Commit Graph

Select branches

Hide Pull Requests

main

origin-main

perf/minblocks-knob

perf/sm120-spills

#10

#11

#12

#13

#14

#15

#16

#17

#18

#19

#20

#21

#22

#23

#26

#28

#29

#30

#31

#32

#33

v0.2.1

v0.3.0

v1.0.0

v2.0.0

v2.0.1

v2.0.2

v2.1.0

v2.1.1

v2.1.2

v3.0.0

v3.0.1

v3.1.0

v3.2.0

v3.3.0

v3.3.1

v4.0.0

v4.0.1

v4.0.2

v4.0.2-lair.1

v4.0.2-lair.2

Mono Color

• 05bb5d885f Increase CUDA kernel ABI version and add coverage bounds check rob thijssen 2025-09-14 08:28:10 +03:00
• 2a2bc1f60b debug and warn logs for CUDA G2 winner diagnostics rob thijssen 2025-09-14 05:46:26 +03:00
• 060a851300 Bump CUDA ABI version to 2 and use sentinel values for winners rob thijssen 2025-09-13 13:17:48 +03:00
• 25fdbf6ed2 Add kernel ABI version constant and probe in CUDA engine rob thijssen 2025-09-13 13:01:30 +03:00
• fa9b90ef28 report winner thread and iteration via output buffers for nonce reconstruction rob thijssen 2025-09-13 12:44:27 +03:00
• 9739f7c08a record winner thread and iteration on device for accurate nonce reconstruction rob thijssen 2025-09-13 12:33:49 +03:00
• fbd143f1cc Fix nonce calculation by tracking per-thread base nonces rob thijssen 2025-09-13 12:17:15 +03:00
• d8c96df8ba Add alternative nonce mappings to diagnose CUDA false positives rob thijssen 2025-09-13 12:02:40 +03:00
• 8dada4cb61 Add additional host distance check for false positive logs rob thijssen 2025-09-13 11:45:24 +03:00
• 24ba4b0aa4 Fix qpow kernel to use h_le instead of digest_be in XOR and assignments rob thijssen 2025-09-13 11:31:23 +03:00
• fd048d4923 Fix big-endian byte order handling in qpow kernel rob thijssen 2025-09-13 11:19:20 +03:00
• 17eb8e473c Fix byte order in qpow kernel to use big-endian reversal rob thijssen 2025-09-13 11:04:29 +03:00
• 39d68b989c Fix digest big-endian conversion to preserve lane order rob thijssen 2025-09-13 10:54:00 +03:00
• ff477754d2 Use big-endian bytes consistently in qpow kernelSHA3 digest and comparisons rob thijssen 2025-09-13 10:36:23 +03:00
• 860503792c Adjust qpow kernel to use lane-LE byte order for target and threshold rob thijssen 2025-09-13 10:26:34 +03:00
• 03d3225478 Clarify sha3_512_64bytes_le input interpretation rob thijssen 2025-09-13 10:15:38 +03:00
• 57483a0050 Refactor GPU kernel for G2 SHA3-512 with threshold check rob thijssen 2025-09-13 09:57:45 +03:00
• b72be05386 Fix Keccak state indexing in keccak_f1600 kernel for CUDA rob thijssen 2025-09-13 09:19:02 +03:00
• 7a3c40d8e8 Unroll Keccak-f1600 rounds for better performance rob thijssen 2025-09-13 09:06:33 +03:00
• 642b596fad rewrite distance and comparison logic to use big-endian byte arrays instead of uint64 limbs rob thijssen 2025-09-13 08:51:47 +03:00
• 6048d08664 optimize big-endian distance calculation in qpow kernel rob thijssen 2025-09-13 08:38:45 +03:00
• f62eff6be1 use little-endian output and byte-wise XOR in qpow kernel rob thijssen 2025-09-13 08:20:09 +03:00
• 734b4fbb74 richer diagnostics for cuda false positive logging rob thijssen 2025-09-13 07:56:47 +03:00
• 5fe204349f Add debug output buffers to CUDA G2 kernel and log on false positive rejection rob thijssen 2025-09-13 07:43:18 +03:00
• 16057a8e20 Add optional CUDA sampler readback and parity check rob thijssen 2025-09-13 06:24:28 +03:00
• 8a6de1a53f Simplify CUDA build workflow by removing Dockerfile rob thijssen 2025-09-13 06:07:01 +03:00
• 94ef423ff9 ci: build builders rob thijssen 2025-09-13 10:58:17 +08:00
• 9bfd75ba35 ci: syntax correction rob thijssen 2025-09-13 10:38:56 +08:00
• 9d648f06c7 ci: syntax correction rob thijssen 2025-09-13 10:33:06 +08:00
