-
Notifications
You must be signed in to change notification settings - Fork 585
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
Add cuQuantum-based TFQ native ops and layers. #770
Closed
Closed
Changes from all commits
Commits
Show all changes
123 commits
Select commit
Hold shift + click to select a range
bd2b612
broken version of ops
Sinestro38 d749b05
Add cuquantum_configure()
jaeyoo 1831ec1
Merge branch 'master' into custatevec_support_v4
jaeyoo 9ae4fd0
Add CUQUANTUM_ROOT detection for automatic setup in configure.sh
jaeyoo eca1f01
Merge pull request #4 from tensorflow/master
jaeyoo 2e29308
Fix errors
jaeyoo 60a2ee9
Merge branch 'master' into custatevec_support_v4
jaeyoo 67b8e81
Split cuda/cuquantum and fix cuquantum_configure error
jaeyoo dcf189f
modify kernels and add python wrapper file
Sinestro38 3eae118
linting
Sinestro38 c5e0235
Add simulate cuquantum ops
jaeyoo 41c1839
Fix lint and format
jaeyoo 7189efc
Fix lint
jaeyoo 8b2ce11
Merge pull request #5 from jaeyoo/custatevec_support_v5
jaeyoo 615a949
merge master
Sinestro38 e9dfeb4
merge master ops BUILD file
Sinestro38 80861ae
cuquantum support for gpu ops, need to add CUDA support tho
Sinestro38 ae9cac5
python support for adj grad cuqantum op (needs to be merged WIP)
Sinestro38 d830a3b
cuquantum support for circuit executor ops
Sinestro38 c97fa3a
keras layers cuquantum support
Sinestro38 6aec6dd
adj grad cuquantum op kernel v0
Sinestro38 19717bf
update BUILD to master version
Sinestro38 249e2eb
added build targets and initial tests
Sinestro38 9b59824
add adj grad cuquantum op to release BUILD
Sinestro38 bad38a0
uncomment accidentally commented out tests
Sinestro38 69a61a5
add passing sanity check tests for cuquantm simulate ops
Sinestro38 68dc4fe
Merge branch 'pavan/add_cuquantum_simulate_tests' into pavan/port_cuq…
Sinestro38 39ba7c2
modify bazel test target
Sinestro38 d457e60
add cpu vs gpu benchmark test
Sinestro38 d92225a
Merge branch 'pavan/port_cuquantum_kernels' into pavan/keras_gpu_support
Sinestro38 34ad903
lint all
Sinestro38 b6ba3cc
Merge pull request #6 from jaeyoo/pavan/port_cuquantum_kernels
jaeyoo 50814f6
add adj grad keras layer use_gpu option [left debug statements]
Sinestro38 40f1ba2
comment out all tests but trivial adj grad op learning with gpu test
Sinestro38 f2fb9ca
remove the debug print statements
Sinestro38 5158802
modify the cuquantum dep in adjoint build target to be conditional on…
Sinestro38 ccd2138
uncomment out the tests
Sinestro38 44fae73
linting
Sinestro38 d0410e4
Merge branch 'master' into pavan/keras_gpu_support
Sinestro38 176f266
Merge pull request #7 from jaeyoo/pavan/keras_gpu_support
jaeyoo 75f8cb3
Fix BUILD error with unloaded bzl rule.
jaeyoo 30756d2
Merge pull request #9 from jaeyoo/fix_build
jaeyoo eb05692
Rename old _gpu_cpu to _cuquantum
jaeyoo 2ba5a20
cuquantum op should not be called in paralell.
jaeyoo de033ac
Rename use_gpu to use_cuquantum not to mean cuda.
jaeyoo b729c60
Fix wrong tfq version (0.7.2 to 0.7.3) and lint use_cuquantum
jaeyoo f1a09ab
Add circuit_execution_ops_test
jaeyoo 72ca20d
Fix wrong usage of GuardedPhiloxRandom, so fix expectation_test error
jaeyoo 0bdfe15
Merge pull request #10 from jaeyoo/test_device_gpu
jaeyoo 1eff5e6
Update expectation_test.py
Sinestro38 2b6af67
Fix the quantum_concurrent for expectation layer
jaeyoo 4efdb66
Remove *_cuda ops. support it later.
jaeyoo 3adb3ea
Move cublas/custatevec init/destory handlers to cstr/dstr
jaeyoo 317cd46
Update 4 cuquantum ops
jaeyoo 790fc06
Fix typos
jaeyoo e135088
Fix typo
jaeyoo c2220b1
Remove wrongly alive codes
jaeyoo 32e10f6
Change seed type from numbertype to int
jaeyoo 4e7c36f
Apply unsaved changes
jaeyoo 636d2fe
Add seed2
jaeyoo 3783a65
Fix sampled_expectation and samples ops of CPU version.
jaeyoo 3a3d30e
Remove legacy random code
jaeyoo 66fb6f0
Tune the test parameters
jaeyoo 0036ad8
Add more tolerance because it's large number of qubits...
