Skip to content

AMDGPU: Add cost model tests for minimumnum/maximumnum #141904

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: users/arsenm/amdgpu/custom-lower-minimumnum-maximumnum-no-ieee-mode
Choose a base branch
from

Conversation

arsenm
Copy link
Contributor

@arsenm arsenm commented May 29, 2025

The f16 cases in particular look broken since every vector size
has the same reported cost.

Copy link
Contributor Author

arsenm commented May 29, 2025

@llvmbot
Copy link
Member

llvmbot commented May 29, 2025

@llvm/pr-subscribers-llvm-analysis

@llvm/pr-subscribers-backend-amdgpu

Author: Matt Arsenault (arsenm)

Changes

The f16 cases in particular look broken since every vector size
has the same reported cost.


Patch is 80.97 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/141904.diff

2 Files Affected:

  • (added) llvm/test/Analysis/CostModel/AMDGPU/maximumnum.ll (+378)
  • (added) llvm/test/Analysis/CostModel/AMDGPU/minimumnum.ll (+378)
diff --git a/llvm/test/Analysis/CostModel/AMDGPU/maximumnum.ll b/llvm/test/Analysis/CostModel/AMDGPU/maximumnum.ll
new file mode 100644
index 0000000000000..3d16f68581fd6
--- /dev/null
+++ b/llvm/test/Analysis/CostModel/AMDGPU/maximumnum.ll
@@ -0,0 +1,378 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx700 < %s | FileCheck -check-prefixes=ALL,GFX7 %s
+; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 < %s | FileCheck -check-prefixes=ALL,GFX9 %s
+; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1200 < %s | FileCheck -check-prefixes=ALL,GFX12 %s
+
+; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx700 < %s | FileCheck -check-prefixes=SIZE,GFX7-SIZE %s
+; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx900 -mattr=+half-rate-64-ops < %s | FileCheck -check-prefixes=SIZE,GFX9-SIZE %s
+; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1200 < %s | FileCheck -check-prefixes=SIZE,GFX12-SIZE %s
+
+define void @maximumnum_f16() {
+; GFX7-LABEL: 'maximumnum_f16'
+; GFX7-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f16 = call half @llvm.maximumnum.f16(half poison, half poison)
+; GFX7-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v2f16 = call <2 x half> @llvm.maximumnum.v2f16(<2 x half> poison, <2 x half> poison)
+; GFX7-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v3f16 = call <3 x half> @llvm.maximumnum.v3f16(<3 x half> poison, <3 x half> poison)
+; GFX7-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v4f16 = call <4 x half> @llvm.maximumnum.v4f16(<4 x half> poison, <4 x half> poison)
+; GFX7-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v8f16 = call <8 x half> @llvm.maximumnum.v8f16(<8 x half> poison, <8 x half> poison)
+; GFX7-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v16f16 = call <16 x half> @llvm.maximumnum.v16f16(<16 x half> poison, <16 x half> poison)
+; GFX7-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; GFX9-LABEL: 'maximumnum_f16'
+; GFX9-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f16 = call half @llvm.maximumnum.f16(half poison, half poison)
+; GFX9-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f16 = call <2 x half> @llvm.maximumnum.v2f16(<2 x half> poison, <2 x half> poison)
+; GFX9-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v3f16 = call <3 x half> @llvm.maximumnum.v3f16(<3 x half> poison, <3 x half> poison)
+; GFX9-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f16 = call <4 x half> @llvm.maximumnum.v4f16(<4 x half> poison, <4 x half> poison)
+; GFX9-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8f16 = call <8 x half> @llvm.maximumnum.v8f16(<8 x half> poison, <8 x half> poison)
+; GFX9-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16f16 = call <16 x half> @llvm.maximumnum.v16f16(<16 x half> poison, <16 x half> poison)
+; GFX9-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; GFX12-LABEL: 'maximumnum_f16'
+; GFX12-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f16 = call half @llvm.maximumnum.f16(half poison, half poison)
+; GFX12-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f16 = call <2 x half> @llvm.maximumnum.v2f16(<2 x half> poison, <2 x half> poison)
+; GFX12-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v3f16 = call <3 x half> @llvm.maximumnum.v3f16(<3 x half> poison, <3 x half> poison)
+; GFX12-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f16 = call <4 x half> @llvm.maximumnum.v4f16(<4 x half> poison, <4 x half> poison)
+; GFX12-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8f16 = call <8 x half> @llvm.maximumnum.v8f16(<8 x half> poison, <8 x half> poison)
+; GFX12-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16f16 = call <16 x half> @llvm.maximumnum.v16f16(<16 x half> poison, <16 x half> poison)
+; GFX12-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; GFX7-SIZE-LABEL: 'maximumnum_f16'
+; GFX7-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f16 = call half @llvm.maximumnum.f16(half poison, half poison)
