[RISCV] Mark FSIN and other math functions as Expand for scalable vec…

…tors. This prevents them from being assumed legal by the cost model. This matches what is done for AArch64 SVE. Reviewed By: reames Differential Revision: https://reviews.llvm.org/D123799
llvm · Jun 10, 2022 · e910511 · e910511
1 parent 2247e4d
commit e910511
Show file tree

Hide file tree

Showing 2 changed files with 63 additions and 0 deletions.
diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -648,6 +648,25 @@ RISCVTargetLowering::RISCVTargetLowering(const TargetMachine &TM,
                           ISD::VECREDUCE_FMIN, ISD::VECREDUCE_FMAX},
                          VT, Custom);
 
+      // Expand FP operations that need libcalls.
+      setOperationAction(ISD::FREM, VT, Expand);
+      setOperationAction(ISD::FPOW, VT, Expand);
+      setOperationAction(ISD::FCOS, VT, Expand);
+      setOperationAction(ISD::FSIN, VT, Expand);
+      setOperationAction(ISD::FSINCOS, VT, Expand);
+      setOperationAction(ISD::FEXP, VT, Expand);
+      setOperationAction(ISD::FEXP2, VT, Expand);
+      setOperationAction(ISD::FLOG, VT, Expand);
+      setOperationAction(ISD::FLOG2, VT, Expand);
+      setOperationAction(ISD::FLOG10, VT, Expand);
+      setOperationAction(ISD::FRINT, VT, Expand);
+      setOperationAction(ISD::FNEARBYINT, VT, Expand);
+
+      setOperationAction(ISD::VECREDUCE_FADD, VT, Custom);
+      setOperationAction(ISD::VECREDUCE_SEQ_FADD, VT, Custom);
+      setOperationAction(ISD::VECREDUCE_FMIN, VT, Custom);
+      setOperationAction(ISD::VECREDUCE_FMAX, VT, Custom);
+
       setOperationAction(ISD::FCOPYSIGN, VT, Legal);
 
       setOperationAction({ISD::LOAD, ISD::STORE}, VT, Custom);

diff --git a/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll b/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll
@@ -0,0 +1,44 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
+; RUN: opt < %s -passes='print<cost-model>' 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v | FileCheck %s
+
+define void @unsupported_fp_ops(<vscale x 4 x float> %vec) {
+; CHECK-LABEL: 'unsupported_fp_ops'
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %sin = call <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float> %vec)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %cos = call <vscale x 4 x float> @llvm.cos.nxv4f32(<vscale x 4 x float> %vec)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %pow = call <vscale x 4 x float> @llvm.pow.nxv4f32(<vscale x 4 x float> %vec, <vscale x 4 x float> %vec)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %powi = call <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float> %vec, i32 42)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %exp = call <vscale x 4 x float> @llvm.exp.nxv4f32(<vscale x 4 x float> %vec)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %exp2 = call <vscale x 4 x float> @llvm.exp2.nxv4f32(<vscale x 4 x float> %vec)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %log = call <vscale x 4 x float> @llvm.log.nxv4f32(<vscale x 4 x float> %vec)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %log2 = call <vscale x 4 x float> @llvm.log2.nxv4f32(<vscale x 4 x float> %vec)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %log10 = call <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float> %vec)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %rint = call <vscale x 4 x float> @llvm.rint.nxv4f32(<vscale x 4 x float> %vec)
+; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %nearbyint = call <vscale x 4 x float> @llvm.nearbyint.nxv4f32(<vscale x 4 x float> %vec)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+
+  %sin = call <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float> %vec)
+  %cos = call <vscale x 4 x float> @llvm.cos.nxv4f32(<vscale x 4 x float> %vec)
+  %pow = call <vscale x 4 x float> @llvm.pow.nxv4f32(<vscale x 4 x float> %vec, <vscale x 4 x float> %vec)
+  %powi = call <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float> %vec, i32 42)
+  %exp = call <vscale x 4 x float> @llvm.exp.nxv4f32(<vscale x 4 x float> %vec)
+  %exp2 = call <vscale x 4 x float> @llvm.exp2.nxv4f32(<vscale x 4 x float> %vec)
+  %log = call <vscale x 4 x float> @llvm.log.nxv4f32(<vscale x 4 x float> %vec)
+  %log2 = call <vscale x 4 x float> @llvm.log2.nxv4f32(<vscale x 4 x float> %vec)
+  %log10 = call <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float> %vec)
+  %rint = call <vscale x 4 x float> @llvm.rint.nxv4f32(<vscale x 4 x float> %vec)
+  %nearbyint = call <vscale x 4 x float> @llvm.nearbyint.nxv4f32(<vscale x 4 x float> %vec)
+  ret void
+}
+
+declare <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float>)
+declare <vscale x 4 x float> @llvm.cos.nxv4f32(<vscale x 4 x float>)
+declare <vscale x 4 x float> @llvm.pow.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
+declare <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float>, i32)
+declare <vscale x 4 x float> @llvm.exp.nxv4f32(<vscale x 4 x float>)
+declare <vscale x 4 x float> @llvm.exp2.nxv4f32(<vscale x 4 x float>)
+declare <vscale x 4 x float> @llvm.log.nxv4f32(<vscale x 4 x float>)
+declare <vscale x 4 x float> @llvm.log2.nxv4f32(<vscale x 4 x float>)
+declare <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float>)
+declare <vscale x 4 x float> @llvm.rint.nxv4f32(<vscale x 4 x float>)
+declare <vscale x 4 x float> @llvm.nearbyint.nxv4f32(<vscale x 4 x float>)