• 56c121e239 ci: syntax correction rob thijssen 2025-09-13 10:30:09 +08:00
• 0a95ec6f87 ci: build builders: cuda-build:12.9.0, cuda-build:13.0.0 rob thijssen 2025-09-13 10:25:52 +08:00
• 8db0496b88 sampling logic for debugging decisions rob thijssen 2025-09-13 04:52:01 +03:00
• 0aaacdf85d Add optional CUDA sampler support and big-endian SHA3 output rob thijssen 2025-09-13 04:02:06 +03:00
• 191cc799b7 fix: cuda metrics and initialize estimated rate gauge rob thijssen 2025-09-13 02:42:48 +03:00
• 300fa89927 Add optional metrics and big-endian limb support to CUDA engine rob thijssen 2025-09-13 01:54:54 +03:00
• 9fc95a1ca8 Add estimated rate and candidate metrics to mining jobs rob thijssen 2025-09-13 01:23:26 +03:00
• 4bffb144cb Add host re-verification for CUDA results and new metrics rob thijssen 2025-09-13 01:16:23 +03:00
• 9c87c711b3 script support for cuda miner binary builds on dev workstation rob thijssen 2025-09-13 01:16:07 +03:00
• 92f58d1b76 immutable bindings for is_g2 and d_distance rob thijssen 2025-09-13 00:10:40 +03:00
• 4ca906ac1b corrected host-side constant upload to pass CStrings rob thijssen 2025-09-12 23:55:04 +03:00
• 943d35100f Fix conditional use of n0_inv in qpow Montgomery kernels rob thijssen 2025-09-12 18:35:01 +03:00
• 398c9f9bc9 Use __constant__ memory for per-job constants in CUDA kernels rob thijssen 2025-09-12 18:14:26 +03:00
• b7f56fb05a Add CUDA miner environment presets for various NVIDIA GPUs rob thijssen 2025-09-12 17:19:23 +03:00
• 69cbb7fa99 remove 1024 thread cap in CUDA kernel launches rob thijssen 2025-09-12 16:24:45 +03:00
• 1d956c499e Allocate and copy-back CUDA output buffer for G1 path rob thijssen 2025-09-12 16:00:52 +03:00
• 297a74181a Refactor CUDA kernel launch to conditionally allocate output buffer rob thijssen 2025-09-12 15:52:21 +03:00
• 9167b8e48d Refactor CUDA kernel launch to separate G1 and G2 modes rob thijssen 2025-09-12 15:09:32 +03:00
• baf15fbb75 Add G2 kernel with device SHA3-512, early-exit, and threshold compare rob thijssen 2025-09-12 14:38:13 +03:00
• 5b44ef20df Use optional pinned host buffer and async copy for CUDA results rob thijssen 2025-09-12 14:00:53 +03:00
• c0fa1d15aa Limit SHA3 host hashing to remaining range and use scoped threads rob thijssen 2025-09-12 12:56:58 +03:00
• cec209170f Fix paths-ignore order in CUDA workflow triggers rob thijssen 2025-09-12 12:47:29 +03:00
• 99af459363 Reorder disk action step in CUDA build workflow rob thijssen 2025-09-12 12:44:04 +03:00
• 910e614cfb Add MINER_CUDA_IMAGE override and parallel host SHA3 workers rob thijssen 2025-09-12 12:40:47 +03:00
• abd8c878f7 Add disk space cleanup action and integrate in CUDA workflow rob thijssen 2025-09-12 11:29:06 +03:00
• 96875e12b2 Use self-hosted runner for quality-control job in CI workflow rob thijssen 2025-09-12 11:17:36 +03:00
• 9bb6dc840d Log SHA3 host timing after GPU result consumption rob thijssen 2025-09-12 11:15:42 +03:00
• 14115a12c1 Add timing logs for CUDA kernel and copy-back operations rob thijssen 2025-09-12 11:09:28 +03:00
• 39d9eed005 Add CARGO_TERM_COLOR=always environment variable to Containerfile rob thijssen 2025-09-12 09:35:37 +03:00
• 60d25d0d8e Export CUDA_TAG and SM args as environment variables in Containerfile rob thijssen 2025-09-12 09:34:02 +03:00
• bfeb0328cd Refactor CUDA build workflow to use repo Containerfile rob thijssen 2025-09-12 09:14:55 +03:00
• 6e089208ab Add fallback CUDA include paths in build script and deduplicate dirs rob thijssen 2025-09-12 08:57:28 +03:00
• 48e99f9db5 reduce artifact retention to 3 days and add CUDA_HOME env variable rob thijssen 2025-09-12 08:49:26 +03:00