+; GFX7-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v2f16 = call <2 x half> @llvm.maximumnum.v2f16(<2 x half> poison, <2 x half> poison)
+; GFX7-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v3f16 = call <3 x half> @llvm.maximumnum.v3f16(<3 x half> poison, <3 x half> poison)
+; GFX7-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v4f16 = call <4 x half> @llvm.maximumnum.v4f16(<4 x half> poison, <4 x half> poison)
+; GFX7-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v8f16 = call <8 x half> @llvm.maximumnum.v8f16(<8 x half> poison, <8 x half> poison)
+; GFX7-SIZE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v16f16 = call <16 x half> @llvm.maximumnum.v16f16(<16 x half> poison, <16 x half> poison)
+; GFX7-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+; GFX9-SIZE-LABEL: 'maximumnum_f16'
+; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f16 = call half @llvm.maximumnum.f16(half poison, half poison)
+; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f16 = call <2 x half> @llvm.maximumnum.v2f16(<2 x half> poison, <2 x half> poison)
+; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v3f16 = call <3 x half> @llvm.maximumnum.v3f16(<3 x half> poison, <3 x half> poison)
+; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f16 = call <4 x half> @llvm.maximumnum.v4f16(<4 x half> poison, <4 x half> poison)
+; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8f16 = call <8 x half> @llvm.maximumnum.v8f16(<8 x half> poison, <8 x half> poison)
+; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16f16 = call <16 x half> @llvm.maximumnum.v16f16(<16 x half> poison, <16 x half> poison)
+; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+; GFX12-SIZE-LABEL: 'maximumnum_f16'
+; GFX12-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f16 = call half @llvm.maximumnum.f16(half poison, half poison)
+; GFX12-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v2f16 = call <2 x half> @llvm.maximumnum.v2f16(<2 x half> poison, <2 x half> poison)
+; GFX12-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v3f16 = call <3 x half> @llvm.maximumnum.v3f16(<3 x half> poison, <3 x half> poison)
+; GFX12-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v4f16 = call <4 x half> @llvm.maximumnum.v4f16(<4 x half> poison, <4 x half> poison)
+; GFX12-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v8f16 = call <8 x half> @llvm.maximumnum.v8f16(<8 x half> poison, <8 x half> poison)
+; GFX12-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %v16f16 = call <16 x half> @llvm.maximumnum.v16f16(<16 x half> poison, <16 x half> poison)
+; GFX12-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+  %f16 = call half @llvm.maximumnum.f16(half poison, half poison)
+  %v2f16 = call <2 x half> @llvm.maximumnum.v2f16(<2 x half> poison, <2 x half> poison)
+  %v3f16 = call <3x half> @llvm.maximumnum.v3f16(<3 x half> poison, <3 x half> poison)
+  %v4f16 = call <4 x half> @llvm.maximumnum.v4f16(<4 x half> poison, <4 x half> poison)
+  %v8f16 = call <8 x half> @llvm.maximumnum.v8f16(<8 x half> poison, <8 x half> poison)
+  %v16f16 = call <16 x half> @llvm.maximumnum.v16f16(<16 x half> poison, <16 x half> poison)
+  ret void
+}
+
+define void @maximumnum_bf16() {
+; GFX7-LABEL: 'maximumnum_bf16'
+; GFX7-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bf16 = call bfloat @llvm.maximumnum.bf16(bfloat poison, bfloat poison)
+; GFX7-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v2bf16 = call <2 x bfloat> @llvm.maximumnum.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison)
+; GFX7-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v3bf16 = call <3 x bfloat> @llvm.maximumnum.v3bf16(<3 x bfloat> poison, <3 x bfloat> poison)
+; GFX7-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v4bf16 = call <4 x bfloat> @llvm.maximumnum.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison)
+; GFX7-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v8bf16 = call <8 x bfloat> @llvm.maximumnum.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison)
+; GFX7-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v16bf16 = call <16 x bfloat> @llvm.maximumnum.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison)
+; GFX7-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; GFX9-LABEL: 'maximumnum_bf16'
+; GFX9-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %bf16 = call bfloat @llvm.maximumnum.bf16(bfloat poison, bfloat poison)
+; GFX9-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %v2bf16 = call <2 x bfloat> @llvm.maximumnum.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison)
+; GFX9-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v3bf16 = call <3 x bfloat> @llvm.maximumnum.v3bf16(<3 x bfloat> poison, <3 x bfloat> poison)
