This is an archive of the discontinued LLVM Phabricator instance.

Differential D131269

[CostModel] Add bfloat and fp128 reduction tests
ClosedPublic

Authored by virnarula on Aug 5 2022, 9:40 AM.

Details

Reviewers
fhahn
Commits
rGbc56f6377c08: [CostModel] Add bfloat and fp128 reduction tests

Diff Detail

Event Timeline

virnarula created this revision.Aug 5 2022, 9:40 AM
Herald added a project: Restricted Project. · View Herald TranscriptAug 5 2022, 9:40 AM
virnarula requested review of this revision.Aug 5 2022, 9:40 AM
Herald added a project: Restricted Project. · View Herald TranscriptAug 5 2022, 9:40 AM
Herald added a subscriber: llvm-commits. · View Herald Transcript
Harbormaster completed remote builds in B179531: Diff 450312.Aug 5 2022, 9:41 AM
virnarula updated this revision to Diff 450315.Aug 5 2022, 9:57 AM

Fix costs of old tests

virnarula added a reviewer: fhahn.Aug 5 2022, 9:57 AM
fhahn added a child revision: D131028: [AArch64] Fix cost model for FADD vector reduction.Aug 5 2022, 10:45 AM
Harbormaster completed remote builds in B179534: Diff 450315.Aug 5 2022, 11:00 AM
fhahn accepted this revision.Aug 11 2022, 1:00 AM

LGTM, thanks!

This revision is now accepted and ready to land.Aug 11 2022, 1:00 AM
fhahn added a comment.Aug 11 2022, 3:05 AM

@virnarula could you rebase the patch? It looks like it doesn't apply cleanly on current main.

virnarula updated this revision to Diff 452057.Aug 11 2022, 7:29 PM

Rebased onto main

Harbormaster completed remote builds in B180836: Diff 452057.Aug 11 2022, 8:39 PM
This revision was landed with ongoing or failed builds.Aug 12 2022, 8:44 AM
Closed by commit rGbc56f6377c08: [CostModel] Add bfloat and fp128 reduction tests (authored by virnarula, committed by fhahn). · Explain Why
This revision was automatically updated to reflect the committed changes.
fhahn added a commit: rGbc56f6377c08: [CostModel] Add bfloat and fp128 reduction tests.