• 70485d3d91 Remove optional rsync to CDN from CUDA build workflow rob thijssen 2025-09-12 08:39:29 +03:00
• c703e7d273 Fix condition to check SSH key presence correctly in workflow rob thijssen 2025-09-12 08:38:46 +03:00
• aef8c865cb clippy cleanup rob thijssen 2025-09-12 08:34:54 +03:00
• d2c39bbdcb ci: build cuda binaries rob thijssen 2025-09-12 08:29:09 +03:00
• 8b02b790a4 wip: cubin embed rob thijssen 2025-09-12 04:22:15 +03:00
• 222890dc92 cuda scaffold rob thijssen 2025-09-11 18:51:38 +08:00
• e107f03c5a Merge pull request #3 from Quantus-Network/feat/montgomery rob thijssen 2025-09-11 18:40:48 +08:00
• 50a620b9b4 fix clippy warning and simplify cpu feature detection in mont_portable module rob thijssen 2025-09-11 10:13:35 +03:00
• 113a2ad78c refactor montgomery normalization and fix mul target detection rob thijssen 2025-09-11 10:06:07 +03:00
• 80af3ce052 test triage rob thijssen 2025-09-11 09:38:30 +03:00
• 68c5835fc6 clippy cleanup rob thijssen 2025-09-11 09:19:07 +03:00
• 60cc91ddd6 taplo tidy rob thijssen 2025-09-11 09:07:20 +03:00
• f8e2378045 chore: replace references to deprecated --num-cores flag with --workers rob thijssen 2025-09-10 19:45:06 +08:00
• 63f271519d Add aarch64 UMULH/ADCS Montgomery backend and update docs rob thijssen 2025-09-11 01:42:06 +08:00
• 317734ad0e Add aarch64 UMULH optimized Montgomery multiplication backend rob thijssen 2025-09-11 01:32:31 +08:00
• ef2797d295 Add BMI2+ADX optimized Montgomery multiplication with inline asm rob thijssen 2025-09-11 01:21:15 +08:00
• 11839c07b2 feat: conditional metrics for engine-montgomery in miner-service cargo features rob thijssen 2025-09-10 23:36:56 +08:00
• 8b758492c1 fix: optional metrics feature to engine-montgomery crate rob thijssen 2025-09-10 23:17:01 +08:00
• 7ec802ee24 feat: montgomery-optimized cpu mining engine rob thijssen 2025-09-10 22:52:04 +08:00
• 604f61fd9d Merge pull request #2 from Quantus-Network/workers rob thijssen 2025-09-10 21:31:29 +08:00
• b035a497fc chore: replace references to deprecated --num-cores flag with --workers rob thijssen 2025-09-10 19:45:06 +08:00
• fc6a6b1014 Merge pull request #1 from Quantus-Network/feat/optimisation rob thijssen 2025-09-10 17:35:40 +08:00
• 1b4771ebc3 pr-cleanup: scrubbed references to implementation docs rob thijssen 2025-09-10 11:34:32 +08:00
• 7cbeb43b39 pr-cleanup rob thijssen 2025-09-10 11:08:39 +08:00
• b5cfa06ffe 09: unit tests rob thijssen 2025-09-10 10:46:36 +08:00
• cff7a3284b 08: cpuset metric and systemd units rob thijssen 2025-09-10 09:57:42 +08:00
• 49efb4ebc5 07: stable toolchain, rust validations rob thijssen 2025-09-09 21:39:01 +08:00
• 242bbe71f6 06: manipulator and difficulty rob thijssen 2025-09-09 19:41:38 +08:00
• d0382f875a 05: workers and dashboard sync rob thijssen 2025-09-09 12:18:04 +08:00
• ce600d454c fix: remove deprecated metrics update on job cancel and consolidate active job metrics update rob thijssen 2025-09-08 21:52:01 +08:00
• b69832bb4a 04: metrics chunking and dashboards rob thijssen 2025-09-08 17:01:43 +08:00
• e3b7da480d 00: roadmap to gpu rob thijssen 2025-09-07 21:48:07 +08:00
• ea40fdf6e5 03: engine comparability rob thijssen 2025-09-07 21:34:44 +08:00
• 85a4818c09 02: fix compiler issues rob thijssen 2025-09-07 20:49:47 +08:00
• 6cd53557d7 02: cpu fast engine and metrics rob thijssen 2025-09-07 20:48:01 +08:00
• 0d5adf583b 01: soc and metrics rob thijssen 2025-09-07 20:21:10 +08:00
• 614e23370e bump version to v0.2.0 GitHub Action 2025-08-29 13:04:05 +00:00
• e01af68954 Revert "chsnge version to 0.2" NIK 2025-08-29 20:00:55 +07:00