41 Commits

Author SHA1 Message Date
Andrzej Janik
407664600a Hack to read clang output 2021-08-07 16:16:59 +02:00
Andrzej Janik
3ce6aee65d Try seeking before reading 2021-08-07 16:06:15 +02:00
Andrzej Janik
3070d983ab Take path to llvm-spirv from environment 2021-08-07 15:29:19 +02:00
Andrzej Janik
fefdd528d5 Handle xnack suffix in device name 2021-08-07 15:21:45 +02:00
Andrzej Janik
479014a783 Wire up AMD compilation 2021-08-06 13:19:55 +02:00
Andrzej Janik
5bfc2a56b9 Remove all use of L0 2021-08-06 02:15:57 +02:00
Andrzej Janik
becda31524 Convert OpenCL host code to SVM 2021-08-04 19:34:56 +02:00
Andrzej Janik
638786b0ec Hack enough functionality that AMD GPU code builds 2021-08-03 00:22:47 +02:00
Andrzej Janik
b4de21fbc5 Use calls to OpenCL builtins when translating sregs, do SPIRV->LLVM conversion on every build 2021-08-02 01:04:05 +02:00
Andrzej Janik
8f68287b18 Tune generated code, add a workaround for geekbench 2021-07-25 15:19:43 +02:00
Andrzej Janik
9d4f26bd07 Finish converting to OpenCL 2021-07-22 00:20:33 +02:00
Andrzej Janik
3d2024bf62 Start converting to OpenCL 2021-07-21 01:46:50 +02:00
Andrzej Janik
58fb8a234c Synchronize through barrier 2021-07-06 00:16:46 +02:00
Andrzej Janik
2c6bee4955 Fix overzealus check 2021-07-05 01:14:46 +02:00
Andrzej Janik
5b593ec185 Implement stream-wide event reuse 2021-07-04 19:06:37 +02:00
Andrzej Janik
ce25035051 Use immediate command lists 2021-07-04 16:46:07 +02:00
Andrzej Janik
ecc33f7b10 Make everything async 2021-07-04 15:40:08 +02:00
Andrzej Janik
d76ffd691c Remember to actually submit workload 2021-07-04 13:24:35 +02:00
Andrzej Janik
b460e359ae First attempt at async host side 2021-07-04 12:54:27 +02:00
Andrzej Janik
b2a455e12e Bunch of tiny fixes and improvements 2021-06-28 01:40:35 +02:00
Andrzej Janik
196242b410 Revert "Fix offset calculation in kernel launch"
This reverts commit d7d38256e0580c3cfb649a641d9ed62c6ff0fc20.
2021-06-27 21:55:08 +02:00
Andrzej Janik
55fbe1abb5 Fix bugs related to replay on Linux 2021-06-27 16:19:04 +02:00
Andrzej Janik
d7d38256e0 Fix offset calculation in kernel launch 2021-06-27 13:08:46 +02:00
Andrzej Janik
b2765370e5 Fix more bugs 2021-06-27 11:46:59 +02:00
Andrzej Janik
015d23b5ad Add missing import 2021-06-27 02:36:41 +02:00
Andrzej Janik
1c0deca9e4 Add missing pub qualifier 2021-06-27 02:35:33 +02:00
Andrzej Janik
23306e944b Fix build on Linux 2021-06-27 02:33:57 +02:00
Andrzej Janik
2fc7af0434 Fix level zero bindings 2021-05-28 00:14:45 +02:00
Andrzej Janik
e40785aa74 Refactor L0 bindings 2021-05-27 02:05:17 +02:00
Andrzej Janik
89e72e4e95 Handle even more export table functions 2021-05-17 01:25:38 +02:00
Andrzej Janik
a39dda67d1 Make dumper compatible with older versions of CUDA 2021-04-10 23:01:01 +02:00
Andrzej Janik
8393dbd6e9 More fixes for 32bit 2021-04-09 22:00:23 +02:00
Andrzej Janik
94af72f46b Fix 32-bit builds 2021-04-09 20:32:37 +02:00
Andrzej Janik
a906c350f2 Make misc fixes (#41)
* Update ze_loader.lib to the newest version
* Export _ptsz/_ptds for which we have a legacy stream implementations
* Stop producing build logs if we are not looking at them anyway
2021-02-22 01:29:03 +01:00
Andrzej Janik
3e2e73ac33 Add script for replaying dumped kernel (#34)
zluda_dump can already create traces of GPU execution, this script can replay those traces.
Additionally, changed added just enough code in core ZLUDA to support simple PyCUDAexecution
2021-01-23 16:57:07 +01:00
Andrzej Janik
ff8135e8a3 Add a library for dumping kernels arguments before and after launch (#18) 2021-01-16 22:28:48 +01:00
Andrzej Janik
09f679693b Prevent linker from stripping exports on Linux (#33) 2021-01-15 01:17:44 +01:00
Andrzej Janik
5cd9a5fbc4 Add empty implementation of cuDeviceGetLuid (#30)
This function is required by recent versions of CUDA runtime on Windows
2021-01-08 19:43:46 +01:00
Andrzej Janik
078ae20c2c Improve build procedure and instructions (#28)
Fixes issues pointed out in #27:
* spirv_tools-sys was build in non-test profiles
* By default ZLUDA dll has a wrong name
* We relied on third-party OpenCL installation on Windows
* We encouraged building debug configuration
* We didn't provide build information for developers (cmake, python, submodules)
2021-01-08 17:17:46 +01:00
Andrzej Janik
690f4f3ad2 Append short project name to the device if there's not enough space for long name 2020-11-23 22:24:35 +01:00
Andrzej Janik
eb7c9aeeee Rename everything 2020-11-23 20:01:10 +01:00