[RISCV] Fix bug in [l](lrint|lround) vector-cost (#151298)

Follow up on a review of bd66fd0 ([CostModel/RISCV] Fix costs of vector
[l](lrint|lround)) post-landing to fix a subtle problem with the cost
of vector [l](lrint|lround). We should use source LMUL in the case of
a narrowing op.

Co-authored-by: Luke Lau <[email protected]>

Author: artagnon

llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp

@@ -1280,8 +1280,13 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
       } else {
         Ops = {RISCV::VFCVT_X_F_V};
       }
-      return std::max(SrcLT.first, LT.first) *
-             getRISCVInstructionCost(Ops, LT.second, CostKind);
+
+      // We need to use the source LMUL in the case of a narrowing op, and the
+      // destination LMUL otherwise.
+      if (SrcEltSz > DstEltSz)
+        return SrcLT.first *
+               getRISCVInstructionCost(Ops, SrcLT.second, CostKind);
+      return LT.first * getRISCVInstructionCost(Ops, LT.second, CostKind);
     }
     break;
   }

llvm/test/Analysis/CostModel/RISCV/fround.ll

@@ -446,13 +446,13 @@ define void @lrint() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %20 = call <vscale x 16 x i32> @llvm.lrint.nxv16i32.nxv16f32(<vscale x 16 x float> poison)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %21 = call i32 @llvm.lrint.i32.f64(double poison)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = call <2 x i32> @llvm.lrint.v2i32.v2f64(<2 x double> poison)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> poison)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %24 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> poison)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %25 = call <16 x i32> @llvm.lrint.v16i32.v16f64(<16 x double> poison)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %23 = call <4 x i32> @llvm.lrint.v4i32.v4f64(<4 x double> poison)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %24 = call <8 x i32> @llvm.lrint.v8i32.v8f64(<8 x double> poison)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %25 = call <16 x i32> @llvm.lrint.v16i32.v16f64(<16 x double> poison)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 1 x i32> @llvm.lrint.nxv1i32.nxv1f64(<vscale x 1 x double> poison)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 2 x i32> @llvm.lrint.nxv2i32.nxv2f64(<vscale x 2 x double> poison)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %28 = call <vscale x 4 x i32> @llvm.lrint.nxv4i32.nxv4f64(<vscale x 4 x double> poison)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %29 = call <vscale x 8 x i32> @llvm.lrint.nxv8i32.nxv8f64(<vscale x 8 x double> poison)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %27 = call <vscale x 2 x i32> @llvm.lrint.nxv2i32.nxv2f64(<vscale x 2 x double> poison)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %28 = call <vscale x 4 x i32> @llvm.lrint.nxv4i32.nxv4f64(<vscale x 4 x double> poison)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %29 = call <vscale x 8 x i32> @llvm.lrint.nxv8i32.nxv8f64(<vscale x 8 x double> poison)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %30 = call i32 @llvm.lrint.i32.bf16(bfloat poison)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %31 = call <2 x i64> @llvm.lrint.v2i64.v2bf16(<2 x bfloat> poison)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %32 = call <4 x i64> @llvm.lrint.v4i64.v4bf16(<4 x bfloat> poison)
@@ -708,13 +708,13 @@ define void @lround() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %20 = call <vscale x 16 x i32> @llvm.lround.nxv16i32.nxv16f32(<vscale x 16 x float> poison)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %21 = call i32 @llvm.lround.i32.f64(double poison)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %22 = call <2 x i32> @llvm.lround.v2i32.v2f64(<2 x double> poison)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %23 = call <4 x i32> @llvm.lround.v4i32.v4f64(<4 x double> poison)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %24 = call <8 x i32> @llvm.lround.v8i32.v8f64(<8 x double> poison)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %25 = call <16 x i32> @llvm.lround.v16i32.v16f64(<16 x double> poison)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %23 = call <4 x i32> @llvm.lround.v4i32.v4f64(<4 x double> poison)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %24 = call <8 x i32> @llvm.lround.v8i32.v8f64(<8 x double> poison)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %25 = call <16 x i32> @llvm.lround.v16i32.v16f64(<16 x double> poison)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %26 = call <vscale x 1 x i32> @llvm.lround.nxv1i32.nxv1f64(<vscale x 1 x double> poison)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %27 = call <vscale x 2 x i32> @llvm.lround.nxv2i32.nxv2f64(<vscale x 2 x double> poison)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %28 = call <vscale x 4 x i32> @llvm.lround.nxv4i32.nxv4f64(<vscale x 4 x double> poison)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %29 = call <vscale x 8 x i32> @llvm.lround.nxv8i32.nxv8f64(<vscale x 8 x double> poison)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %27 = call <vscale x 2 x i32> @llvm.lround.nxv2i32.nxv2f64(<vscale x 2 x double> poison)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %28 = call <vscale x 4 x i32> @llvm.lround.nxv4i32.nxv4f64(<vscale x 4 x double> poison)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %29 = call <vscale x 8 x i32> @llvm.lround.nxv8i32.nxv8f64(<vscale x 8 x double> poison)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %30 = call <vscale x 16 x i32> @llvm.lround.nxv16i32.nxv16f64(<vscale x 16 x double> poison)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %31 = call i64 @llvm.lround.i64.bf16(bfloat poison)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %32 = call <2 x i64> @llvm.lround.v2i64.v2bf16(<2 x bfloat> poison)