[TTI] Check type legalization of both src and result for fpto{u|s}i.sat. #147657

ElvisWang123 · 2025-07-09T05:57:30Z

For the cast instructions such ass fptoui.sat, fptosi.sat, need to check
both type of the source and the result type can be lowering legally. If
one of them is invalid, return invalid cost.

--
Fixes #142973.

For the cast instructions such ass fptoui.sat, fptosi.sat, need to check both type of the source and the result type can be lowering legally. If one of them is invalid, return invalid cost.

llvmbot · 2025-07-09T05:58:01Z

@llvm/pr-subscribers-llvm-analysis

Author: Elvis Wang (ElvisWang123)

Changes

For the cast instructions such ass fptoui.sat, fptosi.sat, need to check
both type of the source and the result type can be lowering legally. If
one of them is invalid, return invalid cost.

--
Fixes #142973.

Patch is 77.72 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/147657.diff

2 Files Affected:

(modified) llvm/include/llvm/CodeGen/BasicTTIImpl.h (+8-4)
(added) llvm/test/Analysis/CostModel/RISCV/cast-sat.ll (+583)

diff --git a/llvm/include/llvm/CodeGen/BasicTTIImpl.h b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
index 2b9be43eadb7a..079a405be3eba 100644
--- a/llvm/include/llvm/CodeGen/BasicTTIImpl.h
+++ b/llvm/include/llvm/CodeGen/BasicTTIImpl.h
@@ -2486,11 +2486,15 @@ class BasicTTIImplBase : public TargetTransformInfoImplCRTPBase<T> {
       ISD = ISD::UMULO;
       break;
     case Intrinsic::fptosi_sat:
-      ISD = ISD::FP_TO_SINT_SAT;
-      break;
-    case Intrinsic::fptoui_sat:
-      ISD = ISD::FP_TO_UINT_SAT;
+    case Intrinsic::fptoui_sat: {
+      std::pair<InstructionCost, MVT> SrcLT = getTypeLegalizationCost(Tys[0]);
+      std::pair<InstructionCost, MVT> RetLT = getTypeLegalizationCost(RetTy);
+      if (!SrcLT.first.isValid() || !RetLT.first.isValid())
+        return InstructionCost::getInvalid();
+      ISD = IID == Intrinsic::fptosi_sat ? ISD::FP_TO_SINT_SAT
+                                         : ISD::FP_TO_UINT_SAT;
       break;
+    }
     case Intrinsic::ctpop:
       ISD = ISD::CTPOP;
       // In case of legalization use TCC_Expensive. This is cheaper than a
diff --git a/llvm/test/Analysis/CostModel/RISCV/cast-sat.ll b/llvm/test/Analysis/CostModel/RISCV/cast-sat.ll
new file mode 100644
index 0000000000000..2306d51c89118
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/RISCV/cast-sat.ll
@@ -0,0 +1,583 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --version 5
+; RUN: opt < %s -mtriple=riscv64 -mattr=+zve32f,+zvl128b,+f,+d,+zfh,+zvfh -passes="print<cost-model>" -cost-kind=throughput 2>&1 -disable-output | FileCheck %s --check-prefixes=CHECK,RV64ZVE32F
+; RUN: opt < %s -mtriple=riscv64 -mattr=+v,+zvl128b,+f,+d,+zfh,+zvfh -passes="print<cost-model>" -cost-kind=throughput 2>&1 -disable-output | FileCheck %s --check-prefixes=CHECK,RV64V
+
+define void @fptoui_sat() {
+; RV64ZVE32F-LABEL: 'fptoui_sat'
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v1f32_v1i8 = call <1 x i8> @llvm.fptoui.sat.v1i8.v1f32(<1 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v1f64_v1i8 = call <1 x i8> @llvm.fptoui.sat.v1i8.v1f64(<1 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v1f32_v1i16 = call <1 x i16> @llvm.fptoui.sat.v1i16.v1f32(<1 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v1f64_v1i16 = call <1 x i16> @llvm.fptoui.sat.v1i16.v1f64(<1 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v1f32_v1i32 = call <1 x i32> @llvm.fptoui.sat.v1i32.v1f32(<1 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v1f64_v1i32 = call <1 x i32> @llvm.fptoui.sat.v1i32.v1f64(<1 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v1f32_v1i64 = call <1 x i64> @llvm.fptoui.sat.v1i64.v1f32(<1 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v1f64_v1i64 = call <1 x i64> @llvm.fptoui.sat.v1i64.v1f64(<1 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v1f32_v1i1 = call <1 x i1> @llvm.fptoui.sat.v1i1.v1f32(<1 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v1f64_v1i1 = call <1 x i1> @llvm.fptoui.sat.v1i1.v1f64(<1 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f32_v2i8 = call <2 x i8> @llvm.fptoui.sat.v2i8.v2f32(<2 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f64_v2i8 = call <2 x i8> @llvm.fptoui.sat.v2i8.v2f64(<2 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f32_v2i16 = call <2 x i16> @llvm.fptoui.sat.v2i16.v2f32(<2 