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
75 lines
6.1 KiB
LLVM
75 lines
6.1 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --version 3
|
|
; RUN: opt -passes="print<cost-model>" -cost-kind=all 2>&1 -disable-output -mtriple aarch64-linux-gnu -mattr=+sve -S -o - < %s | FileCheck %s --check-prefixes=CHECK,CHECK-SVE
|
|
; RUN: opt -passes="print<cost-model>" -cost-kind=all 2>&1 -disable-output -mtriple aarch64-linux-gnu -mattr=+sve2 -S -o - < %s | FileCheck %s --check-prefixes=CHECK,CHECK-SVE2
|
|
; RUN: opt -passes="print<cost-model>" -cost-kind=all 2>&1 -disable-output -mtriple aarch64-linux-gnu -mattr=+sve2,+bf16 -S -o - < %s | FileCheck %s --check-prefixes=CHECK,CHECK-BF16
|
|
|
|
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
|
|
target triple = "aarch64-unknown-linux-gnu"
|
|
|
|
define void @sve_fptruncs() {
|
|
; CHECK-LABEL: 'sve_fptruncs'
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %nxv2_f16_from_f32 = fptrunc <vscale x 2 x float> poison to <vscale x 2 x half>
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %nxv4_f16_from_f32 = fptrunc <vscale x 4 x float> poison to <vscale x 4 x half>
|
|
; CHECK-NEXT: Cost Model: Found costs of 3 for: %nxv8_f16_from_f32 = fptrunc <vscale x 8 x float> poison to <vscale x 8 x half>
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %nxv2_f16_from_f64 = fptrunc <vscale x 2 x double> poison to <vscale x 2 x half>
|
|
; CHECK-NEXT: Cost Model: Found costs of 3 for: %nxv4_f16_from_f64 = fptrunc <vscale x 4 x double> poison to <vscale x 4 x half>
|
|
; CHECK-NEXT: Cost Model: Found costs of 7 for: %nxv8_f16_from_f64 = fptrunc <vscale x 8 x double> poison to <vscale x 8 x half>
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %nxv2_f32_from_f64 = fptrunc <vscale x 2 x double> poison to <vscale x 2 x float>
|
|
; CHECK-NEXT: Cost Model: Found costs of 3 for: %nxv4_f32_from_f64 = fptrunc <vscale x 4 x double> poison to <vscale x 4 x float>
|
|
; CHECK-NEXT: Cost Model: Found costs of 6 for: %nxv8_f32_from_f64 = fptrunc <vscale x 8 x double> poison to <vscale x 8 x float>
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%nxv2_f16_from_f32 = fptrunc <vscale x 2 x float> poison to <vscale x 2 x half>
|
|
%nxv4_f16_from_f32 = fptrunc <vscale x 4 x float> poison to <vscale x 4 x half>
|
|
%nxv8_f16_from_f32 = fptrunc <vscale x 8 x float> poison to <vscale x 8 x half>
|
|
|
|
%nxv2_f16_from_f64 = fptrunc <vscale x 2 x double> poison to <vscale x 2 x half>
|
|
%nxv4_f16_from_f64 = fptrunc <vscale x 4 x double> poison to <vscale x 4 x half>
|
|
%nxv8_f16_from_f64 = fptrunc <vscale x 8 x double> poison to <vscale x 8 x half>
|
|
|
|
%nxv2_f32_from_f64 = fptrunc <vscale x 2 x double> poison to <vscale x 2 x float>
|
|
%nxv4_f32_from_f64 = fptrunc <vscale x 4 x double> poison to <vscale x 4 x float>
|
|
%nxv8_f32_from_f64 = fptrunc <vscale x 8 x double> poison to <vscale x 8 x float>
|
|
|
|
ret void
|
|
}
|
|
|
|
define void @sve_fptruncs_bf16() {
|
|
; CHECK-SVE-LABEL: 'sve_fptruncs_bf16'
|
|
; CHECK-SVE-NEXT: Cost Model: Found costs of 8 for: %nxv2_f16_from_f32 = fptrunc <vscale x 2 x float> poison to <vscale x 2 x bfloat>
|
|