+; GFX9-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %v4bf16 = call <4 x bfloat> @llvm.maximumnum.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison)
+; GFX9-NEXT:  Cost Model: Found an estimated cost of 87 for instruction: %v8bf16 = call <8 x bfloat> @llvm.maximumnum.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison)
+; GFX9-NEXT:  Cost Model: Found an estimated cost of 175 for instruction: %v16bf16 = call <16 x bfloat> @llvm.maximumnum.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison)
+; GFX9-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; GFX12-LABEL: 'maximumnum_bf16'
+; GFX12-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %bf16 = call bfloat @llvm.maximumnum.bf16(bfloat poison, bfloat poison)
+; GFX12-NEXT:  Cost Model: Found an estimated cost of 21 for instruction: %v2bf16 = call <2 x bfloat> @llvm.maximumnum.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison)
+; GFX12-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v3bf16 = call <3 x bfloat> @llvm.maximumnum.v3bf16(<3 x bfloat> poison, <3 x bfloat> poison)
+; GFX12-NEXT:  Cost Model: Found an estimated cost of 43 for instruction: %v4bf16 = call <4 x bfloat> @llvm.maximumnum.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison)
+; GFX12-NEXT:  Cost Model: Found an estimated cost of 87 for instruction: %v8bf16 = call <8 x bfloat> @llvm.maximumnum.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison)
+; GFX12-NEXT:  Cost Model: Found an estimated cost of 175 for instruction: %v16bf16 = call <16 x bfloat> @llvm.maximumnum.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison)
+; GFX12-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; GFX7-SIZE-LABEL: 'maximumnum_bf16'
+; GFX7-SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %bf16 = call bfloat @llvm.maximumnum.bf16(bfloat poison, bfloat poison)
+; GFX7-SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v2bf16 = call <2 x bfloat> @llvm.maximumnum.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison)
+; GFX7-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v3bf16 = call <3 x bfloat> @llvm.maximumnum.v3bf16(<3 x bfloat> poison, <3 x bfloat> poison)
+; GFX7-SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v4bf16 = call <4 x bfloat> @llvm.maximumnum.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison)
+; GFX7-SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v8bf16 = call <8 x bfloat> @llvm.maximumnum.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison)
+; GFX7-SIZE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v16bf16 = call <16 x bfloat> @llvm.maximumnum.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison)
+; GFX7-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+; GFX9-SIZE-LABEL: 'maximumnum_bf16'
+; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bf16 = call bfloat @llvm.maximumnum.bf16(bfloat poison, bfloat poison)
+; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v2bf16 = call <2 x bfloat> @llvm.maximumnum.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison)
+; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %v3bf16 = call <3 x bfloat> @llvm.maximumnum.v3bf16(<3 x bfloat> poison, <3 x bfloat> poison)
+; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %v4bf16 = call <4 x bfloat> @llvm.maximumnum.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison)
+; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %v8bf16 = call <8 x bfloat> @llvm.maximumnum.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison)
+; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %v16bf16 = call <16 x bfloat> @llvm.maximumnum.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison)
+; GFX9-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+; GFX12-SIZE-LABEL: 'maximumnum_bf16'
+; GFX12-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %bf16 = call bfloat @llvm.maximumnum.bf16(bfloat poison, bfloat poison)
+; GFX12-SIZE-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %v2bf16 = call <2 x bfloat> @llvm.maximumnum.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison)
+; GFX12-SIZE-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %v3bf16 = call <3 x bfloat> @llvm.maximumnum.v3bf16(<3 x bfloat> poison, <3 x bfloat> poison)
+; GFX12-SIZE-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %v4bf16 = call <4 x bfloat> @llvm.maximumnum.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison)
+; GFX12-SIZE-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %v8bf16 = call <8 x bfloat> @llvm.maximumnum.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison)
+; GFX12-SIZE-NEXT:  Cost Model: Found an estimated cost of 31 for instruction: %v16bf16 = call <16 x bfloat> @llvm.maximumnum.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison)
+; GFX12-SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+  %bf16 = call bfloat @llvm.maximumnum.bf16(bfloat poison, bfloat poison)