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f64_v2i16 = call <2 x i16> @llvm.fptoui.sat.v2i16.v2f64(<2 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f32_v2i32 = call <2 x i32> @llvm.fptoui.sat.v2i32.v2f32(<2 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f64_v2i32 = call <2 x i32> @llvm.fptoui.sat.v2i32.v2f64(<2 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v2f32_v2i64 = call <2 x i64> @llvm.fptoui.sat.v2i64.v2f32(<2 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v2f64_v2i64 = call <2 x i64> @llvm.fptoui.sat.v2i64.v2f64(<2 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f32_v2i1 = call <2 x i1> @llvm.fptoui.sat.v2i1.v2f32(<2 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f64_v2i1 = call <2 x i1> @llvm.fptoui.sat.v2i1.v2f64(<2 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f32_v4i8 = call <4 x i8> @llvm.fptoui.sat.v4i8.v4f32(<4 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f64_v4i8 = call <4 x i8> @llvm.fptoui.sat.v4i8.v4f64(<4 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f32_v4i16 = call <4 x i16> @llvm.fptoui.sat.v4i16.v4f32(<4 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f64_v4i16 = call <4 x i16> @llvm.fptoui.sat.v4i16.v4f64(<4 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f32_v4i32 = call <4 x i32> @llvm.fptoui.sat.v4i32.v4f32(<4 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f64_v4i32 = call <4 x i32> @llvm.fptoui.sat.v4i32.v4f64(<4 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v4f32_v4i64 = call <4 x i64> @llvm.fptoui.sat.v4i64.v4f32(<4 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v4f64_v4i64 = call <4 x i64> @llvm.fptoui.sat.v4i64.v4f64(<4 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f32_v4i1 = call <4 x i1> @llvm.fptoui.sat.v4i1.v4f32(<4 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f64_v4i1 = call <4 x i1> @llvm.fptoui.sat.v4i1.v4f64(<4 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8f32_v8i8 = call <8 x i8> @llvm.fptoui.sat.v8i8.v8f32(<8 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8f64_v8i8 = call <8 x i8> @llvm.fptoui.sat.v8i8.v8f64(<8 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8f32_v8i16 = call <8 x i16> @llvm.fptoui.sat.v8i16.v8f32(<8 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8f64_v8i16 = call <8 x i16> @llvm.fptoui.sat.v8i16.v8f64(<8 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8f32_v8i32 = call <8 x i32> @llvm.fptoui.sat.v8i32.v8f32(<8 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8f64_v8i32 = call <8 x i32> @llvm.fptoui.sat.v8i32.v8f64(<8 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v8f32_v8i64 = call <8 x i64> @llvm.fptoui.sat.v8i64.v8f32(<8 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v8f64_v8i64 = call <8 x i64> @llvm.fptoui.sat.v8i64.v8f64(<8 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8f32_v8i1 = call <8 x i1> @llvm.fptoui.sat.v8i1.v8f32(<8 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8f64_v8i1 = call <8 x i1> @llvm.fptoui.sat.v8i1.v8f64(<8 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv1f32_nxv1i8 = call <vscale x 1 x i8> @llvm.fptoui.sat.nxv1i8.nxv1f32(<vscale x 1 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv1f64_nxv1i8 = call <vscale x 1 x i8> @llvm.fptoui.sat.nxv1i8.nxv1f64(<vscale x 1 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv1f32_nxv1i16 = call <vscale x 1 x i16> @llvm.fptoui.sat.nxv1i16.nxv1f32(<vscale x 1 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv1f64_nxv1i16 = call <vscale x 1 x i16> @llvm.fptoui.sat.nxv1i16.nxv1f64(<vscale x 1 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv1f32_nxv1i32 = call <vscale x 1 x i32> @llvm.fptoui.sat.nxv1i32.nxv1f32(<vscale x 1 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv1f64_nxv1i32 = call <vscale x 1 x i32> @llvm.fptoui.sat.nxv1i32.nxv1f64(<vscale x 1 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv1f32_nxv1i64 = call <vscale x 1 x i64> @llvm.fptoui.sat.nxv1i64.nxv1f32(<vscale x 1 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv1f64_nxv1i64 = call <vscale x 1 x i64> @llvm.fptoui.sat.nxv1i64.nxv1f64(<vscale x 1 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv1f32_nxv1i1 = call <vscale x 1 x i1> @llvm.fptoui.sat.nxv1i1.nxv1f32(<vscale x 1 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv1f64_nxv1i1 = call <vscale x 1 x i1> @llvm.fptoui.sat.nxv1i1.nxv1f64(<vscale x 1 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv2f32_nxv2i8 = call <vscale x 2 x i8> @llvm.fptoui.sat.nxv2i8.nxv2f32(<vscale x 2 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv2f64_nxv2i8 = call <vscale x 2 x i8> @llvm.fptoui.sat.nxv2i8.nxv2f64(<vscale x 2 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv2f32_nxv2i16 = call <vscale x 2 x i16> @llvm.fptoui.sat.nxv2i16.nxv2f32(<vscale x 2 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv2f64_nxv2i16 = call <vscale x 2 x i16> @llvm.fptoui.sat.nxv2i16.nxv2f64(<vscale x 2 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv2f32_nxv2i32 = call <vscale x 2 x i32> @llvm.fptoui.sat.nxv2i32.nxv2f32(<vscale x 2 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv2f64_nxv2i32 = call <vscale x 2 x i32> @llvm.fptoui.sat.nxv2i32.nxv2f64(<vscale x 2 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv2f32_nxv2i64 = call <vscale x 2 x i64> @llvm.fptoui.sat.nxv2i64.nxv2f32(<vscale x 2 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv2f64_nxv2i64 = call <vscale x 2 x i64> @llvm.fptoui.sat.nxv2i64.nxv2f64(<vscale x 2 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv2f32_nxv2i1 = call <vscale x 2 x i1> @llvm.fptoui.sat.nxv2i1.nxv2f32(<vscale x 2 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv2f64_nxv2i1 = call <vscale x 2 x i1> @llvm.fptoui.sat.nxv2i1.nxv2f64(<vscale x 2 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv4f32_nxv4i8 = call <vscale x 4 x i8> @llvm.fptoui.sat.nxv4i8.nxv4f32(<vscale x 4 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv4f64_nxv4i8 = call <vscale x 4 x i8> @llvm.fptoui.sat.nxv4i8.nxv4f64(<vscale x 4 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv4f32_nxv4i16 = call <vscale x 4 x i16> @llvm.fptoui.sat.nxv4i16.nxv4f32(<vscale x 4 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv4f64_nxv4i16 = call <vscale x 4 x i16> @llvm.fptoui.sat.nxv4i16.nxv4f64(<vscale x 4 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv4f32_nxv4i32 = call <vscale x 4 x i32> @llvm.fptoui.sat.nxv4i32.nxv4f32(<vscale x 4 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv4f64_nxv4i32 = call <vscale x 4 x i32> @llvm.fptoui.sat.nxv4i32.nxv4f64(<vscale x 4 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv4f32_nxv4i64 = call <vscale x 4 x i64> @llvm.fptoui.sat.nxv4i64.nxv4f32(<vscale x 4 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv4f64_nxv4i64 = call <vscale x 4 x i64> @llvm.fptoui.sat.nxv4i64.nxv4f64(<vscale x 4 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv4f32_nxv4i1 = call <vscale x 4 x i1> @llvm.fptoui.sat.nxv4i1.nxv4f32(<vscale x 4 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv4f64_nxv4i1 = call <vscale x 4 x i1> @llvm.fptoui.sat.nxv4i1.nxv4f64(<vscale x 4 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv8f32_nxv8i8 = call <vscale x 8 x i8> @llvm.fptoui.sat.nxv8i8.nxv8f32(<vscale x 8 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv8f64_nxv8i8 = call <vscale x 8 x i8> @llvm.fptoui.sat.nxv8i8.nxv8f64(<vscale x 8 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv8f32_nxv8i16 = call <vscale x 8 x i16> @llvm.fptoui.sat.nxv8i16.nxv8f32(<vscale x 8 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv8f64_nxv8i16 = call <vscale x 8 x i16> @llvm.fptoui.sat.nxv8i16.nxv8f64(<vscale x 8 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv8f32_nxv8i32 = call <vscale x 8 x i32> @llvm.fptoui.sat.nxv8i32.nxv8f32(<vscale x 8 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv8f64_nxv8i32 = call <vscale x 8 x i32> @llvm.fptoui.sat.nxv8i32.nxv8f64(<vscale x 8 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv8f32_nxv8i64 = call <vscale x 8 x i64> @llvm.fptoui.sat.nxv8i64.nxv8f32(<vscale x 8 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv8f64_nxv8i64 = call <vscale x 8 x i64> @llvm.fptoui.sat.nxv8i64.nxv8f64(<vscale x 8 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv8f32_nxv8i1 = call <vscale x 8 x i1> @llvm.fptoui.sat.nxv8i1.nxv8f32(<vscale x 8 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv8f64_nxv8i1 = call <vscale x 8 x i1> @llvm.fptoui.sat.nxv8i1.nxv8f64(<vscale x 8 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv16f32_nxv16i8 = call <vscale x 16 x i8> @llvm.fptoui.sat.nxv16i8.nxv16f32(<vscale x 16 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv16f64_nxv16i8 = call <vscale x 16 x i8> @llvm.fptoui.sat.nxv16i8.nxv16f64(<vscale x 16 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv16f32_nxv16i16 = call <vscale x 16 x