; CHECK-SVE-NEXT: Cost Model: Found costs of 8 for: %nxv4_f16_from_f32 = fptrunc <vscale x 4 x float> poison to <vscale x 4 x bfloat>
|
|
; CHECK-SVE-NEXT: Cost Model: Found costs of 17 for: %nxv8_f16_from_f32 = fptrunc <vscale x 8 x float> poison to <vscale x 8 x bfloat>
|
|
; CHECK-SVE-NEXT: Cost Model: Found costs of Invalid for: %nxv2_f16_from_f64 = fptrunc <vscale x 2 x double> poison to <vscale x 2 x bfloat>
|
|
; CHECK-SVE-NEXT: Cost Model: Found costs of Invalid for: %nxv4_f16_from_f64 = fptrunc <vscale x 4 x double> poison to <vscale x 4 x bfloat>
|
|
; CHECK-SVE-NEXT: Cost Model: Found costs of Invalid for: %nxv8_f16_from_f64 = fptrunc <vscale x 8 x double> poison to <vscale x 8 x bfloat>
|
|
; CHECK-SVE-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
; CHECK-SVE2-LABEL: 'sve_fptruncs_bf16'
|
|
; CHECK-SVE2-NEXT: Cost Model: Found costs of 8 for: %nxv2_f16_from_f32 = fptrunc <vscale x 2 x float> poison to <vscale x 2 x bfloat>
|
|
; CHECK-SVE2-NEXT: Cost Model: Found costs of 8 for: %nxv4_f16_from_f32 = fptrunc <vscale x 4 x float> poison to <vscale x 4 x bfloat>
|
|
; CHECK-SVE2-NEXT: Cost Model: Found costs of 17 for: %nxv8_f16_from_f32 = fptrunc <vscale x 8 x float> poison to <vscale x 8 x bfloat>
|
|
; CHECK-SVE2-NEXT: Cost Model: Found costs of 9 for: %nxv2_f16_from_f64 = fptrunc <vscale x 2 x double> poison to <vscale x 2 x bfloat>
|
|
; CHECK-SVE2-NEXT: Cost Model: Found costs of 19 for: %nxv4_f16_from_f64 = fptrunc <vscale x 4 x double> poison to <vscale x 4 x bfloat>
|
|
; CHECK-SVE2-NEXT: Cost Model: Found costs of 39 for: %nxv8_f16_from_f64 = fptrunc <vscale x 8 x double> poison to <vscale x 8 x bfloat>
|
|
; CHECK-SVE2-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
; CHECK-BF16-LABEL: 'sve_fptruncs_bf16'
|
|
; CHECK-BF16-NEXT: Cost Model: Found costs of 1 for: %nxv2_f16_from_f32 = fptrunc <vscale x 2 x float> poison to <vscale x 2 x bfloat>
|
|
; CHECK-BF16-NEXT: Cost Model: Found costs of 1 for: %nxv4_f16_from_f32 = fptrunc <vscale x 4 x float> poison to <vscale x 4 x bfloat>
|
|
; CHECK-BF16-NEXT: Cost Model: Found costs of 3 for: %nxv8_f16_from_f32 = fptrunc <vscale x 8 x float> poison to <vscale x 8 x bfloat>
|
|
; CHECK-BF16-NEXT: Cost Model: Found costs of 2 for: %nxv2_f16_from_f64 = fptrunc <vscale x 2 x double> poison to <vscale x 2 x bfloat>
|
|
; CHECK-BF16-NEXT: Cost Model: Found costs of 5 for: %nxv4_f16_from_f64 = fptrunc <vscale x 4 x double> poison to <vscale x 4 x bfloat>
|
|
; CHECK-BF16-NEXT: Cost Model: Found costs of 11 for: %nxv8_f16_from_f64 = fptrunc <vscale x 8 x double> poison to <vscale x 8 x bfloat>
|
|
; CHECK-BF16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%nxv2_f16_from_f32 = fptrunc <vscale x 2 x float> poison to <vscale x 2 x bfloat>
|
|
%nxv4_f16_from_f32 = fptrunc <vscale x 4 x float> poison to <vscale x 4 x bfloat>
|
|
%nxv8_f16_from_f32 = fptrunc <vscale x 8 x float> poison to <vscale x 8 x bfloat>
|
|
|
|
%nxv2_f16_from_f64 = fptrunc <vscale x 2 x double> poison to <vscale x 2 x bfloat>
|
|
%nxv4_f16_from_f64 = fptrunc <vscale x 4 x double> poison to <vscale x 4 x bfloat>
|
|
%nxv8_f16_from_f64 = fptrunc <vscale x 8 x double> poison to <vscale x 8 x bfloat>
|
|
|
|
ret void
|
|
}
|