Commit Graph

  • e4eec8ab4d vx_spawn.c: Handle num_clusters > 1 Hansung Kim 2024-03-28 20:16:44 -07:00
  • a9b0814211 sgemm_wg: Document tiling parameter constraints Hansung Kim 2024-03-28 18:17:00 -07:00
  • 9673db4e8c sgemm_wg: Fix possible divide-by-0 Hansung Kim 2024-03-28 17:35:47 -07:00
  • d8f9359fae test case update joshua 2024-03-28 13:04:02 -07:00
  • 08d7721e11 annoying swizzling problems joshua 2024-03-28 03:00:15 -07:00
  • 9555b790e7 sgemm_wg: ifdef-guard cluster specific code Hansung Kim 2024-03-27 22:45:51 -07:00
  • 09822764e7 sgemm_wg: Remove software-based barrier implementation Hansung Kim 2024-03-27 22:43:25 -07:00
  • 870846f20f vx_spawn.c: Create separate vx_spawn_tasks_contiguous Hansung Kim 2024-03-27 15:38:52 -07:00
  • fa6adceb7e vecaddx: Hardcode args/input device address to match chipyard Hansung Kim 2024-03-27 15:15:38 -07:00
  • 4e834f2103 vx_spawn.c: Rewrite cluster-based vx_spawn_tasks variant Hansung Kim 2024-03-27 15:09:45 -07:00
  • e16584ddd9 bleh still not work joshua 2024-03-27 00:26:04 -07:00
  • df1f7f242a vx_spawn.c: Implement spawn_tasks_cluster_rem_stub Hansung Kim 2024-03-26 23:51:59 -07:00
  • b88dbd7a83 add cycle count and multi core support Richard Yan 2024-03-26 16:43:49 -07:00
  • b545809496 vecaddx: Use -DRADIANCE Hansung Kim 2024-03-26 16:42:36 -07:00
  • 4d2c0084d1 common.mk: Compile separate cluster ELF Hansung Kim 2024-03-26 16:37:44 -07:00
  • 3729a05adc vx_spawn.c: Separate cluster-based scheduling code from original Hansung Kim 2024-03-26 16:36:57 -07:00
  • f050a08d77 Write vx_spawn_tasks_cluster Hansung Kim 2024-03-26 10:45:14 -07:00
  • 7f00e6c376 vecaddx: Change arg device address to 7fff0000 Hansung Kim 2024-03-26 10:44:33 -07:00
  • cc7b34ec5b vecaddx: Write args.bin and input.bin Hansung Kim 2024-03-26 10:44:02 -07:00
  • ff401bdec0 Cleanup tests/.gitignore Hansung Kim 2024-03-24 01:47:00 -07:00
  • 7d177492b2 Move CORES_PER_CLUSTER to vx_spawn.h Hansung Kim 2024-03-24 01:45:30 -07:00
  • 8f3474b151 Don't clean *.bin Hansung Kim 2024-03-24 01:45:08 -07:00
  • f590c4b417 Add vx_spawn.h as dependency to kernel/Makefile Hansung Kim 2024-03-24 01:44:49 -07:00
  • b254281295 initial tcore impl joshua 2024-03-21 01:29:38 -07:00
  • c18267443f matmul kernel switch to proper fence and fsm Richard Yan 2024-03-20 15:22:25 -07:00
  • 94ad1850a9 implement correct gemmini fence and loop fsm support Richard Yan 2024-03-20 15:18:31 -07:00
  • f9b4509936 initial tensor core joshua 2024-03-20 02:46:00 -07:00
  • 978dd3bdfe seemingly working fp32 implementation joshua 2024-03-19 17:56:59 -07:00
  • 12ee2a3a0f Write cluster-aware thread scheduling Hansung Kim 2024-03-18 16:40:02 -07:00
  • 3e6771237f Merge remote-tracking branch 'sungwoong/master' into kernels Hansung Kim 2024-03-14 09:48:31 -07:00
  • 2036d37840 sgemm_wg: Prevent run-ahead using ternary flags; reduce mem accesses Hansung Kim 2024-03-13 21:32:57 -07:00
  • 510a834db5 sgemm_wg: Implement software barrier for inter-core synchronization Hansung Kim 2024-03-12 15:34:42 -07:00
