Skip to content
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.

Sign up for GitHub

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

Jump to bottom

b2b PR #16

Closed
wants to merge 275 commits into from
Closed

b2b PR #16

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
275 commits
Select commit Hold shift + click to select a range
6db1d9e
cleaned up makefile
AntonLydike Apr 3, 2023
fee500e
fixed interop.c
AntonLydike Apr 3, 2023
a0909d1
MLIR dockerfile.
PapyChacal Apr 3, 2023
47b7740
readme: update
georgebisbas Apr 3, 2023
9a3944e
scripts: Update timers
georgebisbas Apr 4, 2023
ea8bb95
Update makefile
georgebisbas Apr 4, 2023
8ac06b4
compare.py fix.
PapyChacal Apr 4, 2023
0f38a10
Correct stencil.cast bounds, add clang opts to the Makefile, use clan…
PapyChacal Apr 5, 2023
51cf7fb
2d5pt use to from CLI
PapyChacal Apr 5, 2023
4dfe31f
Bump xDSL to 0.11
PapyChacal May 4, 2023
95af73f
Switch requirements syntax.
PapyChacal May 4, 2023
168a313
Merge pull request #18 from xdslproject/emilien/xdsl-0.11
AntonLydike May 4, 2023
c645d55
move interop to proper i64
AntonLydike May 4, 2023
43105f2
Switching requirements back.
PapyChacal May 5, 2023
d41f47a
Use new memref pass after xDSL bump.
PapyChacal May 5, 2023
377ca7c
Use clang to compile interop.c. (gcc caused linkage issues on Archer2)
PapyChacal May 5, 2023
132fcef
Add a simple script to benchmark different grid sizes.
PapyChacal May 5, 2023
84b77ab
Add file output.
PapyChacal May 5, 2023
a952a6a
Add plotting and SVG output.
PapyChacal May 7, 2023
faa624e
Increase size more progressively.
PapyChacal May 7, 2023
f09bd1b
Default max value
PapyChacal May 7, 2023
9f96ab2
Cleanup, factorize plotting to depend only on the CSV.
PapyChacal May 7, 2023
4c09dd0
Split benchmark and plotting scripts.
PapyChacal May 7, 2023
9a96018
Write benchmark data on-the-go (don't lose past runs if interrupted)
PapyChacal May 7, 2023
ead1632
Return 0 from main if finishing.
PapyChacal May 7, 2023
cd743ea
Makefile polish + allow skipping output saving & comparison.
PapyChacal May 7, 2023
dc7c84d
No dump in bench script.
PapyChacal May 7, 2023
3febbd0
Display failed bench cmd.
PapyChacal May 7, 2023
b20abe5
Optional arg to plot.py to star with nth line.
PapyChacal May 8, 2023
5a81e05
Slight refactor of the Makefile.
PapyChacal May 8, 2023
a347150
Add OpenMP pipeline.
PapyChacal May 8, 2023
22283c0
Handle OpenMP in runs.
PapyChacal May 8, 2023
64e6db3
Add threads bench and plot scripts.
PapyChacal May 8, 2023
498a77a
Add CFLAGS to kernel.
PapyChacal May 8, 2023
4533ad5
Add cmd's output when failing.
PapyChacal May 12, 2023
f98e3f2
Refactor 2d5pt.py
PapyChacal May 12, 2023
a7b360a
More refactor, output "unrounded" times.
PapyChacal May 12, 2023
d365c8b
Add benchmarks.py.
PapyChacal May 14, 2023
bc23130
Remove 2d5pt.py and 3d_diff.py in favor of benchmarks.py
PapyChacal May 14, 2023
6ee753b
Compile main from benchmarks.py
PapyChacal May 14, 2023
14d8b1e
Compile interop in benchmarks.py and use CFLAGS.
PapyChacal May 15, 2023
6d7193c
Compile and run kernel from benchmarks.py
PapyChacal May 15, 2023
04dcc81
Rename benchmarks.py to fast_benchmarks.py (import reasons).
PapyChacal May 16, 2023
beb764d
Update plotting scripts to handle lists (by just averaging now).
PapyChacal May 16, 2023
8f50d8f
Dump inputs in benchmarks..
PapyChacal May 16, 2023
aa13ec9
Add points argument to grid_scale.py
PapyChacal May 16, 2023
9636e11
Now thread_scale benchmarks EITHER devito or xdsl.
PapyChacal May 16, 2023
1c473a6
Don't import thread_scale from plotting script.
