Files
TheRock/compiler/amd-llvm/llvm/test/Analysis/CostModel/AArch64/sve-scatter.ll
T
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

129 lines
15 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output < %s | FileCheck %s --check-prefix=CHECK-VSCALE-1
; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mcpu=neoverse-v1 < %s | FileCheck %s --check-prefix=CHECK-VSCALE-2
; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mcpu=neoverse-n2 < %s | FileCheck %s --check-prefix=CHECK-VSCALE-1
; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mcpu=cortex-a510 < %s | FileCheck %s --check-prefix=CHECK-VSCALE-1
; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mcpu=neoverse-v2 < %s | FileCheck %s --check-prefix=CHECK-V2
target triple="aarch64--linux-gnu"
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
define void @masked_scatters(<vscale x 4 x i1> %nxv4i1mask, <vscale x 8 x i1> %nxv8i1mask, <4 x i1> %v4i1mask, <1 x i1> %v1i1mask, <vscale x 1 x i1> %nxv1i1mask) #0 {
; CHECK-VSCALE-1-LABEL: 'masked_scatters'
; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> undef, <vscale x 4 x ptr> align 4 undef, <vscale x 4 x i1> %nxv4i1mask)
; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv8i32.nxv8p0(<vscale x 8 x i32> undef, <vscale x 8 x ptr> align 4 undef, <vscale x 8 x i1> %nxv8i1mask)
; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.masked.scatter.nxv1i64.nxv1p0(<vscale x 1 x i64> undef, <vscale x 1 x ptr> align 8 undef, <vscale x 1 x i1> %nxv1i1mask)
; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.masked.scatter.nxv4i1.nxv4p0(<vscale x 4 x i1> undef, <vscale x 4 x ptr> align 1 undef, <vscale x 4 x i1> %nxv4i1mask)
; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CHECK-VSCALE-2-LABEL: 'masked_scatters'
; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> undef, <vscale x 4 x ptr> align 4 undef, <vscale x 4 x i1> %nxv4i1mask)
; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.scatter.nxv8i32.nxv8p0(<vscale x 8 x i32> undef, <vscale x 8 x ptr> align 4 undef, <vscale x 8 x i1> %nxv8i1mask)
; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.masked.scatter.nxv1i64.nxv1p0(<vscale x 1 x i64> undef, <vscale x 1 x ptr> align 8 undef, <vscale x 1 x i1> %nxv1i1mask)
; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.masked.scatter.nxv4i1.nxv4p0(<vscale x 4 x i1> undef, <vscale x 4 x ptr> align 1 undef, <vscale x 4 x i1> %nxv4i1mask)
; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CHECK-V2-LABEL: 'masked_scatters'
; CHECK-V2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> undef, <vscale x 4 x ptr> align 4 undef, <vscale x 4 x i1> %nxv4i1mask)
; CHECK-V2-NEXT: Cost Model: Found an estimated cost of 104 for instruction: call void @llvm.masked.scatter.nxv8i32.nxv8p0(<vscale x 8 x i32> undef, <vscale x 8 x ptr> align 4 undef, <vscale x 8 x i1> %nxv8i1mask)
; CHECK-V2-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.masked.scatter.nxv1i64.nxv1p0(<vscale x 1 x i64> undef, <vscale x 1 x ptr> align 8 undef, <vscale x 1 x i1> %nxv1i1mask)
; CHECK-V2-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.masked.scatter.nxv4i1.nxv4p0(<vscale x 4 x i1> undef, <vscale x 4 x ptr> align 1 undef, <vscale x 4 x i1> %nxv4i1mask)
; CHECK-V2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call void @llvm.masked.scatter.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x ptr> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask)
call void @llvm.masked.scatter.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x ptr> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask)
call void @llvm.masked.scatter.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x ptr> undef, i32 0, <vscale x 1 x i1> %nxv1i1mask)
call void @llvm.masked.scatter.nxv4i1(<vscale x 4 x i1> undef, <vscale x 4 x ptr> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask)
ret void
}
define void @masked_scatters_tune_generic(<vscale x 4 x i1> %nxv4i1mask, <vscale x 8 x i1> %nxv8i1mask, <4 x i1> %v4i1mask, <1 x i1> %v1i1mask, <vscale x 1 x i1> %nxv1i1mask) #1 {
; CHECK-VSCALE-1-LABEL: 'masked_scatters_tune_generic'
; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> undef, <vscale x 4 x ptr> align 4 undef, <vscale x 4 x i1> %nxv4i1mask)
; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv8i32.nxv8p0(<vscale x 8 x i32> undef, <vscale x 8 x ptr> align 4 undef, <vscale x 8 x i1> %nxv8i1mask)
; CHECK-VSCALE-1-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.masked.scatter.nxv1i64.nxv1p0(<vscale x 1 x i64> undef, <vscale x 1 x ptr> align 8 undef, <vscale x 1 x i1> %nxv1i1mask)
; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CHECK-VSCALE-2-LABEL: 'masked_scatters_tune_generic'
; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> undef, <vscale x 4 x ptr> align 4 undef, <vscale x 4 x i1> %nxv4i1mask)
; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv8i32.nxv8p0(<vscale x 8 x i32> undef, <vscale x 8 x ptr> align 4 undef, <vscale x 8 x i1> %nxv8i1mask)
; CHECK-VSCALE-2-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.masked.scatter.nxv1i64.nxv1p0(<vscale x 1 x i64> undef, <vscale x 1 x ptr> align 8 undef, <vscale x 1 x i1> %nxv1i1mask)
; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CHECK-V2-LABEL: 'masked_scatters_tune_generic'
; CHECK-V2-NEXT: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> undef, <vscale x 4 x ptr> align 4 undef, <vscale x 4 x i1> %nxv4i1mask)
; CHECK-V2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv8i32.nxv8p0(<vscale x 8 x i32> undef, <vscale x 8 x ptr> align 4 undef, <vscale x 8 x i1> %nxv8i1mask)
; CHECK-V2-NEXT: Cost Model: Invalid cost for instruction: call void @llvm.masked.scatter.nxv1i64.nxv1p0(<vscale x 1 x i64> undef, <vscale x 1 x ptr> align 8 undef, <vscale x 1 x i1> %nxv1i1mask)
; CHECK-V2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call void @llvm.masked.scatter.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x ptr> undef, i32 0, <vscale x 4 x i1> %nxv4i1mask)
call void @llvm.masked.scatter.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x ptr> undef, i32 0, <vscale x 8 x i1> %nxv8i1mask)
call void @llvm.masked.scatter.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x ptr> undef, i32 0, <vscale x 1 x i1> %nxv1i1mask)
ret void
}
define void @masked_scatters_no_vscale_range() #2 {
; CHECK-VSCALE-1-LABEL: 'masked_scatters_no_vscale_range'
; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.nxv4f64.nxv4p0(<vscale x 4 x double> undef, <vscale x 4 x ptr> align 1 undef, <vscale x 4 x i1> undef)
; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.nxv2f64.nxv2p0(<vscale x 2 x double> undef, <vscale x 2 x ptr> align 1 undef, <vscale x 2 x i1> undef)
; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv8f32.nxv8p0(<vscale x 8 x float> undef, <vscale x 8 x ptr> align 1 undef, <vscale x 8 x i1> undef)
; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.nxv4f32.nxv4p0(<vscale x 4 x float> undef, <vscale x 4 x ptr> align 1 undef, <vscale x 4 x i1> undef)
; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 20 for instruction: call void @llvm.masked.scatter.nxv2f32.nxv2p0(<vscale x 2 x float> undef, <vscale x 2 x ptr> align 1 undef, <vscale x 2 x i1> undef)
; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.scatter.nxv16i16.nxv16p0(<vscale x 16 x i16> undef, <vscale x 16 x ptr> align 1 undef, <vscale x 16 x i1> undef)
; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv8i16.nxv8p0(<vscale x 8 x i16> undef, <vscale x 8 x ptr> align 1 undef, <vscale x 8 x i1> undef)
; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.nxv4i16.nxv4p0(<vscale x 4 x i16> undef, <vscale x 4 x ptr> align 1 undef, <vscale x 4 x i1> undef)
; CHECK-VSCALE-1-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CHECK-VSCALE-2-LABEL: 'masked_scatters_no_vscale_range'
; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv4f64.nxv4p0(<vscale x 4 x double> undef, <vscale x 4 x ptr> align 1 undef, <vscale x 4 x i1> undef)
; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.nxv2f64.nxv2p0(<vscale x 2 x double> undef, <vscale x 2 x ptr> align 1 undef, <vscale x 2 x i1> undef)
; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.scatter.nxv8f32.nxv8p0(<vscale x 8 x float> undef, <vscale x 8 x ptr> align 1 undef, <vscale x 8 x i1> undef)
; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv4f32.nxv4p0(<vscale x 4 x float> undef, <vscale x 4 x ptr> align 1 undef, <vscale x 4 x i1> undef)
; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 40 for instruction: call void @llvm.masked.scatter.nxv2f32.nxv2p0(<vscale x 2 x float> undef, <vscale x 2 x ptr> align 1 undef, <vscale x 2 x i1> undef)
; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 320 for instruction: call void @llvm.masked.scatter.nxv16i16.nxv16p0(<vscale x 16 x i16> undef, <vscale x 16 x ptr> align 1 undef, <vscale x 16 x i1> undef)
; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.scatter.nxv8i16.nxv8p0(<vscale x 8 x i16> undef, <vscale x 8 x ptr> align 1 undef, <vscale x 8 x i1> undef)
; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.nxv4i16.nxv4p0(<vscale x 4 x i16> undef, <vscale x 4 x ptr> align 1 undef, <vscale x 4 x i1> undef)
; CHECK-VSCALE-2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
; CHECK-V2-LABEL: 'masked_scatters_no_vscale_range'
; CHECK-V2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: call void @llvm.masked.scatter.nxv4f64.nxv4p0(<vscale x 4 x double> undef, <vscale x 4 x ptr> align 1 undef, <vscale x 4 x i1> undef)
; CHECK-V2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: call void @llvm.masked.scatter.nxv2f64.nxv2p0(<vscale x 2 x double> undef, <vscale x 2 x ptr> align 1 undef, <vscale x 2 x i1> undef)
; CHECK-V2-NEXT: Cost Model: Found an estimated cost of 104 for instruction: call void @llvm.masked.scatter.nxv8f32.nxv8p0(<vscale x 8 x float> undef, <vscale x 8 x ptr> align 1 undef, <vscale x 8 x i1> undef)
; CHECK-V2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: call void @llvm.masked.scatter.nxv4f32.nxv4p0(<vscale x 4 x float> undef, <vscale x 4 x ptr> align 1 undef, <vscale x 4 x i1> undef)
; CHECK-V2-NEXT: Cost Model: Found an estimated cost of 26 for instruction: call void @llvm.masked.scatter.nxv2f32.nxv2p0(<vscale x 2 x float> undef, <vscale x 2 x ptr> align 1 undef, <vscale x 2 x i1> undef)
; CHECK-V2-NEXT: Cost Model: Found an estimated cost of 208 for instruction: call void @llvm.masked.scatter.nxv16i16.nxv16p0(<vscale x 16 x i16> undef, <vscale x 16 x ptr> align 1 undef, <vscale x 16 x i1> undef)
; CHECK-V2-NEXT: Cost Model: Found an estimated cost of 104 for instruction: call void @llvm.masked.scatter.nxv8i16.nxv8p0(<vscale x 8 x i16> undef, <vscale x 8 x ptr> align 1 undef, <vscale x 8 x i1> undef)
; CHECK-V2-NEXT: Cost Model: Found an estimated cost of 52 for instruction: call void @llvm.masked.scatter.nxv4i16.nxv4p0(<vscale x 4 x i16> undef, <vscale x 4 x ptr> align 1 undef, <vscale x 4 x i1> undef)
; CHECK-V2-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
call void @llvm.masked.scatter.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x ptr> undef, i32 1, <vscale x 4 x i1> undef)
call void @llvm.masked.scatter.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x ptr> undef, i32 1, <vscale x 2 x i1> undef)
call void @llvm.masked.scatter.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x ptr> undef, i32 1, <vscale x 8 x i1> undef)
call void @llvm.masked.scatter.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x ptr> undef, i32 1, <vscale x 4 x i1> undef)
call void @llvm.masked.scatter.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x ptr> undef, i32 1, <vscale x 2 x i1> undef)
call void @llvm.masked.scatter.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x ptr> undef, i32 1, <vscale x 16 x i1> undef)
call void @llvm.masked.scatter.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x ptr> undef, i32 1, <vscale x 8 x i1> undef)
call void @llvm.masked.scatter.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x ptr> undef, i32 1, <vscale x 4 x i1> undef)
ret void
}
attributes #0 = { "target-features"="+sve" vscale_range(1, 8) }
attributes #1 = { "target-features"="+sve" vscale_range(1, 16) "tune-cpu"="generic" }
attributes #2 = { "target-features"="+sve" }
declare void @llvm.masked.scatter.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x ptr>, i32, <vscale x 4 x i1>)
declare void @llvm.masked.scatter.nxv8i32(<vscale x 8 x i32>, <vscale x 8 x ptr>, i32, <vscale x 8 x i1>)
declare void @llvm.masked.scatter.nxv1i64(<vscale x 1 x i64>, <vscale x 1 x ptr>, i32, <vscale x 1 x i1>)
declare void @llvm.masked.scatter.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x ptr>, i32, <vscale x 4 x i1>)
declare void @llvm.masked.scatter.nxv4f64(<vscale x 4 x double>, <vscale x 4 x ptr>, i32, <vscale x 4 x i1>)
declare void @llvm.masked.scatter.nxv2f64(<vscale x 2 x double>, <vscale x 2 x ptr>, i32, <vscale x 2 x i1>)
declare void @llvm.masked.scatter.nxv8f32(<vscale x 8 x float>, <vscale x 8 x ptr>, i32, <vscale x 8 x i1>)
declare void @llvm.masked.scatter.nxv4f32(<vscale x 4 x float>, <vscale x 4 x ptr>, i32, <vscale x 4 x i1>)
declare void @llvm.masked.scatter.nxv2f32(<vscale x 2 x float>, <vscale x 2 x ptr>, i32, <vscale x 2 x i1>)
declare void @llvm.masked.scatter.nxv16i16(<vscale x 16 x i16>, <vscale x 16 x ptr>, i32, <vscale x 16 x i1>)
declare void @llvm.masked.scatter.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x ptr>, i32, <vscale x 8 x i1>)
declare void @llvm.masked.scatter.nxv4i16(<vscale x 4 x i16>, <vscale x 4 x ptr>, i32, <vscale x 4 x i1>)