mirrors/ZLUDA
1
0
Fork 0
mirror of https://github.com/vosen/ZLUDA.git synced 2025-04-20 00:14:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Commit graph

  • 659b2c6ec4 Merge commit '4b96dbc8f49c5ae00c96935e0b576df88a5d8af9' Andrzej Janik 2021-01-03 17:54:01 +01:00
  • 4b96dbc8f4 Squashed 'ext/detours/' changes from 39aa864..36b69b9 Andrzej Janik 2021-01-03 17:54:01 +01:00
  • 77523940b3 Merge commit 'dabc40cb19bf4e297c32284d26c74adbd6775e49' as 'ext/detours' Andrzej Janik 2021-01-03 17:52:14 +01:00
  • dabc40cb19 Squashed 'ext/detours/' content from commit 39aa864 Andrzej Janik 2021-01-03 17:52:14 +01:00
  • ae950163cd
         Add building only CI (#25) Takeshi Watanabe 2020-12-30 06:54:48 +09:00
  • ceddaffca5
         Update rust.yml Takeshi Watanabe 2020-12-25 10:30:30 +09:00
  • 98da1588b0
         Update rust.yml Takeshi Watanabe 2020-12-24 20:52:10 +09:00
  • 928401500d
         Update rust.yml Takeshi Watanabe 2020-12-24 20:38:30 +09:00
  • b8e33672e5
         Update rust.yml Takeshi Watanabe 2020-12-24 20:17:33 +09:00
  • 5dacefae15
         Install newer compute runtime Takeshi Watanabe 2020-12-24 20:04:48 +09:00
  • 3ac54b8919
         Update rust.yml Takeshi Watanabe 2020-12-24 19:33:48 +09:00
  • d1233afa29
         Fix opencl install Takeshi Watanabe 2020-12-24 19:30:12 +09:00
  • 060540b606
         Install libze-loader-dev too Takeshi Watanabe 2020-12-24 19:26:12 +09:00
  • 5fb20d337f
         Install opencl Takeshi Watanabe 2020-12-24 19:21:34 +09:00
  • 1292abdfd3
         Setup cache for cargo Takeshi Watanabe 2020-12-24 19:14:53 +09:00
  • 153421b1c6
         Checkout submodules Takeshi Watanabe 2020-12-24 19:08:51 +09:00
  • 44cd85eeec
         Create rust.yml Takeshi Watanabe 2020-12-24 19:05:22 +09:00
  • c984dfa87d
         Added known build issues and workarounds Puspendu Banerjee 2020-12-21 00:21:44 -06:00
  • 5a9fa74ca0
         Added Known build issues and workarounds Puspendu Banerjee 2020-12-19 22:46:20 -06:00
  • 06153f81bf
         Added Known build issues and workarounds Puspendu Banerjee 2020-12-19 22:41:18 -06:00
  • 63af70a01f
         Fix builtins generation, mark ld/st as aligned (#22) Andrzej Janik 2020-12-12 20:40:24 +01:00
  • e7b663d557 Mark loads and stores as aligned Andrzej Janik 2020-12-12 20:37:36 +01:00
  • 8b8a688cef Fix bugs Andrzej Janik 2020-12-10 02:10:50 +01:00
  • a3cfa24593
         Fix SPIR-V code generation for PTX special registers (#21) Andrzej Janik 2020-12-11 21:31:08 +01:00
  • 22ead3ea56 Fix bugs Andrzej Janik 2020-12-09 21:27:22 +01:00
  • 35c18d4bb9 Add casts to convert PTX -> SPIRV builtins Andrzej Janik 2020-12-09 02:01:31 +01:00
  • 5976e55b2b Start fixing builtins Andrzej Janik 2020-12-04 00:15:42 +01:00
  • 770a379452
         Refactor how vectors are handled (#20) vosen 2020-12-09 00:20:06 +01:00
  • 0c880043d5 Simplify operand types Andrzej Janik 2020-12-09 00:16:36 +01:00
  • eee780e7b4 Fix failures with access to builtins Andrzej Janik 2020-12-08 22:49:33 +01:00
  • 18d5aa85b5 Reimplement vector member access Andrzej Janik 2020-12-08 00:46:10 +01:00
  • 100831daaf Remove CompositeRead statement and clean up statement visitor traits Andrzej Janik 2020-12-07 00:37:39 +01:00