PapyChacal May 16, 2023
ddbf002
Update fast_benchmarks.py 2d5pt initialization to be non-squared resi…
PapyChacal May 16, 2023
062923c
Use elipsis indexing.
PapyChacal May 16, 2023
62289d6
bench: Add 2D elastic example
georgebisbas May 18, 2023
7a5b8c8
update to work with latest xdsl main
AntonLydike May 23, 2023
9a27115
update to work with mpi-sprint-2
AntonLydike May 23, 2023
b472b38
put the mpi not omp on the correct thingy
AntonLydike May 24, 2023
f006510
put the mpi not omp on the correct thingy (for real now)
AntonLydike May 24, 2023
174d89d
mpi compilation now at a stage where it doesn't segfault
AntonLydike May 24, 2023
6a5daff
improvements in preperation for new stencil lowering
AntonLydike May 24, 2023
8216511
update for new stencil loops and bounds in types
AntonLydike May 30, 2023
83e36ed
fix main generation
AntonLydike May 30, 2023
d9dca5c
remove a bunch of prints and fix pipeline
AntonLydike May 30, 2023
f950f65
Better comparison.
PapyChacal May 31, 2023
54f0fdc
add scatter/gather to generated main
AntonLydike Jun 1, 2023
6582329
add mpi run mode to fast_benchmarks.py
AntonLydike Jun 1, 2023
7c5e843
fix rank at which data is gathered to 0
AntonLydike Jun 1, 2023
229d0fb
fix missing dump call in non-mpi version of generated main
AntonLydike Jun 2, 2023
1c2f110
(again) fix missing dump call in non-mpi version of generated main
AntonLydike Jun 2, 2023
b0e2918
a bunch of debugging helpers but no actual bugs fixed
AntonLydike Jun 2, 2023
09ecc40
remove unused MPI imports
AntonLydike Jun 3, 2023
1b8f21e
add visualization notebook
AntonLydike Jun 4, 2023
cd16c16
Add GPU lowering to Devito and a flag in fast_benchmarks.
PapyChacal Jun 5, 2023
4bccb41
Commit the lowering too :)
PapyChacal Jun 6, 2023
c717eb4
Small updates.
PapyChacal Jun 6, 2023
fcdd224
factor compile arguments in fast_benchmarks for easy benchmarking scr…
PapyChacal Jun 6, 2023
4cbd20e
Update bench;arking scripts.
PapyChacal Jun 6, 2023
a477751
add more mpi debugging things to interop.c
AntonLydike Jun 7, 2023
c888640
fix missing memref arg handling in interop.c
AntonLydike Jun 7, 2023
5ab37d6
main pipeline; move gpu-to-llvm down, to play nice with MPI (mhh)
PapyChacal Jun 7, 2023
0c357cb
Bench;ark scripts CLI args rerefactor.
PapyChacal Jun 7, 2023
70b1999
add asserts for subprocess calls
AntonLydike Jun 9, 2023
73afeb0
fix file name for per-rank dumps
AntonLydike Jun 9, 2023
afc1406
init non t0 memrefs to 0, assert exit codes in fast_benchmarks.py
AntonLydike Jun 9, 2023
1cd51f9
fix dumping twice when running mpi or gpu
AntonLydike Jun 9, 2023
42f9fcf
LD_LIBRARY_PATH to -L shennanigans.
PapyChacal Jun 9, 2023
0edd561
Update Makefile and Readme for MPI.
PapyChacal Jun 12, 2023
e872df7
Switch from -lmpi to using mpic..
PapyChacal Jun 12, 2023
f9b4650
docs: Small pass and check
georgebisbas Jun 12, 2023
4f78ca4
Update to xDSL main.
PapyChacal Jun 13, 2023
1a2064a
Update viz.py
AntonLydike Jun 13, 2023
0abca29
Add archer2 flag to fast_bench;arks to run with srun instead of mpirun.
PapyChacal Jun 13, 2023
52c6a18
Don't initialize GPU memory from host.
PapyChacal Jun 13, 2023
2eb000e
Add proper devito settings to grid_scale.py
PapyChacal Jun 13, 2023
350e8b3
Oops, import, too
PapyChacal Jun 13, 2023
98a6e68
Output grid_scale csv to gpu file.
PapyChacal Jun 13, 2023
133dca5
Try unmangling as part of compare.py
PapyChacal Jun 14, 2023
f9e5ea0
Add mpi flag to compare.py and make data PRECIOUS.
PapyChacal Jun 14, 2023
88ca7f8
New GPU pipeline.
