pgardratzama
3073d60f11
fix(hpu): work-around a criterion assert by reducing number of elements on division & modulus throughput bench
2025-10-07 14:23:07 +02:00
Himess
a05d228899
docs(wasm): remove obsolete TODO in CompactPkeCrs::deserialize
2025-10-07 11:24:37 +02:00
Arthur Meyre
63055d5ca8
test: add KS32 compatibility for the dp_ks_pbs128_packingks AP
2025-10-07 10:22:38 +02:00
Arthur Meyre
46a3008739
test: add KS32 compatibility for the dp_ks_ms AP
2025-10-07 10:22:38 +02:00
Arthur Meyre
f2674da031
test: add KS32 compatibility for the br_dp_ks_ms AP
2025-10-07 10:22:38 +02:00
Arthur Meyre
12c2a2a8b7
feat: make FheUint/FheInt/FheBool compatible with AP params for conformance
...
- update From impl for conformance parameters to manage the AP params
2025-10-07 10:22:11 +02:00
pgardratzama
b61dd21ef7
fix(hpu): HPU HLAPI ERC20 bench was missing pbs-stats feature
2025-10-07 10:14:43 +02:00
pgardratzama
ca4159f123
fix(hpu): fix overflow flag of OVF_MUL & OVF_MULS, also update simulation HPU config
2025-10-07 10:14:43 +02:00
pgardratzama
ab25919187
fix(hpu): throughput benchmarks were done 1 IOp per 1 IOp...
2025-10-07 10:14:43 +02:00
pgardratzama
1b38f8ccfc
fix(hpu): fix expected value of ilog2 & modulus operation
2025-10-07 10:14:43 +02:00
Nicolas Sarlin
6a676551d8
chore(shortint): add metaparams for ks32
2025-10-07 09:51:09 +02:00
Thomas Montaigu
afb79a0b1c
chore(hlapi): export CompressedKVStore
...
Without this, users cannot use the CompressedKVStore type
that is required in the KVStore deserialization
2025-10-07 09:07:28 +02:00
Thomas Montaigu
0277403c45
feat: add From<MetaParameters> for Config
...
This convertion is important to make the use
of meta parameters for high level API
users
2025-10-06 16:47:13 +02:00
Thomas Montaigu
18159d6458
chore(MetaParameters)!: move re-rand ksk params in
...
Re-Randomization is something that requires a
dedicated public key.
Thus we move the parameters of the KSK
into the struct for dedicated PKE parameters
BREAKING CHANGE: This is breaking change regarding the latest alpha
released. But MetaParameters did not seem to be used directly in
fhevm/kms
2025-10-06 16:47:13 +02:00
Nicolas Sarlin
728409aef8
chore(hl): and cpk tests for ks32
2025-10-06 13:59:15 +02:00
Thomas Montaigu
034f3b3c25
feat(xofkeyset): add ks32 support
2025-10-06 13:59:15 +02:00
Nicolas Sarlin
c30e9c39f6
feat(shortint): add compact pke for the ks32 atomic pattern
2025-10-06 13:59:15 +02:00
Arthur Meyre
1513c3bc8c
chore: bump TFHE-rs to 1.4.0
2025-10-06 13:26:54 +02:00
Arthur Meyre
e07f07c4c8
chore: bump tfhe-cuda-backend to 0.12.0
2025-10-06 13:26:54 +02:00
Arthur Meyre
81cc0c31b4
chore: constrain bytemuck < 1.24.0 as we don't have avx512 updated code
2025-10-06 13:24:16 +02:00
tmontaigu
c95e38e26f
feat(hlapi): add flip operation
2025-10-06 11:07:12 +02:00
Enzo Di Maria
f0f3dd76eb
feat(gpu): aes 128
2025-10-06 09:31:36 +02:00
Andrei Stoian
0604d237eb
chore(gpu): multi-gpu debug target
2025-10-03 16:48:42 +02:00
Thomas Montaigu
e523fd2cb6
feat: add KVStore to the high level api
...
* Added Value type name to crate::integer::KVStore impl of Named trait
as well as a bool to check we deserialize the correct value type
(Radix vs SignedRadix)
* Add KVStore to high_level_api
* Add KVStore hlapi benches
* Remove specialized `[add,mul,sub]_to_slot` as `map` is now the
intended API.