i16> @llvm.fptoui.sat.nxv16i16.nxv16f32(<vscale x 16 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv16f64_nxv16i16 = call <vscale x 16 x i16> @llvm.fptoui.sat.nxv16i16.nxv16f64(<vscale x 16 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv16f32_nxv16i32 = call <vscale x 16 x i32> @llvm.fptoui.sat.nxv16i32.nxv16f32(<vscale x 16 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv16f64_nxv16i32 = call <vscale x 16 x i32> @llvm.fptoui.sat.nxv16i32.nxv16f64(<vscale x 16 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv16f32_nxv16i64 = call <vscale x 16 x i64> @llvm.fptoui.sat.nxv16i64.nxv16f32(<vscale x 16 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv16f64_nxv16i64 = call <vscale x 16 x i64> @llvm.fptoui.sat.nxv16i64.nxv16f64(<vscale x 16 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %nxv16f32_nxv16i1 = call <vscale x 16 x i1> @llvm.fptoui.sat.nxv16i1.nxv16f32(<vscale x 16 x float> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Invalid cost for instruction: %nxv16f64_nxv16i1 = call <vscale x 16 x i1> @llvm.fptoui.sat.nxv16i1.nxv16f64(<vscale x 16 x double> undef)
+; RV64ZVE32F-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; RV64V-LABEL: 'fptoui_sat'
+; RV64V-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v1f32_v1i8 = call <1 x i8> @llvm.fptoui.sat.v1i8.v1f32(<1 x float> undef)
+; RV64V-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v1f64_v1i8 = call <1 x i8> @llvm.fptoui.sat.v1i8.v1f64(<1 x double> undef)
+; RV64V-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v1f32_v1i16 = call <1 x i16> @llvm.fptoui.sat.v1i16.v1f32(<1 x float> undef)
+; RV64V-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v1f64_v1i16 = call <1 x i16> @llvm.fptoui.sat.v1i16.v1f64(<1 x double> undef)
+; RV64V-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v1f32_v1i32 = call <1 x i32> @llvm.fptoui.sat.v1i32.v1f32(<1 x float> undef)
+; RV64V-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v1f64_v1i32 = call <1 x i32> @llvm.fptoui.sat.v1i32.v1f64(<1 x double> undef)
+; RV64V-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v1f32_v1i64 = call <1 x i64> @llvm.fptoui.sat.v1i64.v1f32(<1 x float> undef)
+; RV64V-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v1f64_v1i64 = call <1 x i64> @llvm.fptoui.sat.v1i64.v1f64(<1 x double> undef)
+; RV64V-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v1f32_v1i1 = call <1 x i1> @llvm.fptoui.sat.v1i1.v1f32(<1 x float> undef)
+; RV64V-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v1f64_v1i1 = call <1 x i1> @llvm.fptoui.sat.v1i1.v1f64(<1 x double> undef)
+; RV64V-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f32_v2i8 = call <2 x i8> @llvm.fptoui.sat.v2i8.v2f32(<2 x float> undef)
+; RV64V-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f64_v2i8 = call <2 x i8> @llvm.fptoui.sat.v2i8.v2f64(<2 x double> undef)
+; RV64V-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f32_v2i16 = call <2 x i16> @llvm.fptoui.sat.v2i16.v2f32(<2 x float> undef)
+; RV64V-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f64_v2i16 = call <2 x i16> @llvm.fptoui.sat.v2i16.v2f64(<2 x double> undef)
+; RV64V-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f32_v2i32 = call <2 x i32> @llvm.fptoui.sat.v2i32.v2f32(<2 x float> undef)
+; RV64V-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f64_v2i32 = call <2 x i32> @llvm.fptoui.sat.v2i32.v2f64(<2 x double> undef)
+; RV64V-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f32_v2i64 = call <2 x i64> @llvm.fptoui.sat.v2i64.v2f32(<2 x float> undef)
+; RV64V-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f64_v2i64 = call <2 x i64> @llvm.fptoui.sat.v2i64.v2f64(<2 x double> undef)
+; RV64V-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f32_v2i1 = call <2 x i1> @llvm.fptoui.sat.v2i1.v2f32(<2 x float> undef)
+; RV64V-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f64_v2i1 = call <2 x i1> @llvm.fptoui.sat.v2i1.v2f64(<2 x double> undef)
+; RV64V-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f32_v4i8 = call <4 x i8> @llvm.fptoui.sat.v4i8.v4f32(<4 x float> undef)
+; RV64V-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f64_v4i8 = call <4 x i8> @llvm.fptoui.sat.v4i8.v4f64(<4 x double> undef)
+; RV64V-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f32_v4i16 = call <4 x i16> @llvm.fptoui.sat.v4i16.v4f32(<4 x float> undef)
+; RV64V-NEXT:  Cost Model: Found an est...
[truncated]