PapyChacal Jun 14, 2023
bd0071c
Update viz.py
AntonLydike Jun 14, 2023
593a10e
compare.py: fix mpi calculations
AntonLydike Jun 14, 2023
57d6758
fast_benchmarks.py: swicth to 2d-grid for mpi
AntonLydike Jun 14, 2023
553e6f3
compare.py: fix mpi node count
AntonLydike Jun 14, 2023
2ac7690
towards jit compiling in devito
AntonLydike Jun 15, 2023
f866643
add 2d5pt.py as example
AntonLydike Jun 15, 2023
46ba8e1
add mlir types interop file
AntonLydike Jun 15, 2023
c86d77f
make it less insane by running only 4 ranks
AntonLydike Jun 15, 2023
d2e34bb
add proper args handling?
AntonLydike Jun 15, 2023
3f5b105
remove steam-run
AntonLydike Jun 15, 2023
b300e38
fix dict error
AntonLydike Jun 15, 2023
38f21d9
fix name of generated function
AntonLydike Jun 15, 2023
241dfd4
fix not passing args to construct_cfunction_args
AntonLydike Jun 15, 2023
7951627
fix params used in setup_memref_args
AntonLydike Jun 15, 2023
c7de52a
fix missing numpy import
AntonLydike Jun 15, 2023
b0321cd
add _C_ctype to Memref type
AntonLydike Jun 15, 2023
90a92c5
fix _C_ctype to Memref type
AntonLydike Jun 15, 2023
dde80ad
make memrefs passed explicit
AntonLydike Jun 15, 2023
af5898a
fix how func args are typed?
AntonLydike Jun 15, 2023
7e91563
make memrefs passed more explicit
AntonLydike Jun 15, 2023
c232b4b
fixed bug in memref to func args
AntonLydike Jun 15, 2023
d8f4bad
fixed sequencing error in 2d5pt.py
AntonLydike Jun 15, 2023
ef53151
add jit backdoor and print dialect support
AntonLydike Jun 16, 2023
89f7473
remove memref struct from func signature
AntonLydike Jun 16, 2023
967e4ee
make it ready for mpi
AntonLydike Jun 16, 2023
5a9b6bd
make mpi for two ranks work
AntonLydike Jun 19, 2023
7133d22
add pydebug.sh
AntonLydike Jun 19, 2023
3fb6f65
remove debug prints from dmp-to-mpi lowering
AntonLydike Jun 19, 2023
a3b84e7
make apply_kernel timed
AntonLydike Jun 19, 2023
3cee8d2
Add expand-strided-metadata to CPU (necessary for MPI, actually) pipe…
PapyChacal Jun 19, 2023
78e05da
make xdsl passes also register timers
AntonLydike Jun 19, 2023
5762b9e
explicitly flush stdout in 2d5pt.py
AntonLydike Jun 19, 2023
b51c7ed
fix 2d5pt init
AntonLydike Jun 19, 2023
50d2a2b
update 2d5pt.py
AntonLydike Jun 20, 2023
50bafb1
Reminder for pinning
georgebisbas Jun 21, 2023
96b287c
Add some perf logging prints
georgebisbas Jun 21, 2023
55a2d79
Update with perf logging
georgebisbas Jun 21, 2023
9054c36
update pipeline, remove unused code
AntonLydike Jun 22, 2023
2de0f09
major cleanup of fast_benchmarks, renamed to run_benchmark
AntonLydike Jun 22, 2023
731049e
refactoring of benchmarking tooling
AntonLydike Jun 22, 2023
6c25f83
remove dumping references
AntonLydike Jun 22, 2023
fe6d3f9
make printing nicer
AntonLydike Jun 22, 2023
8cedcb6
fix environ key errors
AntonLydike Jun 22, 2023
4f657bc
debug printing
AntonLydike Jun 22, 2023
cae562d
capture stderr for compiler errors
AntonLydike Jun 22, 2023
117fde3
capture stderr for compiler errors
AntonLydike Jun 22, 2023
359413b
fix encoding of compiler stderr
AntonLydike Jun 22, 2023
2a77522
move interop compiler to clang
AntonLydike Jun 22, 2023
6df855c
add missing flags for GPU and OMP
AntonLydike Jun 22, 2023
7f8ea7d
typo
AntonLydike Jun 22, 2023
78f42bf
fix openmp pipeline
AntonLydike Jun 22, 2023
0836517
add ability to compare to run_benchmark.py
AntonLydike Jun 22, 2023
c6bcee0
added --random-init flag to run_benchmark.py
AntonLydike Jun 22, 2023
