Andrzej Janik
|
cd141590be
|
Fix typo in selp
|
2020-11-22 21:50:54 +01:00 |
|
Andrzej Janik
|
2e8e55738c
|
Add 8bit memset
|
2020-11-22 18:42:34 +01:00 |
|
Andrzej Janik
|
6e39c4a90c
|
Fix linking with shl/shr, add memset on host and support __assertfail
|
2020-11-21 01:53:07 +01:00 |
|
Andrzej Janik
|
84ac086146
|
Fix problems with linking
|
2020-11-21 00:27:37 +01:00 |
|
Andrzej Janik
|
70dc298381
|
Fix buggy handling of u8 shared memory
|
2020-11-20 00:07:50 +01:00 |
|
Andrzej Janik
|
f77b653d36
|
Implement stateless-to-stateful optimization
|
2020-11-19 22:12:12 +01:00 |
|
Andrzej Janik
|
eac5fbd806
|
Support more property queries
|
2020-11-14 15:48:05 +01:00 |
|
Andrzej Janik
|
a6765baa3a
|
Add back erroneously removed functionality
|
2020-11-12 22:47:14 +01:00 |
|
Andrzej Janik
|
a2e77fe961
|
Refactor host code to use one big lock
|
2020-11-12 20:12:14 +01:00 |
|
Andrzej Janik
|
7c93997cc9
|
Append project URL to device name and add few missing CUDA v1 functions
|
2020-11-07 18:08:09 +01:00 |
|
Andrzej Janik
|
62d14cdffe
|
Fix ftz behavior slightly
|
2020-11-07 16:14:37 +01:00 |
|
Andrzej Janik
|
ac6265f257
|
Implement instructions bfe, rem, xor
|
2020-11-06 00:56:45 +01:00 |
|
Andrzej Janik
|
d7bf1acf84
|
Implement instructions clz, brev, popc
|
2020-11-05 22:10:06 +01:00 |
|
Andrzej Janik
|
8e409254b3
|
Fix same width float-to-float conversions
|
2020-11-05 21:39:34 +01:00 |
|
Andrzej Janik
|
96702d86c9
|
Fix issues with .param/.local and implement sin, cos, ex2, lg2
|
2020-11-05 00:27:46 +01:00 |
|
Andrzej Janik
|
e5a53ed5d3
|
Implement neg instruction
|
2020-11-01 14:58:44 +01:00 |
|
Andrzej Janik
|
b7d61baf37
|
Implement div, sqrt, rsqrt and more of setp
|
2020-11-01 14:34:03 +01:00 |
|
Andrzej Janik
|
a82eb20817
|
Implement atomic instructions
|
2020-10-31 21:28:15 +01:00 |
|
Andrzej Janik
|
861116f223
|
Add support for fma instruction
|
2020-10-26 23:46:28 +01:00 |
|
Andrzej Janik
|
c8dadca7d2
|
Implement selp instruction
|
2020-10-26 19:18:23 +01:00 |
|
Andrzej Janik
|
fc7cc00f47
|
Add support for and instruction
|
2020-10-26 18:45:28 +01:00 |
|
Andrzej Janik
|
40bdb83e6b
|
Support float constants
|
2020-10-26 01:49:25 +01:00 |
|
Andrzej Janik
|
17b788f2a7
|
Implement ftz handling through Intel extension
|
2020-10-25 21:09:16 +01:00 |
|
Andrzej Janik
|
45f5183370
|
Implement ftz handling through Khronos extensions
|
2020-10-25 19:29:28 +01:00 |
|
Andrzej Janik
|
6480cccc4f
|
Implement rcp instruction
|
2020-10-25 11:21:51 +01:00 |
|
Andrzej Janik
|
eb9053a42f
|
Add test for indirect shared mem use
|
2020-10-25 10:34:09 +01:00 |
|
Andrzej Janik
|
85ee8210df
|
Add dynamic shared mem support
|
2020-10-25 00:24:40 +02:00 |
|
Andrzej Janik
|
28a0968294
|
Fix small regression
|
2020-10-18 15:06:37 +02:00 |
|
Andrzej Janik
|
2b3ecc99e3
|
Implement pass to handle .extern .shared and add parsing code for it
|
2020-10-18 14:46:05 +02:00 |
|
Andrzej Janik
|
27d25865af
|
Add support for top-level global variables, improve array support
|
2020-10-04 19:53:07 +02:00 |
|
Andrzej Janik
|
9a65dd32f5
|
Add sub, min, max
|
2020-10-02 00:11:28 +02:00 |
|
Andrzej Janik
|
bd3d440dba
|
Implement or
|
2020-10-01 20:28:57 +02:00 |
|
Andrzej Janik
|
96a342e33f
|
Implement shr
|
2020-10-01 18:13:09 +02:00 |
|
Andrzej Janik
|
3e92921275
|
Fix remaining bugs in vector destructuring and in the process improve implicit conversions
|
2020-10-01 18:11:57 +02:00 |
|
Andrzej Janik
|
1e0b35be4b
|
Implement vector-destructuring mov/ld/st
|
2020-09-30 19:27:29 +02:00 |
|
Andrzej Janik
|
7c26568cbf
|
Add test for vector extract
|
2020-09-27 13:51:52 +02:00 |
|
Andrzej Janik
|
e0190fcbe1
|
Add missing support for Milestone 1
|
2020-09-27 13:14:19 +02:00 |
|
Andrzej Janik
|
42bcd999eb
|
Fix minor problems with a private CUDA function
|
2020-09-24 02:20:54 +02:00 |
|
Andrzej Janik
|
3f41f21acb
|
Implement more host code, moving execution further
|
2020-09-24 01:54:16 +02:00 |
|
Andrzej Janik
|
03005140dd
|
Add a workaround for IGC bug
|
2020-09-23 00:40:26 +02:00 |
|
Andrzej Janik
|
5a7860d9f1
|
Fix more bugs in implicit conversions
|
2020-09-20 20:43:09 +02:00 |
|
Andrzej Janik
|
b11ce92d2c
|
Better propagate information about address-mov and emit conversion for it
|
2020-09-20 17:29:38 +02:00 |
|
Andrzej Janik
|
dcaea507ba
|
Add more tests
|
2020-09-20 15:44:52 +02:00 |
|
Andrzej Janik
|
17f2d09cc7
|
Fix basic test failures
|
2020-09-18 20:19:35 +02:00 |
|
Andrzej Janik
|
bcb749cdd9
|
Continue working on a better addressable support
|
2020-09-18 18:08:40 +02:00 |
|
Andrzej Janik
|
952ed5d504
|
[BROKEN] Start implementing better support for addressable arguments
|
2020-09-18 02:25:20 +02:00 |
|
Andrzej Janik
|
42bad8fcc2
|
Fix st/ld offsets implement abs and fix remaining bugs from vectorAdd generation
|
2020-09-16 00:20:49 +02:00 |
|
Andrzej Janik
|
fcf3aaeb16
|
Implement missing pieces in vector support
|
2020-09-15 02:34:08 +02:00 |
|
Andrzej Janik
|
bb5025c9b1
|
Refactor implicit conversions and start implementing vector extract/insert
|
2020-09-14 21:45:56 +02:00 |
|
Andrzej Janik
|
48dac43540
|
Parse vector movs (mov.type a.x b.y;)
|
2020-09-12 02:33:20 +02:00 |
|