  • fbe872c831 sgemm_wg: Add missing makefile dep to common.h Hansung Kim 2024-03-12 15:34:17 -07:00
  • beb3dce46d integer reduction unit joshua 2024-03-06 01:39:17 -08:00
  • 3c2a266d37 second pass Sungwoong Ha 2024-03-01 21:27:26 -08:00
  • a9709edae2 first pass Sungwoong Ha 2024-03-01 21:05:52 -08:00
  • 6f4dfe5a0e sgemm_wg: Implement 2D threadtiling Hansung Kim 2024-02-29 14:40:54 -08:00
  • a06b2dd20e sgemm_wg: Cleanup & proper unroll Hansung Kim 2024-02-28 21:17:42 -08:00
  • 46f242e520 sgemm_wg: Constantify BM/BN/BK/TM, computationally set gridsize and TB/core Hansung Kim 2024-02-27 22:23:25 -08:00
  • 27646bb507 sgemm_wg: Implement multiple C per thread with sliding A/B blocks Hansung Kim 2024-02-27 22:06:01 -08:00
  • a2ea27b2b5 vx_spawn: Add spawn_tasks_contiguous_all_stub Hansung Kim 2024-02-27 15:46:02 -08:00
  • 2b1b5fe537 convolution: Fix write_operand_file after upstream merge Hansung Kim 2024-02-27 15:45:22 -08:00
  • f1e7407d3a sgemm_wg: Run multiple threadblock per core Hansung Kim 2024-02-27 15:44:04 -08:00
  • 5b1c527186 Merge branch 'kernels' of https://github.com/hansungk/vortex into kernels Richard Yan 2024-02-24 00:27:23 -08:00
  • 914864206a MMIO gemmini matmul kernel Richard Yan 2024-02-24 00:27:16 -08:00
  • be7d87c82d temp Sungwoong Ha 2024-02-22 16:31:42 -08:00
  • d2da0d3394 sgemm_wg: Parameterize threadblock dimensions Hansung Kim 2024-02-17 18:05:59 -08:00
  • 301f1ca260 sgemm_wg: Implement blocking over k-dimension Hansung Kim 2024-02-16 16:20:45 -08:00
  • 5f79e8a3f1 sgemm_wg: reference matmul in cpu Hansung Kim 2024-02-12 22:29:38 -08:00
  • 6b420aceb6 sgemm_wg: write simple C=A*A matmul Hansung Kim 2024-02-12 22:22:28 -08:00
  • a43d5eb1a7 Merge remote-tracking branch 'upstream/master' into kernels Hansung Kim 2024-02-12 20:50:32 -08:00
  • 6a1a506b64 sgemm_wg: save args and input bin Hansung Kim 2024-02-12 20:48:23 -08:00
  • f586ab28df vecadd: save operand to file Hansung Kim 2024-02-12 20:47:36 -08:00
  • 5a216ef9ca flops: unroll by 16 Hansung Kim 2024-02-12 20:46:50 -08:00
  • 5f2b10b8a6 minor update Blaise Tine 2024-02-09 21:20:23 -08:00
  • 3fee1a6193 minor update Blaise Tine 2024-02-09 20:34:44 -08:00
  • c258557999 Merge branch 'kernels' of https://github.com/hansungk/vortex into kernels Richard Yan 2024-02-08 17:05:37 -08:00
  • 12bdab8043 update gemmini matmul kernel Richard Yan 2024-02-08 17:00:19 -08:00
  • ae7b01405c CI minor update Blaise Tine 2024-02-08 14:10:00 -08:00
  • ad8bf9b223 Add sgemm_wg C kernel Hansung Kim 2024-02-07 21:31:08 -08:00
  • be0db6e1a5 minor update Blaise Tine 2024-02-04 20:32:05 -08:00
  • 50028c1a33 Merge remote-tracking branch 'origin' into develop Blaise Tine 2024-02-04 20:19:30 -08:00
  • 8d4b6c804f minor update Blaise Tine 2024-02-04 20:17:12 -08:00
  • 6f7a389a1f arbiters unlock refactoring Blaise Tine 2024-02-04 20:16:18 -08:00
  • fe15647f98 minor update Blaise Tine 2024-02-04 02:11:53 -08:00