+  %v2bf16 = call <2 x bfloat> @llvm.maximumnum.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison)
+  %v3bf16 = call <3x bfloat> @llvm.maximumnum.v3bf16(<3 x bfloat> poison, <3 x bfloat> poison)
+  %v4bf16 = call <4 x bfloat> @llvm.maximumnum.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison)
+  %v8bf16 = call <8 x bfloat> @llvm.maximumnum.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison)
+  %v16bf16 = call <16 x bfloat> @llvm.maximumnum.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison)
+  ret void
+}
+
+define void @maximumnum_f32() {
+; ALL-LABEL: 'maximumnum_f32'
+; ALL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f32 = call float @llvm.maximumnum.f32(float poison, float poison)
+; ALL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v2f32 = call <2 x float> @llvm.maximumnum.v2f32(<2 x float> poison, <2 x float> poison)
+; ALL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %v3f32 = call <3 x float> @llvm.maximumnum.v3f32(<3 x float> poison, <3 x float> poison)
+; ALL-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v4f32 = call <4 x float> @llvm.maximumnum.v4f32(<4 x float> poison, <4 x float> poison)
+; ALL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v8f32 = call <8 x float> @llvm.maximumnum.v8f32(<8 x float> poison, <8 x float> poison)
+; ALL-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v16f32 = call <16 x float> @llvm.maximumnum.v16f32(<16 x float> poison, <16 x float> poison)
+; ALL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; SIZE-LABEL: 'maximumnum_f32'
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f32 = call float @llvm.maximumnum.f32(float poison, float poison)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v2f32 = call <2 x float> @llvm.maximumnum.v2f32(<2 x float> poison, <2 x float> poison)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %v3f32 = call <3 x float> @llvm.maximumnum.v3f32(<3 x float> poison, <3 x float> poison)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v4f32 = call <4 x float> @llvm.maximumnum.v4f32(<4 x float> poison, <4 x float> poison)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v8f32 = call <8 x float> @llvm.maximumnum.v8f32(<8 x float> poison, <8 x float> poison)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v16f32 = call <16 x float> @llvm.maximumnum.v16f32(<16 x float> poison, <16 x float> poison)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: ret void
+;
+  %f32 = call float @llvm.maximumnum.f32(float poison, float poison)
+  %v2f32 = call <2 x float> @llvm.maximumnum.v2f32(<2 x float> poison, <2 x float> poison)
+  %v3f32 = call <3x float> @llvm.maximumnum.v3f32(<3 x float> poison, <3 x float> poison)
+  %v4f32 = call <4 x float> @llvm.maximumnum.v4f32(<4 x float> poison, <4 x float> poison)
+  %v8f32 = call <8 x float> @llvm.maximumnum.v8f32(<8 x float> poison, <8 x float> poison)
+  %v16f32 = call <16 x float> @llvm.maximumnum.v16f32(<16 x float> poison, <16 x float> poison)
+  ret void
+}
+
+define void @maximumnum_f64() {
+; ALL-LABEL: 'maximumnum_f64'
+; ALL-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f64 = call double @llvm.maximumnum.f64(double poison, double poison)
+; ALL-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v2f64 = call <2 x double> @llvm.maximumnum.v2f64(<2 x double> poison, <2 x double> poison)
+; ALL-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %v3f64 = call <3 x double> @llvm.maximumnum.v3f64(<3 x double> poison, <3 x double> poison)
+; ALL-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v4f64 = call <4 x double> @llvm.maximumnum.v4f64(<4 x double> poison, <4 x double> poison)
+; ALL-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v8f64 = call <8 x double> @llvm.maximumnum.v8f64(<8 x double> poison, <8 x double> poison)
+; ALL-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %v16f64 = call <16 x double> @llvm.maximumnum.v16f64(<16 x double> poison, <16 x double> poison)
+; ALL-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: ret void
+;
+; SIZE-LABEL: 'maximumnum_f64'
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %f64 = call double @llvm.maximumnum.f64(double poison, double poison)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %v2f64 = call <2 x double> @llvm.maximumnum.v2f64(<2 x double> poison, <2 x double> poison)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %v3f64 = call <3 x double> @llvm.maximumnum.v3f64(<3 x double> poison, <3 x double> poison)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %v4f64 = call <4 x double> @llvm.maximumnum.v4f64(<4 x double> poison, <4 x double> poison)
+; SIZE-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %v8f64 = call <8 x double> @llvm.maximumnum.v8f64(<8 x double> poison, <8 x double> pois...
[truncated]

The f16 cases in particular look broken since every vector size
has the same reported cost.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants