-
Notifications
You must be signed in to change notification settings - Fork 39
New system class: perlmutter #731
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
slabasan
wants to merge
8
commits into
develop
Choose a base branch
from
systems/perlmutter
base: develop
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Changes from all commits
Commits
Show all changes
8 commits
Select commit
Hold shift + click to select a range
e15efa0
add new system: perlmutter
slabasan 5c7da00
update externals with benchpark system external
slabasan 1661031
remove cce compiler for now
6dee0d4
checkpoint
6a2a302
fix system.py
slabasan 870536c
fix path to cublas
slabasan c95d636
Merge branch 'develop' into systems/perlmutter
slabasan 54ab4a4
Merge branch 'develop' into systems/perlmutter
slabasan File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
47 changes: 47 additions & 0 deletions
47
systems/all_hardware_descriptions/HPECray-zen3-A100-Slingshot/hardware_description.yaml
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,47 @@ | ||
# Copyright 2023 Lawrence Livermore National Security, LLC and other | ||
# Benchpark Project Developers. See the top-level COPYRIGHT file for details. | ||
# | ||
# SPDX-License-Identifier: Apache-2.0 | ||
|
||
system_definition: | ||
name: HPECray-zen3-A100-Slingshot | ||
integrator: | ||
vendor: HPECray | ||
name: EX235a | ||
processor: | ||
vendor: AMD | ||
name: EPYC-Zen3 | ||
ISA: x86_64 | ||
uArch: zen3 | ||
accelerator: | ||
vendor: NVIDIA | ||
name: A100 | ||
ISA: PTX | ||
uArch: sm_80 | ||
interconnect: | ||
vendor: HPECray | ||
name: Slingshot11 | ||
systems-tested: | ||
csc-lumi: | ||
os: HPECrayOS | ||
scheduler: slurm | ||
compiler: cce | ||
runtime: rocm | ||
mpi: cray-mpich | ||
installation-year: 2023 | ||
llnl-elcapitan: | ||
os: TOSS | ||
scheduler: flux | ||
compiler: cce | ||
runtime: rocm | ||
mpi: cray-mpich | ||
top500-system-instances: | ||
Frontier: | ||
benchpark_system: | ||
top500: <https://www.top500.org/system/180047> | ||
Lumi: | ||
benchpark_system: csc-lumi | ||
top500: <https://www.top500.org/system/180048> | ||
Tioga: | ||
benchpark_system: llnl-elcapitan | ||
top500: <https://www.top500.org/system/180052> |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,252 @@ | ||
# Copyright 2023 Lawrence Livermore National Security, LLC and other | ||
# Benchpark Project Developers. See the top-level COPYRIGHT file for details. | ||
# | ||
# SPDX-License-Identifier: Apache-2.0 | ||
|
||
from packaging.version import Version | ||
|
||
from benchpark.directives import variant, maintainers | ||
from benchpark.system import System | ||
from benchpark.paths import hardware_descriptions | ||
|
||
|
||
class LbnlPerlmutter(System): | ||
|
||
maintainers("slabasan") | ||
|
||
id_to_resources = { | ||
"perlmutter": { | ||
"cuda_arch": "80", | ||
"sys_cores_per_node": 64, | ||
"sys_gpus_per_node": 4, | ||
"system_site": "lbnl", | ||
"hardware_key": str(hardware_descriptions) | ||
+ "/HPECray-zen3-A100-Slingshot/hardware_description.yaml", | ||
}, | ||
} | ||
|
||
variant( | ||
"compiler", | ||
default="gcc", | ||
values=("gcc",), | ||
description="Which compiler to use", | ||
) | ||
|
||
def __init__(self, spec): | ||
super().__init__(spec) | ||
|
||
if self.spec.satisfies("compiler=gcc"): | ||
self.gcc_version = Version("13.2.1") | ||
self.mpi_version = Version("8.1.30") | ||
|
||
self.scheduler = "slurm" | ||
attrs = self.id_to_resources.get("perlmutter") | ||
for k, v in attrs.items(): | ||
setattr(self, k, v) | ||
|
||
def compute_packages_section(self): | ||
selections = { | ||
"packages": { | ||
"all": {"require": "target=x86_64:"}, | ||
"tar": {"externals": [{"spec": "tar@1.34", "prefix": "/usr"}]}, | ||
"coreutils": { | ||
"externals": [{"spec": "coreutils@8.32", "prefix": "/usr"}] | ||
}, | ||
"libtool": {"externals": [{"spec": "libtool@2.4.6", "prefix": "/usr"}]}, | ||
"flex": {"externals": [{"spec": "flex@2.6.4+lex", "prefix": "/usr"}]}, | ||
"openssl": { | ||
"externals": [{"spec": "openssl@1.1.1l-fips", "prefix": "/usr"}] | ||
}, | ||
"m4": {"externals": [{"spec": "m4@1.4.18", "prefix": "/usr"}]}, | ||
"groff": {"externals": [{"spec": "groff@1.22.4", "prefix": "/usr"}]}, | ||
"cmake": { | ||
"externals": [{"spec": "cmake@3.20.4", "prefix": "/usr"}], | ||
"buildable": False, | ||
}, | ||
"curl": { | ||
"externals": [ | ||
{"spec": "curl@8.0.1+gssapi+ldap+nghttp2", "prefix": "/usr"} | ||
] | ||
}, | ||
"cusolver": { | ||
"externals": [{"spec": "cusolver@12.4", "prefix": "/opt/nvidia/hpc_sdk/Linux_x86_64/24.5/math_libs/12.4"}], | ||
"buildable": False, | ||
}, | ||
"cublas": { | ||
"externals": [{"spec": "cublas@12.4", "prefix": "/opt/nvidia/hpc_sdk/Linux_x86_64/24.5/math_libs/12.4"}], | ||
"buildable": False, | ||
}, | ||
"automake": { | ||
"externals": [{"spec": "automake@1.15.1", "prefix": "/usr"}], | ||
"buildable": False, | ||
}, | ||
"gmake": {"externals": [{"spec": "gmake@4.2.1", "prefix": "/usr"}]}, | ||
"subversion": { | ||
"externals": [{"spec": "subversion@1.14.1", "prefix": "/usr"}], | ||
"buildable": False, | ||
}, | ||
"diffutils": { | ||
"externals": [{"spec": "diffutils@3.6", "prefix": "/usr"}], | ||
"buildable": False, | ||
}, | ||
"gawk": {"externals": [{"spec": "gawk@4.2.1", "prefix": "/usr"}]}, | ||
"binutils": { | ||
"externals": [ | ||
{"spec": "binutils@2.40~gold~headers", "prefix": "/opt/cray/pe/cce/18.0.0/binutils/x86_64/x86_64-pc-linux-gnu"}, | ||
{"spec": "binutils@2.43.1~gold~headers", "prefix": "/usr"} | ||
], | ||
"buildable": False, | ||
}, | ||
"findutils": { | ||
"externals": [{"spec": "findutils@4.8.0", "prefix": "/usr"}], | ||
"buildable": False, | ||
}, | ||
"ccache": { | ||
"externals": [{"spec": "ccache@3.4.7", "prefix": "/usr"}], | ||
"buildable": False, | ||
}, | ||
"git": { | ||
"externals": [{"spec": "git@2.35.3~tcltk", "prefix": "/usr"}], | ||
"buildable": False, | ||
}, | ||
"openssh": { | ||
"externals": [{"spec": "openssh@8.4p1", "prefix": "/usr"}], | ||
"buildable": False, | ||
}, | ||
"autoconf": { | ||
"externals": [{"spec": "autoconf@2.69", "prefix": "/usr"}], | ||
"buildable": False, | ||
}, | ||
"bison": { | ||
"externals": [{"spec": "bison@3.0.4", "prefix": "/usr"}], | ||
"buildable": False, | ||
}, | ||
"python": { | ||
"externals": [ | ||
{ | ||
"prefix": "/usr", | ||
"spec": "python@2.7.18+bz2+crypt+ctypes~dbm~lzma+nis~pyexpat+pythoncmd~readline~sqlite3~ssl~tkinter+uuid+zlib", | ||
}, | ||
{ | ||
"prefix": "/usr", | ||
"spec": "python@3.6.15+bz2+crypt+ctypes~dbm+lzma+nis+pyexpat~pythoncmd+readline+sqlite3+ssl~tkinter+uuid+zlib", | ||
}, | ||
], | ||
"buildable": False, | ||
}, | ||
"doxygen": { | ||
"externals": [{"spec": "doxygen@1.8.14~graphviz~mscgen", "prefix": "/usr"}], | ||
"buildable": False, | ||
}, | ||
"gettext": { | ||
"externals": [{"spec": "gettext@0.20.2", "prefix": "/usr"}], | ||
"buildable": False, | ||
}, | ||
"ninja": { | ||
"externals": [{"spec": "ninja@1.10.0", "prefix": "/usr"}], | ||
"buildable": False, | ||
}, | ||
"perl": { | ||
"externals": [{"spec": "perl@5.26.1~cpanm+opcode+open+shared+threads", "prefix": "/usr"}], | ||
"buildable": False, | ||
}, | ||
"pkg-config": { | ||
"externals": [{"spec": "pkg-config@0.29.2", "prefix": "/usr"}], | ||
"buildable": False, | ||
}, | ||
"sed": { | ||
"externals": [{"spec": "sed@4.4", "prefix": "/usr"}], | ||
"buildable": False, | ||
}, | ||
"tar": { | ||
"externals": [{"spec": "tar@1.34", "prefix": "/usr"}], | ||
"buildable": False, | ||
}, | ||
"zlib": { | ||
"externals": [{"spec": "zlib@1.2.13", "prefix": "/usr"}], | ||
"buildable": False, | ||
}, | ||
} | ||
} | ||
|
||
#selections["packages"] |= self.mpi_config() | ||
|
||
# if self.spec.satisfies("compiler=gcc"): | ||
# selections["packages"] |= { | ||
# "cray-libsci": { | ||
# "externals": [ | ||
# { | ||
# "spec": "cray-libsci@23.05.1.4%gcc", | ||
# "prefix": "/opt/cray/pe/libsci/23.05.1.4/gnu/10.3/x86_64/", | ||
# } | ||
# ] | ||
# } | ||
# } | ||
|
||
return selections | ||
|
||
def compute_compilers_section(self): | ||
selections = { | ||
"compilers": [ | ||
{ | ||
"compiler": { | ||
"spec": "gcc@12.2.0", | ||
"paths": { | ||
"cc": "/opt/cray/pe/gcc/12.2.0/bin/gcc", | ||
"cxx": "/opt/cray/pe/gcc/12.2.0/bin/g++", | ||
"f77": "/opt/cray/pe/gcc/12.2.0/bin/gfortran", | ||
"fc": "/opt/cray/pe/gcc/12.2.0/bin/gfortran", | ||
}, | ||
"flags": {}, | ||
"operating_system": "rhel8", | ||
"target": "x86_64", | ||
"modules": [], | ||
"environment": {}, | ||
"extra_rpaths": [], | ||
} | ||
} | ||
] | ||
} | ||
|
||
return selections | ||
|
||
def mpi_config(self): | ||
if self.spec.satisfies("compiler=gcc"): | ||
return { | ||
"cray-mpich": { | ||
"externals": [ | ||
{ | ||
"spec": f"cray-mpich@{self.mpi_version}%gcc@{self.gcc_version} ~gtl +wrappers", | ||
"prefix": f"/opt/cray/pe/mpich/{self.mpi_version}/ofi/gnu/10.3", | ||
"extra_attributes": { | ||
"gtl_lib_path": f"/opt/cray/pe/mpich/{self.mpi_version}/gtl/lib", | ||
"ldflags": f"-L/opt/cray/pe/mpich/{self.mpi_version}/ofi/gnu/10.3/lib -lmpi -L/opt/cray/pe/mpich/{self.mpi_version}/gtl/lib -Wl,-rpath=/opt/cray/pe/mpich/{self.mpi_version}/gtl/lib", | ||
}, | ||
} | ||
] | ||
} | ||
} | ||
|
||
def compute_software_section(self): | ||
"""This is somewhat vestigial: for the Tioga config that is committed | ||
to the repo, multiple instances of mpi/compilers are stored and | ||
and these variables were used to choose consistent dependencies. | ||
The configs generated by this class should only ever have one | ||
instance of MPI etc., so there is no need for that. The experiments | ||
will fail if these variables are not defined though, so for now | ||
they are still generated (but with more-generic values). | ||
""" | ||
return { | ||
"software": { | ||
"packages": { | ||
"default-compiler": { | ||
"pkg_spec": f"{self.spec.variants['compiler'][0]}" | ||
}, | ||
"default-mpi": {"pkg_spec": "cray-mpich"}, | ||
"compiler-amdclang": {"pkg_spec": "clang"}, | ||
"compiler-gcc": {"pkg_spec": "gcc"}, | ||
"mpi-gcc": {"pkg_spec": "cray-mpich~gtl"}, | ||
"lapack-oneapi": {"pkg_spec": "intel-oneapi-mkl"}, | ||
} | ||
} | ||
} |
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This has changed with merge of #953 - example gcc definition at https://github.com/LLNL/benchpark/blob/develop/systems/llnl-elcapitan/system.py#L369