  • b0b7cd2b1e minor updates Blaise Tine 2024-02-03 19:09:53 -08:00
  • b5bfa7d4b9 Fix bogus spad address Hansung Kim 2024-02-01 14:05:13 -08:00
  • 0462a91953 Update mmio kernel to do single gemm Hansung Kim 2024-02-01 13:52:29 -08:00
  • f9cd8be19e minor update Blaise Tine 2024-01-31 13:35:43 -08:00
  • dab262e4f7 Merge branch 'develop' of https://github.com/vortexgpgpu/vortex into develop Blaise Tine 2024-01-31 12:03:50 -08:00
  • 8ab7c590fd disabling fetch's deadlock check when L1 caches are present Blaise Tine 2024-01-31 06:16:54 -08:00
  • e2d1387df8 elastic buffers classification Blaise Tine 2024-01-31 00:39:37 -08:00
  • fd65ed95eb fix bug to access memory address in simx Shinnung Jeong 2024-01-30 20:45:47 -05:00
  • b31d868a27 Merge branch 'develop' Blaise Tine 2024-01-28 17:34:46 -08:00
  • b6919d19a7 minor update Blaise Tine 2024-01-28 17:34:07 -08:00
  • 6045597ad0 Merge branch 'develop' Blaise Tine 2024-01-28 00:25:55 -08:00
  • 1c1140d517 Merge branch 'develop' of https://github.com/vortexgpgpu/vortex into develop Blaise Tine 2024-01-28 00:25:16 -08:00
  • 38b92ad592 - using SV_DPI defines to disable DPI in synthesis-based simulations - fixed Intel ASE run script: run_ase.sh Blaise Tine 2024-01-28 00:22:21 -08:00
  • 7f6f1d605f Add bare mmio kernel Hansung Kim 2024-01-24 16:24:19 -08:00
  • a9d578f3ab Docs update lpc97667 2024-01-10 15:56:22 -05:00
  • f0e6a435f8 Merge branch 'develop' Blaise Tine 2024-01-03 19:09:49 -08:00
  • 648bf75b0b minor update Blaise Tine 2024-01-03 19:09:18 -08:00
  • 3b75418ea9 Merge branch 'develop' Blaise Tine 2024-01-03 10:24:48 -08:00
  • f2e8317412 updated documentation Blaise Tine 2024-01-03 10:23:38 -08:00
  • a5c50b60c8 Add 'smemcoherence' kernel Hansung Kim 2024-01-02 20:28:40 -08:00
  • edb385f138 Increase smem read loop iter Hansung Kim 2024-01-01 14:26:19 -08:00
  • ee1ed315e2 Write out operand files in sharedmem kernel Hansung Kim 2024-01-01 14:26:10 -08:00
  • 1586ea93ef Add new 'sharedmem' kernel Hansung Kim 2024-01-01 13:56:46 -08:00
  • cc042a4098 Merge branch 'develop' Blaise Tine 2023-12-31 15:30:20 -08:00
  • bd18b03cc3 minor update Blaise Tine 2023-12-31 15:29:04 -08:00
  • e7f8b40d93 minor update Blaise Tine 2023-12-31 11:46:41 -08:00
  • ec2a35def9 Merge branch 'develop' Blaise Tine 2023-12-31 11:26:48 -08:00
  • 031d24e695 minor updates Blaise Tine 2023-12-30 00:52:44 -08:00
  • 645ca62c91 Merge branch 'develop' Blaise Tine 2023-12-29 15:14:23 -08:00
  • 7425446b15 fixed DESTDIR support in simumation Makefiles Blaise Tine 2023-12-29 14:11:16 -08:00
  • a7548db5ec Merge branch 'develop' Blaise Tine 2023-12-28 20:08:12 -08:00
  • e62d122c9b enabling temporary build directory for blackbox multiple instances Blaise Tine 2023-12-28 20:06:10 -08:00
  • e8cbfb4a72 Merge branch 'develop' Blaise Tine 2023-12-28 16:11:29 -08:00
  • 51e621cdf1 minor update Blaise Tine 2023-12-28 16:08:26 -08:00
  • afea903332 Merge branch 'develop' Blaise Tine 2023-12-28 12:33:58 -08:00