  • eb841b3a88 Introduce vector repack statement Andrzej Janik 2020-12-06 00:47:56 +01:00
  • adf88bc1af Update parser Andrzej Janik 2020-12-05 12:30:49 +01:00
  • 00b8d8d87f Start refactoring vector-handling code Andrzej Janik 2020-12-04 19:50:08 +01:00
  • a6a9eb347b
         Merge pull request #15 from nilsmartel/patch-2 vosen 2020-11-29 00:36:05 +01:00
  • 295a70e1cb
         Merge pull request #14 from ritschwumm/patch-1 vosen 2020-11-29 00:35:44 +01:00
  • 1daeaa7a75
         Fix typo in README David 2020-11-28 02:58:12 -05:00
  • f452550c4f
         Fix small typo Nils Martel 2020-11-27 14:26:27 +01:00
  • b11ba3d1f3
         fix typo in readme ritschwumm 2020-11-27 07:24:51 +01:00
  • 103881f70a Update wording, add license Andrzej Janik 2020-11-24 23:23:53 +01:00
  • 892e47a653 Update README with links to GeekBench results v1 Andrzej Janik 2020-11-23 22:37:57 +01:00
  • b62b4ab6dc Support -nolocalra hack Andrzej Janik 2020-11-23 22:24:56 +01:00
  • 690f4f3ad2 Append short project name to the device if there's not enough space for long name Andrzej Janik 2020-11-23 22:24:35 +01:00
  • 8fa044004f Change wording slightly Andrzej Janik 2020-11-23 22:18:30 +01:00
  • 25fc385b8d Add graph with Geekbench results Andrzej Janik 2020-11-23 22:15:59 +01:00
  • bcd1740ba9 Add README and rebuild .spv library Andrzej Janik 2020-11-23 21:50:21 +01:00
  • db491dadf2 Remove temporary file Andrzej Janik 2020-11-23 20:02:47 +01:00
  • eb7c9aeeee Rename everything Andrzej Janik 2020-11-23 20:00:16 +01:00
  • 0415f873ae Throw away useless stuff Andrzej Janik 2020-11-23 19:44:57 +01:00
  • cd141590be Fix typo in selp Andrzej Janik 2020-11-22 21:50:54 +01:00
  • 2e8e55738c Add 8bit memset Andrzej Janik 2020-11-22 18:42:34 +01:00
  • 6e39c4a90c Fix linking with shl/shr, add memset on host and support __assertfail Andrzej Janik 2020-11-21 01:53:07 +01:00
  • 84ac086146 Fix problems with linking Andrzej Janik 2020-11-21 00:27:37 +01:00
  • 70dc298381 Fix buggy handling of u8 shared memory Andrzej Janik 2020-11-20 00:07:50 +01:00
  • f77b653d36 Implement stateless-to-stateful optimization Andrzej Janik 2020-11-19 22:12:12 +01:00
  • eac5fbd806 Support more property queries Andrzej Janik 2020-11-14 15:48:05 +01:00
  • a6765baa3a Add back erroneously removed functionality Andrzej Janik 2020-11-12 21:08:28 +01:00
  • a2e77fe961 Refactor host code to use one big lock Andrzej Janik 2020-11-11 22:35:34 +01:00
  • 7c93997cc9 Append project URL to device name and add few missing CUDA v1 functions Andrzej Janik 2020-11-07 18:08:09 +01:00
  • 62d14cdffe Fix ftz behavior slightly Andrzej Janik 2020-11-07 16:14:37 +01:00
  • ac6265f257 Implement instructions bfe, rem, xor Andrzej Janik 2020-11-06 00:56:45 +01:00
  • d7bf1acf84 Implement instructions clz, brev, popc Andrzej Janik 2020-11-05 22:10:06 +01:00
  • 8e409254b3 Fix same width float-to-float conversions Andrzej Janik 2020-11-05 21:39:34 +01:00
  • 96702d86c9 Fix issues with .param/.local and implement sin, cos, ex2, lg2 Andrzej Janik 2020-11-05 00:27:46 +01:00
  • e5a53ed5d3 Implement neg instruction Andrzej Janik 2020-11-01 14:58:44 +01:00
  • b7d61baf37 Implement div, sqrt, rsqrt and more of setp Andrzej Janik 2020-11-01 14:34:03 +01:00
