_v4f64:           // @test_unsigned_v4i32_to_v4f64
// %bb.0:
        ushll2.2d       v1, v0, #0
        ushll.2d        v0, v0, #0
        ucvtf.2d        v1, v1
        ucvtf.2d        v0, v0
        ret
.Lfunc_end0:
        .size   test_unsigned_v4i32_to_v4f64, .Lfunc_end0-test_unsigned_v4i32_to_v4f64
                                        // -- End function
        .globl  test_signed_v4i32_to_v4f64      // -- Begin function test_signed_v4i32_to_v4f64
        .p2align        2
        .type   test_signed_v4i32_to_v4f64,@function
test_signed_v4i32_to_v4f64:             // @test_signed_v4i32_to_v4f64
// %bb.0:
        sshll2.2d       v1, v0, #0
        sshll.2d        v0, v0, #0
        scvtf.2d        v1, v1
        scvtf.2d        v0, v0
        ret
.Lfunc_end1:
        .size   test_signed_v4i32_to_v4f64, .Lfunc_end1-test_signed_v4i32_to_v4f64
                                        // -- End function
        .section        ".note.GNU-stack","",@progbits

[dmgreen]

LGTM Thanks

llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp

ConversionTbl[] = {
     // Complex: to v2f64
     { ISD::SINT_TO_FP, MVT::v2f64, MVT::v2i8,  4 },
     { ISD::SINT_TO_FP, MVT::v2f64, MVT::v2i16, 4 },
     { ISD::SINT_TO_FP, MVT::v2f64, MVT::v2i32, 2 },
     { ISD::UINT_TO_FP, MVT::v2f64, MVT::v2i8,  4 },
     { ISD::UINT_TO_FP, MVT::v2f64, MVT::v2i16, 4 },
     { ISD::UINT_TO_FP, MVT::v2f64, MVT::v2i32, 2 },
 
+    // Complex: to v4f64
+    { ISD::SINT_TO_FP, MVT::v4f64, MVT::v4i32,  4 },
+    { ISD::UINT_TO_FP, MVT::v4f64, MVT::v4i32,  4 },
 
     // LowerVectorFP_TO_INT
     { ISD::FP_TO_SINT, MVT::v2i32, MVT::v2f32, 1 },
     { ISD::FP_TO_SINT, MVT::v4i32, MVT::v4f32, 1 },
     { ISD::FP_TO_SINT, MVT::v2i64, MVT::v2f64, 1 },
     { ISD::FP_TO_UINT, MVT::v2i32, MVT::v2f32, 1 },
     { ISD::FP_TO_UINT, MVT::v4i32, MVT::v4f32, 1 },
     { ISD::FP_TO_UINT, MVT::v2i64, MVT::v2f64, 1 },

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

 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %r198 = uitofp <4 x i64> undef to <4 x float>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %r199 = sitofp <4 x i64> undef to <4 x float>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %r200 = uitofp <4 x i1> undef to <4 x double>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %r201 = sitofp <4 x i1> undef to <4 x double>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %r202 = uitofp <4 x i8> undef to <4 x double>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %r203 = sitofp <4 x i8> undef to <4 x double>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %r204 = uitofp <4 x i16> undef to <4 x double>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %r205 = sitofp <4 x i16> undef to <4 x double>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %r206 = uitofp <4 x i32> undef to <4 x double>
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %r207 = sitofp <4 x i32> undef to <4 x double>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %r206 = uitofp <4 x i32> undef to <4 x double>
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %r207 = sitofp <4 x i32> undef to <4 x double>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r208 = uitofp <4 x i64> undef to <4 x double>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %r209 = sitofp <4 x i64> undef to <4 x double>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %r210 = uitofp <8 x i1> undef to <8 x float>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %r211 = sitofp <8 x i1> undef to <8 x float>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r212 = uitofp <8 x i8> undef to <8 x float>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %r213 = sitofp <8 x i8> undef to <8 x float>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %r214 = uitofp <8 x i16> undef to <8 x float>
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %r215 = sitofp <8 x i16> undef to <8 x float>