github-actions · 2025-07-09T05:59:50Z

✅ With the latest revision this PR passed the undef deprecator.

davemgreen

Can you add a comment explaining why it needs to check the two types. (It might be able to get away with just checking the Tys, RetTy will be checked later? It sounds OK to keep both checks though, to be safe).

Otherwise LGTM.

llvm/include/llvm/CodeGen/BasicTTIImpl.h

topperc · 2025-07-10T00:41:06Z

This fixes the case where one or both of the types is invalid. But don't we need to take the maximum of the two LT.second values when both types are valid but one them splits more than the other?

Co-authored-by: Craig Topper <craig.topper@sifive.com>

ElvisWang123 · 2025-07-10T03:18:52Z

This fixes the case where one or both of the types is invalid. But don't we need to take the maximum of the two LT.second values when both types are valid but one them splits more than the other?

I think would be better to leave this into follow-up PR.

topperc

LGTM

davemgreen · 2025-07-10T06:09:41Z

This fixes the case where one or both of the types is invalid. But don't we need to take the maximum of the two LT.second values when both types are valid but one them splits more than the other?

Perhaps (in a followup) we could say that custom lowering for fptosi.sat isn't meaningful enough (only based on RetTy) to be useful and should always use the fallback costs (line 2758-2783). The target can override it based on the extra information it knows.

ElvisWang123 · 2025-07-10T06:26:26Z

Perhaps (in a followup) we could say that custom lowering for fptosi.sat isn't meaningful enough (only based on RetTy) to be useful and should always use the fallback costs (line 2758-2783). The target can override it based on the extra information it knows.

Sorry I am not sure what is custom lowering. Is that the expansion cost (Line 2533 - 2551)? https://github.com/llvm/llvm-project/pull/147657/files#diff-3bd7f3712428683f95ff47b2f16b54ab32f478d036deb2f6463a5560bc97712bR2533-R2551

davemgreen · 2025-07-10T06:36:14Z

I might be wrong about what is going on, but yes I assumed that the backends marking those opcodes as Custom (

llvm-project/llvm/lib/Target/ARM/ARMISelLowering.cpp

Line 327 in 20becf3

setOperationAction(ISD::FP_TO_SINT_SAT, VT, Custom);

, https://github.com/llvm/llvm-project/blob/20becf373edcf9d568f8904c2b473e6b48500787/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp#L2060,

llvm-project/llvm/lib/Target/RISCV/RISCVISelLowering.cpp

Line 835 in 20becf3

setOperationAction({ISD::FP_TO_SINT_SAT, ISD::FP_TO_UINT_SAT}, VT,

) makes the cost model use the isOperationCustom cost of 2 in the code you pointed to. That might not be very useful for a lot of types though (it doesn't consider the Tys[0], only RetTy), and maybe for this particular operation it isn't going to be correct enough to be useful.