e499019
fix --random-init flag to run_benchmark.py
AntonLydike Jun 22, 2023
52b9dd7
remove pring of ssa in op.apply
AntonLydike Jun 22, 2023
0a89547
fix slow random init
AntonLydike Jun 22, 2023
e9f5acf
sanity check for domain
AntonLydike Jun 22, 2023
76718c7
make random init better, fix some crashes
AntonLydike Jun 22, 2023
e1628c6
use mpicc when targeting mpi
AntonLydike Jun 23, 2023
770ed94
typo
AntonLydike Jun 23, 2023
14f8840
force mpicc to use our clang
AntonLydike Jun 23, 2023
3132d37
make runner script correctly parse output
AntonLydike Jun 23, 2023
8bedb0e
print command run by run_benchmark
AntonLydike Jun 23, 2023
74c6682
print stderr
AntonLydike Jun 23, 2023
ec3723b
srun - fix -n option
AntonLydike Jun 23, 2023
4bed90b
srun fix options some more
AntonLydike Jun 23, 2023
3a2d757
fix python args
AntonLydike Jun 23, 2023
b799e47
make correctness data cleaner
AntonLydike Jun 23, 2023
f2dd7e5
add report print
AntonLydike Jun 23, 2023
aad9481
add new auto benchmarking script
AntonLydike Jun 23, 2023
5369789
run_benchmark.py respect --repeat option
AntonLydike Jun 23, 2023
91a39b9
fix auto_benchmark to work with OMP_PLACES=cores
AntonLydike Jun 23, 2023
191594f
add core pinning to runner
AntonLydike Jun 23, 2023
df87b52
smaller runs to make benchmarking turnaround quicker
AntonLydike Jun 23, 2023
2930639
remove stray assert
AntonLydike Jun 23, 2023
71b76ca
add qos option
AntonLydike Jun 23, 2023
ed7efcc
add qos option
AntonLydike Jun 23, 2023
0f0cbde
Add nd wave with 3d, no damping field
georgebisbas Jun 23, 2023
52249ca
reduce time limit and add qos options
AntonLydike Jun 23, 2023
38c5bd3
add mpi thread scale
AntonLydike Jun 23, 2023
027785c
fix env in mpi thread scale
AntonLydike Jun 23, 2023
4b64038
fix output of thread scaling
AntonLydike Jun 23, 2023
0962da7
Add .slurm file
georgebisbas Jun 28, 2023
d34485c
compiler: Update with cray compiler and Devito main compiler file
georgebisbas Jul 5, 2023
0a432b3
Add heat examples, drop intel redundancy
georgebisbas Jul 12, 2023
1c1a205
Add nd_wave
georgebisbas Jul 7, 2023
9db6592
fix devito cray
AntonLydike Jul 13, 2023
6288ef2
georges changes to benchmarking
AntonLydike Jul 13, 2023
a7d3e7b
Merge branch 'anton/devito-run-with-apply' into stencil_mad_dash
AntonLydike Jul 14, 2023
760abfa
nd_nwave time fix.
PapyChacal Jul 14, 2023
2b6039f
Sync to xdsl/main.
PapyChacal Jul 14, 2023
446b397
fix issue apply_kernel not found
AntonLydike Jul 14, 2023
687e857
mpi: Add custom topology from devito codebase
georgebisbas Jul 14, 2023
9af33a5
mpi: Add tests for Custom topology
georgebisbas Jul 14, 2023
2d33ad2
devito/mpi/distributed.py
georgebisbas Jul 14, 2023
aa7e25a
Clean benchmark
georgebisbas Jul 14, 2023
d4d0ed3
Cleanup benchmark
georgebisbas Jul 14, 2023
416f1ec
bench: cleanup
georgebisbas Jul 19, 2023
51dbc2d
bench: cleanup 3d
georgebisbas Jul 19, 2023
fe1650c
bench: more cleanup, drop redundant
georgebisbas Jul 19, 2023
479d478
bench: more cleanup
georgebisbas Jul 19, 2023
1142684
add 'set -eo pipefail' to compiler pipeline to catch errors early
AntonLydike Jul 20, 2023
8e5e7ae
Use /bin/bash for set -eo pipefail.
PapyChacal Jul 20, 2023
335b5f5
add todo.
PapyChacal Jul 20, 2023
e9c76a7
Make xDSL flow use a temp .mlir file just like the usual temp .c file.
PapyChacal Jul 20, 2023
5df0f76
operator: Add fixed for xdsloperator compilation - apply_kernel
georgebisbas Jul 21, 2023
6fc0ff7
Lower subviews.
