Antoniu Pop
0329d4fc2d
fix(gpu-wrappers): fix KS/BS wrappers for GPU (memory management).
2023-01-18 19:33:07 +00:00
tmontaigu
237c7eee9b
fix: remove unused but set variable
2023-01-13 13:05:22 +01:00
rudy
456e1952f5
fix: not private side effect in woppbs wrapper
...
Fix #865
2023-01-12 17:15:26 +01:00
aPere3
2fd9b6f0e3
refactor(encodings): raise plaintext/lut encodings higher up in the pipeline
2022-12-13 17:01:52 +01:00
Quentin Bourgerie
2a89f62c1a
fix(cuda): Include cuda_runtime.h in device.h to include the defininition of cudaStream_t
2022-12-07 21:32:01 +01:00
Quentin Bourgerie
3c616af622
feat(compiler): Handle batched operators for gpu codegen
2022-12-07 21:32:01 +01:00
Quentin Bourgerie
11cef2086d
chore(cuda): Add concrete-core as submodule in order to integrate concrete-cuda as a cmake subproject
2022-12-07 21:32:01 +01:00
Quentin Bourgerie
792d46fa80
enhance(runtime/gpu): Cache keys copy to gpu
2022-12-07 21:32:01 +01:00
Quentin Bourgerie
6eb4cec706
fix(wopbs): Fixing woppbs with tensor operators ( close #789 )
...
- Missing offset in woppbs routine
- Better error message for check of tensor result in end to end fixture
- Modify fixture generator for testing purpose
2022-11-30 10:02:07 +01:00
Andi Drebes
46366eec41
feat(compiler): Add fallback implementations for batched keyswitch and bootstrap
...
Add default implementations for batched keyswitch and bootstrap, which
simply call the scalar versions of these operations in a loop.
2022-11-18 12:06:07 +01:00
Samuel Tap
8a231974f7
chore(ffi): update to concrete-ffi without fftw
2022-11-16 11:44:46 +01:00
Quentin Bourgerie
90fca9eb5e
fix(runtime/gpu): Use the amortized version of the gpu boostrap as the parameter space of the lowlat one is too restrictive
2022-10-20 10:36:32 +01:00
youben11
ef778ac75b
refactor: replace some operands by attrs in bs/ks
2022-10-20 10:36:32 +01:00
youben11
d615ff47f2
feat: support GPU keyswitching
2022-10-20 10:36:32 +01:00
youben11
a7a65025ff
refactor: redesign GPU support
...
- unify CPU and GPU bootstrapping operations
- remove operations to build GLWE from table: this is now done in
wrapper functions
- remove GPU memory management operations: done in wrappers now, but we
will have to think about how to deal with it later in MLIR
2022-10-20 10:36:32 +01:00
youben11
d169a27fc0
feat: support GPU (bootstrapping)
2022-10-20 10:36:32 +01:00
Quentin Bourgerie
cf9a36c197
feat(compiler/runtime): Support the pbs for crt encoding (enable apply_lookup_table up to 16bits)
2022-10-07 09:16:19 +02:00
youben11
661d33c2b6
feat: keep std bsk and conv to fourier when needed
2022-09-06 07:18:34 +01:00
Mayeul@Zama
eb4b0753dc
enhance(runtime): Move to the official concrete-core-ffi release 0.2.0-rc2
...
Co-authored-by: Mayeul@Zama <mayeul.debellabre@zama.ai >
Co-authored-by: Quentin Bourgerie <bourgerie.quentin@gmail.com >
2022-08-30 18:08:47 +02:00
Quentin Bourgerie
8cd3a3a599
feat(compiler): First draft to support FHE.eint up to 16bits
...
For now what it works are only levelled ops with user parameters. (take a look to the tests)
Done:
- Add parameters to the fhe parameters to support CRT-based large integers
- Add command line options and tests options to allows the user to give those new parameters
- Update the dialects and pipeline to handle new fhe parameters for CRT-based large integers
- Update the client parameters and the client library to handle the CRT-based large integers
Todo:
- Plug the optimizer to compute the CRT-based large interger parameters
- Plug the pbs for the CRT-based large integer
2022-08-12 16:35:11 +02:00
Mayeul@Zama
928a44d243
chore(ci): enforce ending files with a newline
2022-06-16 17:04:25 +02:00
youben11
1354759884
chore: rename refs to main branch
2022-06-09 09:19:06 +01:00
Quentin Bourgerie
247d60503d
fix(compiler): Custom copy op from 1D tensor to avoir stack allocation from mlir memref to llvm lowering
2022-04-13 10:16:53 +02:00
Mayeul@Zama
ca8d4fb110
feat(compiler): use engine concrete C API
...
remove ConcreteToConcreteCAPI and ConcreteUnparametrize passes
2022-03-15 18:14:35 +01:00
