Files
TheRock/compiler/amd-llvm/llvm/test/tools/llvm-split/AMDGPU/large-kernels-merging.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

93 lines
2.9 KiB
LLVM

; RUN: llvm-split -o %t %s -j 3 -mtriple amdgcn-amd-amdhsa -amdgpu-module-splitting-max-depth=0 -amdgpu-module-splitting-large-threshold=1.2 -amdgpu-module-splitting-merge-threshold=0.5
; RUN: llvm-dis -o - %t0 | FileCheck --check-prefix=CHECK0 --implicit-check-not=define %s
; RUN: llvm-dis -o - %t1 | FileCheck --check-prefix=CHECK1 --implicit-check-not=define %s
; RUN: llvm-split -o %t.nolarge %s -j 3 -mtriple amdgcn-amd-amdhsa -amdgpu-module-splitting-large-threshold=0 -amdgpu-module-splitting-max-depth=0
; RUN: llvm-dis -o - %t.nolarge0 | FileCheck --check-prefix=NOLARGEKERNELS-CHECK0 --implicit-check-not=define %s
; RUN: llvm-dis -o - %t.nolarge1 | FileCheck --check-prefix=NOLARGEKERNELS-CHECK1 --implicit-check-not=define %s
; RUN: llvm-dis -o - %t.nolarge2 | FileCheck --check-prefix=NOLARGEKERNELS-CHECK2 --implicit-check-not=define %s
; 2 kernels (A/B) are large and share all their dependencies.
; They should go in the same partition, the remaining kernel should
; go somewhere else, and one partition should be empty.
;
; Also check w/o large kernels processing to verify they are indeed handled
; differently.
; Only 2 partitions for the first command.
; CHECK0: define internal void @HelperC()
; CHECK0: define amdgpu_kernel void @C
; CHECK1: define internal void @large2()
; CHECK1: define internal void @large1()
; CHECK1: define internal void @large0()
; CHECK1: define internal void @HelperA()
; CHECK1: define internal void @HelperB()
; CHECK1: define amdgpu_kernel void @A
; CHECK1: define amdgpu_kernel void @B
; NOLARGEKERNELS-CHECK0: define internal void @HelperC()
; NOLARGEKERNELS-CHECK0: define amdgpu_kernel void @C
; NOLARGEKERNELS-CHECK1: define internal void @large2()
; NOLARGEKERNELS-CHECK1: define internal void @large1()
; NOLARGEKERNELS-CHECK1: define internal void @large0()
; NOLARGEKERNELS-CHECK1: define internal void @HelperB()
; NOLARGEKERNELS-CHECK1: define amdgpu_kernel void @B
; NOLARGEKERNELS-CHECK2: define internal void @large2()
; NOLARGEKERNELS-CHECK2: define internal void @large1()
; NOLARGEKERNELS-CHECK2: define internal void @large0()
; NOLARGEKERNELS-CHECK2: define internal void @HelperA()
; NOLARGEKERNELS-CHECK2: define amdgpu_kernel void @A
define internal void @large2() {
store volatile i32 42, ptr null
call void @large2()
ret void
}
define internal void @large1() {
call void @large1()
call void @large2()
ret void
}
define internal void @large0() {
call void @large0()
call void @large1()
call void @large2()
ret void
}
define internal void @HelperA() {
call void @large0()
ret void
}
define internal void @HelperB() {
call void @large0()
ret void
}
define amdgpu_kernel void @A() {
call void @HelperA()
ret void
}
define amdgpu_kernel void @B() {
call void @HelperB()
ret void
}
define internal void @HelperC() {
ret void
}
define amdgpu_kernel void @C() {
call void @HelperC()
ret void
}