  • a82eb20817 Implement atomic instructions Andrzej Janik 2020-10-31 21:28:15 +01:00
  • 861116f223 Add support for fma instruction Andrzej Janik 2020-10-26 23:46:28 +01:00
  • c8dadca7d2 Implement selp instruction Andrzej Janik 2020-10-26 19:18:23 +01:00
  • fc7cc00f47 Add support for and instruction Andrzej Janik 2020-10-26 18:45:28 +01:00
  • 40bdb83e6b Support float constants Andrzej Janik 2020-10-26 01:49:25 +01:00
  • 17b788f2a7 Implement ftz handling through Intel extension Andrzej Janik 2020-10-25 21:09:16 +01:00
  • 45f5183370 Implement ftz handling through Khronos extensions Andrzej Janik 2020-10-25 19:29:28 +01:00
  • 6480cccc4f Implement rcp instruction Andrzej Janik 2020-10-25 11:21:51 +01:00
  • eb9053a42f Add test for indirect shared mem use Andrzej Janik 2020-10-25 10:34:09 +01:00
  • 85ee8210df Add dynamic shared mem support Andrzej Janik 2020-10-25 00:24:40 +02:00
  • 28a0968294 Fix small regression Andrzej Janik 2020-10-18 15:06:37 +02:00
  • 2b3ecc99e3 Implement pass to handle .extern .shared and add parsing code for it Andrzej Janik 2020-10-18 14:46:05 +02:00
  • 27d25865af Add support for top-level global variables, improve array support Andrzej Janik 2020-10-02 20:34:45 +02:00
  • 9a65dd32f5 Add sub, min, max Andrzej Janik 2020-10-02 00:11:28 +02:00
  • bd3d440dba Implement or Andrzej Janik 2020-10-01 20:28:57 +02:00
  • 96a342e33f Implement shr Andrzej Janik 2020-10-01 18:13:09 +02:00
  • 3e92921275 Fix remaining bugs in vector destructuring and in the process improve implicit conversions Andrzej Janik 2020-10-01 00:44:58 +02:00
  • 1e0b35be4b Implement vector-destructuring mov/ld/st Andrzej Janik 2020-09-27 23:51:34 +02:00
  • 7c26568cbf Add test for vector extract Andrzej Janik 2020-09-27 13:51:52 +02:00
  • e0190fcbe1 Add missing support for Milestone 1 Andrzej Janik 2020-09-27 13:14:19 +02:00
  • 42bcd999eb Fix minor problems with a private CUDA function Andrzej Janik 2020-09-24 02:20:54 +02:00
  • 3f41f21acb Implement more host code, moving execution further Andrzej Janik 2020-09-24 01:54:16 +02:00
  • 03005140dd Add a workaround for IGC bug Andrzej Janik 2020-09-23 00:40:26 +02:00
  • 5a7860d9f1 Fix more bugs in implicit conversions Andrzej Janik 2020-09-20 20:43:09 +02:00
  • b11ce92d2c Better propagate information about address-mov and emit conversion for it Andrzej Janik 2020-09-20 17:29:38 +02:00
  • dcaea507ba Add more tests Andrzej Janik 2020-09-20 15:44:52 +02:00
  • 17f2d09cc7 Fix basic test failures Andrzej Janik 2020-09-18 20:19:35 +02:00
  • bcb749cdd9 Continue working on a better addressable support Andrzej Janik 2020-09-18 18:08:40 +02:00
  • 952ed5d504 [BROKEN] Start implementing better support for addressable arguments Andrzej Janik 2020-09-18 02:25:20 +02:00
  • 42bad8fcc2 Fix st/ld offsets implement abs and fix remaining bugs from vectorAdd generation Andrzej Janik 2020-09-16 00:20:49 +02:00
  • fcf3aaeb16 Implement missing pieces in vector support Andrzej Janik 2020-09-15 02:34:08 +02:00
  • bb5025c9b1 Refactor implicit conversions and start implementing vector extract/insert Andrzej Janik 2020-09-14 21:45:56 +02:00
  • 48dac43540 Parse vector movs (mov.type a.x b.y;) Andrzej Janik 2020-09-12 02:33:20 +02:00