ElvisWang123 · 2025-07-10T06:44:14Z

Thanks for information! 😃

Will try to use fallback implementation or improve the cost of custom lowering in the followup patch.

arsenm · 2025-07-10T07:00:52Z

llvm/include/llvm/CodeGen/BasicTTIImpl.h

+      std::pair<InstructionCost, MVT> RetLT = getTypeLegalizationCost(RetTy);
+
+      // For cast instructions, types are different between source and
+      // destination. Also need to check if the source type can be legalize.


I don't understand this, any type should be legalizable. Why would this ever return an invalid cost?

Some of the vector type might not be legalize if the target not support.

For example, fptoui.sat(<vscale x 1 x double> ...) is illegal type under riscv64, +zve32f (target only support f32 vectors no f64 vector support) and cannot be scalarize since the element counts is unknown at compile time. So the cost of fptoui.sat(<vscale x 1 x double> ...) should be invalid.

ElvisWang123 added 2 commits July 8, 2025 21:58

Precommit test case.

9253fc6

[TTI] Check type legalization of both src and result for fpto{u|s}i.sat.

6b8397d

For the cast instructions such ass fptoui.sat, fptosi.sat, need to check both type of the source and the result type can be lowering legally. If one of them is invalid, return invalid cost.

ElvisWang123 requested review from arsenm, RKSimon, davemgreen and topperc July 9, 2025 05:57

llvmbot added the llvm:analysis Includes value tracking, cost tables and constant folding label Jul 9, 2025

fixup undef value.

31815b2

ElvisWang123 mentioned this pull request Jul 8, 2025

[RISCV][TTI] Implement vector costs for llvm.fpto{u|s}i.sat(). #143655

Open

RKSimon approved these changes Jul 9, 2025

View reviewed changes

davemgreen approved these changes Jul 9, 2025

View reviewed changes

Add comment.

0972f9c

topperc reviewed Jul 10, 2025

View reviewed changes

llvm/include/llvm/CodeGen/BasicTTIImpl.h Outdated Show resolved Hide resolved

Update llvm/include/llvm/CodeGen/BasicTTIImpl.h

23990c0

Co-authored-by: Craig Topper <craig.topper@sifive.com>

topperc approved these changes Jul 10, 2025

View reviewed changes

ElvisWang123 merged commit 2137354 into llvm:main Jul 10, 2025
9 checks passed

ElvisWang123 deleted the fix-cast-sat-invalid-basic branch July 10, 2025 06:44

arsenm reviewed Jul 10, 2025

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

[TTI] Check type legalization of both src and result for fpto{u|s}i.sat. #147657

[TTI] Check type legalization of both src and result for fpto{u|s}i.sat. #147657

ElvisWang123 commented Jul 9, 2025

Uh oh!

llvmbot commented Jul 9, 2025

Uh oh!

github-actions bot commented Jul 9, 2025 •

edited

Loading

Uh oh!

davemgreen left a comment

Uh oh!

Uh oh!

topperc commented Jul 10, 2025

Uh oh!

ElvisWang123 commented Jul 10, 2025

Uh oh!

topperc left a comment

Uh oh!

davemgreen commented Jul 10, 2025

Uh oh!

ElvisWang123 commented Jul 10, 2025

Uh oh!

davemgreen commented Jul 10, 2025

Uh oh!

ElvisWang123 commented Jul 10, 2025

Uh oh!

Uh oh!

arsenm Jul 10, 2025

Uh oh!

ElvisWang123 Jul 10, 2025

Uh oh!

Uh oh!

[TTI] Check type legalization of both src and result for fpto{u|s}i.sat. #147657

[TTI] Check type legalization of both src and result for fpto{u|s}i.sat. #147657

Conversation

ElvisWang123 commented Jul 9, 2025

Uh oh!

llvmbot commented Jul 9, 2025

Uh oh!

github-actions bot commented Jul 9, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

davemgreen left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

topperc commented Jul 10, 2025

Uh oh!

ElvisWang123 commented Jul 10, 2025

Uh oh!

topperc left a comment

Choose a reason for hiding this comment

Uh oh!

davemgreen commented Jul 10, 2025

Uh oh!

ElvisWang123 commented Jul 10, 2025

Uh oh!

davemgreen commented Jul 10, 2025

Uh oh!

ElvisWang123 commented Jul 10, 2025

Uh oh!

Uh oh!

arsenm Jul 10, 2025

Choose a reason for hiding this comment

Uh oh!

ElvisWang123 Jul 10, 2025

Choose a reason for hiding this comment

Uh oh!

Uh oh!

github-actions bot commented Jul 9, 2025 •

edited

Loading