[llvm] 0ad88e7 - [RISCV] Add cost model coverage for floating point sqrt intrinsic

[Philip Reames via llvm-commits]

Author: Philip Reames
Date: 2022-08-24T14:27:27-07:00
New Revision: 0ad88e74eb5bf166a7a482598e7538ee4b73fa3e

URL: https://github.com/llvm/llvm-project/commit/0ad88e74eb5bf166a7a482598e7538ee4b73fa3e
DIFF: https://github.com/llvm/llvm-project/commit/0ad88e74eb5bf166a7a482598e7538ee4b73fa3e.diff

LOG: [RISCV] Add cost model coverage for floating point sqrt intrinsic

Added: 
    llvm/test/Analysis/CostModel/RISCV/sqrt.ll

Modified: 
    

Removed: 
    


################################################################################
diff  --git a/llvm/test/Analysis/CostModel/RISCV/sqrt.ll b/llvm/test/Analysis/CostModel/RISCV/sqrt.ll
new file mode 100644
index 000000000000..9722910224cf
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/RISCV/sqrt.ll
@@ -0,0 +1,64 @@
+; 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,+f,+d -riscv-v-vector-bits-min=-1 | FileCheck %s
+
+define void @sqrt() {
+; CHECK-LABEL: 'sqrt'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %1 = call float @llvm.sqrt.f32(float undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %2 = call <2 x float> @llvm.sqrt.v2f32(<2 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %3 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %4 = call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %5 = call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %6 = call <vscale x 2 x float> @llvm.sqrt.nxv2f32(<vscale x 2 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %7 = call <vscale x 4 x float> @llvm.sqrt.nxv4f32(<vscale x 4 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %8 = call <vscale x 8 x float> @llvm.sqrt.nxv8f32(<vscale x 8 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %9 = call <vscale x 16 x float> @llvm.sqrt.nxv16f32(<vscale x 16 x float> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %10 = call double @llvm.sqrt.f64(double undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %11 = call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %12 = call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %13 = call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %14 = call <16 x double> @llvm.sqrt.v16f64(<16 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %15 = call <vscale x 1 x double> @llvm.sqrt.nxv1f64(<vscale x 1 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %16 = call <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %17 = call <vscale x 4 x double> @llvm.sqrt.nxv4f64(<vscale x 4 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %18 = call <vscale x 8 x double> @llvm.sqrt.nxv8f64(<vscale x 8 x double> undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+  call float @llvm.sqrt.f32(float undef)
+  call <2 x float> @llvm.sqrt.v2f32(<2 x float> undef)
+  call <4 x float> @llvm.sqrt.v4f32(<4 x float> undef)
+  call <8 x float> @llvm.sqrt.v8f32(<8 x float> undef)
+  call <16 x float> @llvm.sqrt.v16f32(<16 x float> undef)
+  call <vscale x 2 x float> @llvm.sqrt.nvx2f32(<vscale x 2 x float> undef)
+  call <vscale x 4 x float> @llvm.sqrt.nvx4f32(<vscale x 4 x float> undef)
+  call <vscale x 8 x float> @llvm.sqrt.nvx8f32(<vscale x 8 x float> undef)
+  call <vscale x 16 x float> @llvm.sqrt.nvx16f32(<vscale x 16 x float> undef)
+  call double @llvm.sqrt.f64(double undef)
+  call <2 x double> @llvm.sqrt.v2f64(<2 x double> undef)
+  call <4 x double> @llvm.sqrt.v4f64(<4 x double> undef)
+  call <8 x double> @llvm.sqrt.v8f64(<8 x double> undef)
+  call <16 x double> @llvm.sqrt.v16f64(<16 x double> undef)
+  call <vscale x 1 x double> @llvm.sqrt.nvx1f64(<vscale x 1 x double> undef)
+  call <vscale x 2 x double> @llvm.sqrt.nvx2f64(<vscale x 2 x double> undef)
+  call <vscale x 4 x double> @llvm.sqrt.nvx4f64(<vscale x 4 x double> undef)
+  call <vscale x 8 x double> @llvm.sqrt.nvx8f64(<vscale x 8 x double> undef)
+  ret void
+}
+
+declare float @llvm.sqrt.f32(float)
+declare <2 x float> @llvm.sqrt.v2f32(<2 x float>)
+declare <4 x float> @llvm.sqrt.v4f32(<4 x float>)
+declare <8 x float> @llvm.sqrt.v8f32(<8 x float>)
+declare <16 x float> @llvm.sqrt.v16f32(<16 x float>)
+declare <vscale x 2 x float> @llvm.sqrt.nvx2f32(<vscale x 2 x float>)
+declare <vscale x 4 x float> @llvm.sqrt.nvx4f32(<vscale x 4 x float>)
+declare <vscale x 8 x float> @llvm.sqrt.nvx8f32(<vscale x 8 x float>)
+declare <vscale x 16 x float> @llvm.sqrt.nvx16f32(<vscale x 16 x float>)
+declare double @llvm.sqrt.f64(double)
+declare <2 x double> @llvm.sqrt.v2f64(<2 x double>)
+declare <4 x double> @llvm.sqrt.v4f64(<4 x double>)
+declare <8 x double> @llvm.sqrt.v8f64(<8 x double>)
+declare <16 x double> @llvm.sqrt.v16f64(<16 x double>)
+declare <vscale x 1 x double> @llvm.sqrt.nvx1f64(<vscale x 1 x double>)
+declare <vscale x 2 x double> @llvm.sqrt.nvx2f64(<vscale x 2 x double>)
+declare <vscale x 4 x double> @llvm.sqrt.nvx4f64(<vscale x 4 x double>)
+declare <vscale x 8 x double> @llvm.sqrt.nvx8f64(<vscale x 8 x double>)