jaeyoo 6e0aeaf
Tune tolerance one more..
jaeyoo 6854980
Fix format
jaeyoo a7c905f
Fix
jaeyoo 34055d0
Merge pull request #11 from jaeyoo/gpu_context
jaeyoo feddbfa
Upgrade qsim from jaeyoo's to official 0.16.0
jaeyoo 3fb6fe9
Add automatic linkopt for cuquantum without LD_LIBRARY_PATH
jaeyoo 3e5b565
Fix tensorflow/absl status & error
jaeyoo ea3ff94
Fix configure.sh for users not to type bazel options manually
jaeyoo 9f03bb1
Fix typo nescessary to necessary
jaeyoo 0d17c1f
Fix the copy&paste error.
jaeyoo 7323c73
Increase the test time for 4 cuquantum ops
jaeyoo d9243e5
Increase state cpu vs gpu test qubit size to 20 & add logs
jaeyoo 7ce9608
Change simmux.h to simmux_gpu.h for qsim 0.16.0
jaeyoo 9127379
Use cudaMemcpy for fast copy in state op.
jaeyoo 13ac9dc
Merge pull request #12 from jaeyoo/update_qsim_16
Sinestro38 0683d1c
controlled pqc cuquantum support
Sinestro38 1b10b08
Merge pull request #13 from jaeyoo/pavan/control_pqc_gpu
Sinestro38 1ff0912
Bump up to qsim 0.16.1
jaeyoo f4f0125
Fix cuquantum config bzl rule for uninitialized lib path
jaeyoo 598c415
Merge pull request #14 from jaeyoo/update_qsim_16
jaeyoo f6f00fd
Upgrade cirq version to ~= 1.0
jaeyoo 6094d2b
Comment out corrupted test.
jaeyoo 47d7617
Fix parse_context for graceful termination with returning status
jaeyoo d81733d
Fix int to size_t to turn off warning messages.
jaeyoo 8c521bb
Enable cuda config in test all
jaeyoo 5b85e3c
Fix format and use [[maybe_unused]] because we are in c++17
jaeyoo 35c2715
Fix format lint and enable expecation test for cpu&gpu
jaeyoo 2147099
Fix [[maybe_unused]] decorator usage.
jaeyoo 1e3a13e
Fix if-statements for backend & use_cuquantum for 4 major Keras layers.
jaeyoo 0b59038
Merge pull request #15 from jaeyoo/upgrade_cirq
jaeyoo f293478
Fix ./scripts/test_all.sh for CPU mode to be testable and passed
jaeyoo 41bde6d
Fix format
jaeyoo 0a74115
Merge pull request #16 from jaeyoo/both_cpu_gpu_ok
Sinestro38 53222df
Fix lint
jaeyoo 9e30f8d
Fix BulkSetAmpl bug, Add more diff cuquantum unit tests
jaeyoo 4df7a44
Merge branch 'master' into both_cpu_gpu_ok
jaeyoo 780061d
Add skipTest() reason
jaeyoo 5c53f9f
Add random seed for samples & sampled_expectation tests
jaeyoo e9e045e
Add GPU availability in 4 major keras layer tests
jaeyoo 277a56e
Fix format of license / add tests fixed seed random inits
jaeyoo 5931af0
Fix simple errors
jaeyoo 9949d25
Merge pull request #17 from jaeyoo/both_cpu_gpu_ok
jaeyoo 31cd871
Add gpu wheel install path and fix install.md / configs
jaeyoo e629877
update configure
Sinestro38 2ed029c
Merge pull request #18 from jaeyoo/pavan/update_configure
Sinestro38 69e02d6
add benchmark tests
Sinestro38 dd5ecfd
comment out cpu vs gpu benchmark assertions in unit tests
Sinestro38 5b85c78
remove commented lines
Sinestro38 3c787cd
Merge pull request #19 from jaeyoo/pavan/benchmarks
Sinestro38 b5b6f05
disable use_cuquantum with cirq backend
Sinestro38 0eac7aa
fix breaking typo error
Sinestro38 7c13efe
Merge pull request #20 from jaeyoo/pavan/disable_cirq_cuquantum
Sinestro38 e3a14d6
include install instructions to set CUQUANTUM_ROOT env var
Sinestro38 06062de
all benchmarks passing version
Sinestro38 d16aef9
add uncomment toggle
Sinestro38 cd9d928
remove seed
Sinestro38 ffdc598
Merge pull request #21 from jaeyoo/pavan/benchmark_update
Sinestro38 0d2738d
add passing depth benchmark cases
Sinestro38 6b845d3
update default cpu config
Sinestro38 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
This file contains 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
This file contains 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
This file contains 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
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.
Would you be able to revert the files where there are little to no changes made to the actual code so that the diff view is easier to read ?
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.
Sure, let me update the PR soon :) thank you Michael.