- mul_to_slot was way slower than using `map`
- add/mul_to_slot were a bit faster (~5% latency-wise), but returned
less information (no old_value, no new_value, no boolean to check)
if the key matched
- Some known improvement can be made to map, which should result in
it being better than add/sub_to_slot
* Add FheIntegerType trait to make the KVStore generic over
FheUint/FheInt, and should make GPU integration "easy"
2025-10-03 15:01:23 +02:00
David Testé
33dee7673c
chore(ci): enable multi-bit parameters for core_crypto benchmarks
...
Classical or multi-bit or both parameters type can be now run on
CPU core_crypto benchmarks at user discretion.
2025-10-03 12:17:42 +02:00
Mayeul@Zama
9b5596ca66
feat(integer): add oprf over any range
2025-10-03 10:00:18 +02:00
Nicolas Sarlin
aefec1fe64
feat(shortint): add ct compression for the ks32 atomic pattern
2025-10-03 09:59:50 +02:00
Agnes Leroy
f9e876730a
chore(gpu): remove support for drift noise reduction
2025-10-03 09:45:20 +02:00
pgardratzama
f3cddb5635
chore(hpu): force benches to run on specific board
2025-10-02 13:20:36 +02:00
pgardratzama
a395cfe9bf
chore(hpu): new runners missing in actionlint whitelist
2025-10-02 13:20:36 +02:00
pgardratzama
602c6faf8a
chore(hpu): update hpu-backend dependencies, fix pcc
2025-10-02 13:20:36 +02:00
pgardratzama
563502a6a6
chore(hpu): update tfhe-hpu-backend version, readme and run-on-hpu doc
2025-10-02 13:20:36 +02:00
pgardratzama
5f30569452
fix(hpu): update AMC firmware in bitstream to lower polling period
2025-10-02 13:20:36 +02:00
pgardratzama
39b81a8ded
feat(hpu): move to new bitstream at 400Mhz with GRAM_NB 3
...
- update SIMD_N and min_batch_size to 12 which seems to give better
latency and ERC20 throughput
- support IOp on several lines in ami /proc file
- reduce amount of ERC_20_SIMD per batch in HLAPI bench
2025-10-02 13:20:36 +02:00
pgardratzama
da223b36b6
fix(hpu): reduce polling period of backend on iop ack file from 10 to 2us
2025-10-02 13:20:36 +02:00
JJ-hw
db16276715
chore(hpu): Remove all references to U55C, which is not supported anymore.
2025-10-02 13:20:36 +02:00
pgardratzama
a59742f518
fix(hpu): uuid comparison is now done in lower case from both value (metadata, ami read)
2025-10-02 13:20:36 +02:00
pgardratzama
2bf595d0e2
fix(hpu): missing bench numbers for less_than & less_or_equal because lower != less
2025-10-02 13:20:36 +02:00
Nicolas Sarlin
fb2b1a13e7
chore(core): fix encryption of single lwe to use the noise generator
...
This is aligned with what is done with the list encryption
2025-10-02 10:36:12 +02:00
Arthur Meyre
9fdaa983e3
chore: fix october typos
2025-10-01 14:32:41 +02:00
Andrei Stoian
73de886c07
chore(gpu): make deterministic long run GPU test
2025-10-01 13:37:05 +02:00
Nicolas Sarlin
45a849ad36
feat(shortint): add noise squashing for ks32
2025-10-01 10:36:11 +02:00
Nicolas Sarlin
ef5b984448
docs(core): fix fft128 blind rotation doc
2025-10-01 10:36:11 +02:00
Thomas Montaigu
6abed1f228
chore: complete gpu meta params
...
Add noise-squashing params, noise-squashing compression and re-rand
2025-10-01 10:30:22 +02:00
Agnes Leroy
71b45c14da
chore(gpu): refactor subset_first and subset
2025-09-30 12:21:39 +02:00
David Testé
4f5d711c4e
chore(bench): add crs size in wasm zero-knowledge benchmark
...
Done to improve result display in Grafana.
2025-09-30 10:42:19 +02:00
Arthur Meyre
2602c9e1b3
fix(hlapi): clear rerand metadata once rerand is done
2025-09-29 18:17:35 +02:00
Arthur Meyre
06dffc60bd
chore: bump version to 1.4.0-alpha.3
2025-09-29 18:17:35 +02:00
Arthur Meyre
2a82076121
fix(shortint): accept trivial ciphertexts for rerand
...
- make sure to set their noise to NOMINAL once rerand is done
2025-09-29 17:51:44 +02:00
Beka Barbakadze
7549474aac
feat(gpu): Implements optimized division algorithm for message_2_carry_2, when 4 or more gpus are used
2025-09-29 15:16:34 +02:00