Revision Contents

PathSize
llvm/
test/
Analysis/
CostModel/
AArch64/
15 lines

Diff 452195

llvm/test/Analysis/CostModel/AArch64/reduce-fadd.ll

; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=aarch64--linux-gnu < %s | FileCheck %s ; RUN: opt -passes='print<cost-model>' 2>&1 -disable-output -mtriple=aarch64--linux-gnu < %s | FileCheck %s
; RUN: opt -passes='print<cost-model>' 2>&1 -disable-output -mtriple=aarch64--linux-gnu -mattr=+fullfp16 < %s | FileCheck %s
define void @strict_fp_reductions() { define void @strict_fp_reductions() {
; CHECK-LABEL: 'strict_fp_reductions' ; CHECK-LABEL: 'strict_fp_reductions'
; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %fadd_v4f16 = call half @llvm.vector.reduce.fadd.v4f16(half 0xH0000, <4 x half> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %fadd_v4f16 = call half @llvm.vector.reduce.fadd.v4f16(half 0xH0000, <4 x half> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %fadd_v8f16 = call half @llvm.vector.reduce.fadd.v8f16(half 0xH0000, <8 x half> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 45 for instruction: %fadd_v8f16 = call half @llvm.vector.reduce.fadd.v8f16(half 0xH0000, <8 x half> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %fadd_v4f32 = call float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 21 for instruction: %fadd_v4f32 = call float @llvm.vector.reduce.fadd.v4f32(float 0.000000e+00, <4 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %fadd_v8f32 = call float @llvm.vector.reduce.fadd.v8f32(float 0.000000e+00, <8 x float> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 42 for instruction: %fadd_v8f32 = call float @llvm.vector.reduce.fadd.v8f32(float 0.000000e+00, <8 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %fadd_v2f64 = call double @llvm.vector.reduce.fadd.v2f64(double 0.000000e+00, <2 x double> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %fadd_v2f64 = call double @llvm.vector.reduce.fadd.v2f64(double 0.000000e+00, <2 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %fadd_v4f64 = call double @llvm.vector.reduce.fadd.v4f64(double 0.000000e+00, <4 x double> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %fadd_v4f64 = call double @llvm.vector.reduce.fadd.v4f64(double 0.000000e+00, <4 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %fadd_v4f8 = call bfloat @llvm.vector.reduce.fadd.v4bf16(bfloat 0xR0000, <4 x bfloat> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 20 for instruction: %fadd_v4f128 = call fp128 @llvm.vector.reduce.fadd.v4f128(fp128 undef, <4 x fp128> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
; ;
%fadd_v4f16 = call half @llvm.vector.reduce.fadd.v4f16(half 0.0, <4 x half> undef) %fadd_v4f16 = call half @llvm.vector.reduce.fadd.v4f16(half 0.0, <4 x half> undef)
%fadd_v8f16 = call half @llvm.vector.reduce.fadd.v8f16(half 0.0, <8 x half> undef) %fadd_v8f16 = call half @llvm.vector.reduce.fadd.v8f16(half 0.0, <8 x half> undef)
%fadd_v4f32 = call float @llvm.vector.reduce.fadd.v4f32(float 0.0, <4 x float> undef) %fadd_v4f32 = call float @llvm.vector.reduce.fadd.v4f32(float 0.0, <4 x float> undef)
%fadd_v8f32 = call float @llvm.vector.reduce.fadd.v8f32(float 0.0, <8 x float> undef) %fadd_v8f32 = call float @llvm.vector.reduce.fadd.v8f32(float 0.0, <8 x float> undef)
%fadd_v2f64 = call double @llvm.vector.reduce.fadd.v2f64(double 0.0, <2 x double> undef) %fadd_v2f64 = call double @llvm.vector.reduce.fadd.v2f64(double 0.0, <2 x double> undef)
%fadd_v4f64 = call double @llvm.vector.reduce.fadd.v4f64(double 0.0, <4 x double> undef) %fadd_v4f64 = call double @llvm.vector.reduce.fadd.v4f64(double 0.0, <4 x double> undef)
%fadd_v4f8 = call bfloat @llvm.vector.reduce.fadd.v4f8(bfloat 0.0, <4 x bfloat> undef)
%fadd_v4f128 = call fp128 @llvm.vector.reduce.fadd.v4f128(fp128 undef, <4 x fp128> undef)
ret void ret void
} }
define void @fast_fp_reductions() { define void @fast_fp_reductions() {
; CHECK-LABEL: 'fast_fp_reductions' ; CHECK-LABEL: 'fast_fp_reductions'
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %fadd_v4f16_fast = call fast half @llvm.vector.reduce.fadd.v4f16(half 0xH0000, <4 x half> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %fadd_v4f16_fast = call fast half @llvm.vector.reduce.fadd.v4f16(half 0xH0000, <4 x half> undef)
Show All 9 Lines
; CHECK-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %fadd_v13f32 = call fast float @llvm.vector.reduce.fadd.v13f32(float 0.000000e+00, <13 x float> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 50 for instruction: %fadd_v13f32 = call fast float @llvm.vector.reduce.fadd.v13f32(float 0.000000e+00, <13 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %fadd_v5f32_reassoc = call reassoc float @llvm.vector.reduce.fadd.v5f32(float 0.000000e+00, <5 x float> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %fadd_v5f32_reassoc = call reassoc float @llvm.vector.reduce.fadd.v5f32(float 0.000000e+00, <5 x float> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %fadd_v2f64 = call fast double @llvm.vector.reduce.fadd.v2f64(double 0.000000e+00, <2 x double> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %fadd_v2f64 = call fast double @llvm.vector.reduce.fadd.v2f64(double 0.000000e+00, <2 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %fadd_v2f64_reassoc = call reassoc double @llvm.vector.reduce.fadd.v2f64(double 0.000000e+00, <2 x double> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %fadd_v2f64_reassoc = call reassoc double @llvm.vector.reduce.fadd.v2f64(double 0.000000e+00, <2 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %fadd_v4f64 = call fast double @llvm.vector.reduce.fadd.v4f64(double 0.000000e+00, <4 x double> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %fadd_v4f64 = call fast double @llvm.vector.reduce.fadd.v4f64(double 0.000000e+00, <4 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %fadd_v4f64_reassoc = call reassoc double @llvm.vector.reduce.fadd.v4f64(double 0.000000e+00, <4 x double> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %fadd_v4f64_reassoc = call reassoc double @llvm.vector.reduce.fadd.v4f64(double 0.000000e+00, <4 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %fadd_v7f64 = call fast double @llvm.vector.reduce.fadd.v7f64(double 0.000000e+00, <7 x double> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 18 for instruction: %fadd_v7f64 = call fast double @llvm.vector.reduce.fadd.v7f64(double 0.000000e+00, <7 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %fadd_v9f64_reassoc = call reassoc double @llvm.vector.reduce.fadd.v9f64(double 0.000000e+00, <9 x double> undef) ; CHECK-NEXT: Cost Model: Found an estimated cost of 27 for instruction: %fadd_v9f64_reassoc = call reassoc double @llvm.vector.reduce.fadd.v9f64(double 0.000000e+00, <9 x double> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %fadd_v4f8 = call reassoc bfloat @llvm.vector.reduce.fadd.v4bf16(bfloat 0xR8000, <4 x bfloat> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %fadd_v4f128 = call reassoc fp128 @llvm.vector.reduce.fadd.v4f128(fp128 undef, <4 x fp128> undef)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
; ;
%fadd_v4f16_fast = call fast half @llvm.vector.reduce.fadd.v4f16(half 0.0, <4 x half> undef) %fadd_v4f16_fast = call fast half @llvm.vector.reduce.fadd.v4f16(half 0.0, <4 x half> undef)
%fadd_v4f16_reassoc = call reassoc half @llvm.vector.reduce.fadd.v4f16(half 0.0, <4 x half> undef) %fadd_v4f16_reassoc = call reassoc half @llvm.vector.reduce.fadd.v4f16(half 0.0, <4 x half> undef)
%fadd_v8f16 = call fast half @llvm.vector.reduce.fadd.v8f16(half 0.0, <8 x half> undef) %fadd_v8f16 = call fast half @llvm.vector.reduce.fadd.v8f16(half 0.0, <8 x half> undef)
%fadd_v8f16_reassoc = call reassoc half @llvm.vector.reduce.fadd.v8f16(half 0.0, <8 x half> undef) %fadd_v8f16_reassoc = call reassoc half @llvm.vector.reduce.fadd.v8f16(half 0.0, <8 x half> undef)
Show All 13 Lines;
%fadd_v2f64_reassoc = call reassoc double @llvm.vector.reduce.fadd.v2f64(double 0.0, <2 x double> undef) %fadd_v2f64_reassoc = call reassoc double @llvm.vector.reduce.fadd.v2f64(double 0.0, <2 x double> undef)
%fadd_v4f64 = call fast double @llvm.vector.reduce.fadd.v4f64(double 0.0, <4 x double> undef) %fadd_v4f64 = call fast double @llvm.vector.reduce.fadd.v4f64(double 0.0, <4 x double> undef)
%fadd_v4f64_reassoc = call reassoc double @llvm.vector.reduce.fadd.v4f64(double 0.0, <4 x double> undef) %fadd_v4f64_reassoc = call reassoc double @llvm.vector.reduce.fadd.v4f64(double 0.0, <4 x double> undef)
%fadd_v7f64 = call fast double @llvm.vector.reduce.fadd.v7f64(double 0.0, <7 x double> undef) %fadd_v7f64 = call fast double @llvm.vector.reduce.fadd.v7f64(double 0.0, <7 x double> undef)
%fadd_v9f64_reassoc = call reassoc double @llvm.vector.reduce.fadd.v9f64(double 0.0, <9 x double> undef) %fadd_v9f64_reassoc = call reassoc double @llvm.vector.reduce.fadd.v9f64(double 0.0, <9 x double> undef)
%fadd_v4f8 = call reassoc bfloat @llvm.vector.reduce.fadd.v4f8(bfloat -0.0, <4 x bfloat> undef)
%fadd_v4f128 = call reassoc fp128 @llvm.vector.reduce.fadd.v4f128(fp128 undef, <4 x fp128> undef)
ret void ret void
} }
declare bfloat @llvm.vector.reduce.fadd.v4f8(bfloat, <4 x bfloat>)
declare fp128 @llvm.vector.reduce.fadd.v4f128(fp128, <4 x fp128>)
declare half @llvm.vector.reduce.fadd.v4f16(half, <4 x half>) declare half @llvm.vector.reduce.fadd.v4f16(half, <4 x half>)
declare half @llvm.vector.reduce.fadd.v8f16(half, <8 x half>) declare half @llvm.vector.reduce.fadd.v8f16(half, <8 x half>)
declare half @llvm.vector.reduce.fadd.v11f16(half, <11 x half>) declare half @llvm.vector.reduce.fadd.v11f16(half, <11 x half>)
declare half @llvm.vector.reduce.fadd.v13f16(half, <13 x half>) declare half @llvm.vector.reduce.fadd.v13f16(half, <13 x half>)
declare float @llvm.vector.reduce.fadd.v4f32(float, <4 x float>) declare float @llvm.vector.reduce.fadd.v4f32(float, <4 x float>)
declare float @llvm.vector.reduce.fadd.v8f32(float, <8 x float>) declare float @llvm.vector.reduce.fadd.v8f32(float, <8 x float>)
declare float @llvm.vector.reduce.fadd.v13f32(float, <13 x float>) declare float @llvm.vector.reduce.fadd.v13f32(float, <13 x float>)
declare float @llvm.vector.reduce.fadd.v5f32(float, <5 x float>) declare float @llvm.vector.reduce.fadd.v5f32(float, <5 x float>)
declare double @llvm.vector.reduce.fadd.v2f64(double, <2 x double>) declare double @llvm.vector.reduce.fadd.v2f64(double, <2 x double>)
declare double @llvm.vector.reduce.fadd.v4f64(double, <4 x double>) declare double @llvm.vector.reduce.fadd.v4f64(double, <4 x double>)
declare double @llvm.vector.reduce.fadd.v7f64(double, <7 x double>) declare double @llvm.vector.reduce.fadd.v7f64(double, <7 x double>)
declare double @llvm.vector.reduce.fadd.v9f64(double, <9 x double>) declare double @llvm.vector.reduce.fadd.v9f64(double, <9 x double>)