PapyChacal Jul 21, 2023
b346498
Link to MLIR runner utils.
PapyChacal Jul 21, 2023
bd48ffa
c_runner_utils rather.
PapyChacal Jul 21, 2023
d9c4239
Merge branch 'add_custom_topology' into bench_edits
PapyChacal Jul 21, 2023
c389f96
Reverse stencil.apply inputs and try to name accordingly.
PapyChacal Jul 22, 2023
c5f9552
fix data copy, buffer play
georgebisbas Jul 26, 2023
d8b5dba
wave2d.py
georgebisbas Jul 27, 2023
a67394e
Comment out pdb.
PapyChacal Jul 27, 2023
6de1971
Fix initial buffer order.
PapyChacal Jul 27, 2023
afca66d
add canonicalize-dmp pass to dmp pipeline
AntonLydike Jul 31, 2023
f2604c6
Merge pull request #22 from xdslproject/emilien/try-fix-wave
georgebisbas Aug 2, 2023
8087f95
Add tiling.
PapyChacal Aug 1, 2023
63ab369
Add proper quoting.
PapyChacal Aug 1, 2023
e15ce97
Add dimensionality-1 tiling dimensions logic.
PapyChacal Aug 2, 2023
bacf1af
mpi: Init effort for serial modelling on wave operator
georgebisbas Aug 2, 2023
7f3b37e
mpi: wip
georgebisbas Aug 2, 2023
e54cd7b
mpi: wip
georgebisbas Aug 2, 2023
625e976
wave3d: cleanup
georgebisbas Aug 3, 2023
b73489a
wave2d: cleanup
georgebisbas Aug 3, 2023
e4db7f9
mpi-mfe: Add
georgebisbas Aug 3, 2023
ea7fe19
hacky fix for row major dmp.grid
AntonLydike Aug 3, 2023
d45c113
bench: Conditional execution heat2d
georgebisbas Aug 4, 2023
ae3d586
bench: Conditional execution heat3d
georgebisbas Aug 4, 2023
9a973cc
bench: Generalize benchmarking scripts
georgebisbas Aug 4, 2023
4b34fc5
bench: Generalize wave3d
georgebisbas Aug 4, 2023
7d7e639
wave: TryAdd example with no Operator
georgebisbas Aug 4, 2023
26abd2e
add datatest
georgebisbas Aug 4, 2023
fd312d5
setup: Add necessary data
georgebisbas Aug 5, 2023
8db89d7
bench: Load dt to XDSL
georgebisbas Aug 5, 2023
bcd7a8d
setup: Save extent
georgebisbas Aug 5, 2023
8c8858a
bench: Add so to saved data
georgebisbas Aug 5, 2023
72fb27d
bench: Add wave3d setup
georgebisbas Aug 5, 2023
722e998
bench: compress saved data
georgebisbas Aug 5, 2023
aa73e33
bench: compress properly u.data[:]
georgebisbas Aug 5, 2023
163db36
Merge pull request #23 from xdslproject/emilien/stencil-tiling
georgebisbas Aug 6, 2023
ad55988
bench: More cleanup and tiling merge
georgebisbas Aug 6, 2023
6cfe569
bench: Hide pyvista req
georgebisbas Aug 6, 2023
80c0d31
Merge pull request #24 from xdslproject/bench_edits-2
georgebisbas Aug 9, 2023
dde653e
Insert necessary boilerplate. stencil lowerings doesn't handle it.
PapyChacal Aug 9, 2023
0d73b6e
Add more sensible and resilient tile sizes.
PapyChacal Aug 4, 2023
9082d9f
Try with a arguments-minimizing pipeline.
PapyChacal Aug 4, 2023
84b5522
Improve args-minimization pipeline (by still folding all compile-time…
PapyChacal Aug 6, 2023
c694e02
Remove superfluous GPU passes.
PapyChacal Aug 7, 2023
cca08a4
Add direct .so backdoor capability, and XDSL_SKIP_CLEAN env variable …
PapyChacal Aug 7, 2023
f057a23
Use DeVito's par-tile.
PapyChacal Aug 8, 2023
baa38fb
Use the boilerplate flag to not always copy to GPU.
PapyChacal Aug 9, 2023
fa0276f
Merge pull request #26 from xdslproject/emilien/gpu-again
georgebisbas Aug 9, 2023
e203d59
Merge pull request #21 from xdslproject/bench_edits
AntonLydike Oct 3, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Loading