Andrei Stoian
e43528db71
feat(gpu): support keyswitch 64/32 in PBS
2026-01-05 09:48:00 +01:00
Guillermo Oyarzun
e12638dabe
feat(gpu): extend specialized version to classical pbs
2025-10-22 09:20:40 +02:00
Agnes Leroy
f9e876730a
chore(gpu): remove support for drift noise reduction
2025-10-03 09:45:20 +02:00
Pedro Alves
94d24e1f8b
feat(gpu): implement the centered modulus switch technique to classical PBS
2025-08-29 11:38:26 -03:00
Guillermo Oyarzun
ef5a391dc2
feat(gpu): write specialized pbs accumulate for 2_2 params
2025-08-07 09:34:32 +02:00
Agnes Leroy
48dfeb21dc
chore(gpu): refactor size tracker to avoid future bugs
2025-07-04 14:37:02 +01:00
Pedro Alves
8c88678ee8
feat(gpu): implement 128-bit multi-bit PBS
2025-07-03 20:34:32 -03:00
Guillermo Oyarzun
0d81623a23
feat(gpu): add squash noise in the hlapi
2025-06-10 13:14:29 +02:00
Pedro Alves
b066ef19fa
fix(gpu): fix the internal benchmark
2025-05-23 10:32:24 +02:00
Guillermo Oyarzun
c19cd9f021
fix(gpu): add indexes to modulus switch noise reduction
2025-05-22 10:50:51 +02:00
Agnes Leroy
9eaa77ddef
feat(gpu): make all scratch functions return the amount of memory consumed for temporary buffers
2025-04-30 10:48:03 +02:00
Beka Barbakadze
eeaffab7de
feat(gpu): Implement 128 bit classic CG PBS
2025-04-07 17:19:18 +02:00
Guillermo Oyarzun
9eb6d5afd1
feat(gpu): add modulus switch noise reduction gpu
2025-03-27 10:55:51 +01:00
Agnes Leroy
b1008824e2
chore(gpu): supress warnings in pcc_gpu
2025-03-21 18:02:07 +01:00
Beka Barbakadze
459969e9d2
feat(gpu): Implement 128 bit classic pbs
2025-03-12 22:13:22 +04:00
Pedro Alves
3c88574a52
chore(gpu): encapsulate cudaSetDevice
2025-01-31 09:08:30 +01:00
Pedro Alves
64b8d1e3f6
fix(gpu): general fixes on indexes used in multi-gpu context.
...
- fix a bug in which the wrong GPU may be queried for the max shared memory
- If multiple streams are running split through multiple GPUs,
operations happening on a stream in GPU i should query GPU i about its
max shared memory,
- also fixes wrong indexing at rust side.
2025-01-31 09:08:30 +01:00
Guillermo Oyarzun
81e11a6d70
feat(gpu): improve full propagation in sum and sub
2024-11-25 13:23:37 +01:00
Pedro Alves
b041608d25
fix(gpu): general fixes and improvements to PBS
...
- update pbs test parameters to match tfhe-rs' integer tests
- refactor mul_ggsw_glwe to make it easier to read
- fix the way we accumulate the external product result on multi-bit PBS
2024-11-13 13:36:55 +01:00
Agnes Leroy
e698d18242
chore(gpu): automatically generate rust bindings for cuda functions, except device.cu
2024-10-14 17:07:57 +02:00
