 evghenii
|
4e7ae5269b
|
added pseudo_prefetch definitions
|
2014-10-14 14:48:02 +02:00 |
|
|
evghenii
|
9238c72e08
|
Merge branch 'master' into nvptx_clean_master
|
2014-10-14 14:27:00 +02:00 |
|
 Vsevolod Livinskiy
|
eb61d5df72
|
Support for cache 2/3 and all targets
|
2014-10-02 16:25:23 +04:00 |
|
|
Vsevolod Livinskiy
|
0a6eb61ad0
|
Extend gather-scatter optimization with prefetch optimization
|
2014-10-02 15:21:43 +04:00 |
|
|
evghenii
|
8745888ce9
|
merged with master
|
2014-08-11 10:04:54 +02:00 |
|
 Anton Mitrokhin
|
d0c9b7c9b5
|
wiped out all LLVM 3.1 support
|
2014-08-01 14:54:08 +04:00 |
|
|
Anton Mitrokhin
|
368d2f18f9
|
rewritten comment for util.m4
|
2014-07-30 16:43:41 +04:00 |
|
|
Anton Mitrokhin
|
7171701599
|
checked Makefile 'if' constructions, fixed ReleaseNotes.txt, added comments to util.m4
|
2014-07-30 16:25:39 +04:00 |
|
|
Anton Mitrokhin
|
725be222ac
|
added LLVM_3_6 var
|
2014-07-30 11:50:15 +04:00 |
|
|
evghenii
|
2dbb4d9890
|
remove dependenace on llvm-dis from 3.2
|
2014-07-08 15:11:13 +02:00 |
|
|
evghenii
|
fe150c539f
|
fix for exclusive_scan_and
|
2014-07-08 13:33:04 +02:00 |
|
|
evghenii
|
69f3898a61
|
Merge branch 'master' into nvptx_merge
|
2014-07-07 16:30:12 +02:00 |
|
 Ilia Filippov
|
76ea59b40b
|
support LLVM build
|
2014-06-18 17:53:42 +04:00 |
|
|
Evghenii
|
4641a15287
|
Merge branch 'master' into nvptx
|
2014-03-19 10:53:07 +01:00 |
|
 Dmitry Babokin
|
31b95b665b
|
Copyright update
|
2014-03-12 20:19:16 +04:00 |
|
|
Ilia Filippov
|
ead5cc741d
|
support LLVM trunk after 203559 203213 and 203381 revisions
|
2014-03-12 12:58:50 +04:00 |
|
|
Ilia Filippov
|
6738af0a0c
|
changing uniform_min and uniform_max implementations for avx targets
|
2014-03-06 12:05:24 +04:00 |
|
|
Evghenii
|
b60d77c154
|
use __nv_* libcalls for rcp/sqrt/rsqrt
|
2014-02-21 10:36:46 +01:00 |
|
|
Evghenii
|
ac05de6835
|
merged with master
|
2014-02-21 08:25:28 +01:00 |
|
|
Dmitry Babokin
|
f280b32fa4
|
Merge pull request #736 from egaburov/native_trigonometry
Native trigonometry
|
2014-02-20 19:18:35 +03:00 |
|
|
Evghenii
|
690a8acb30
|
merged with master
|
2014-02-20 15:22:09 +01:00 |
|
|
Evghenii
|
24e1a98275
|
compiles
|
2014-02-20 11:20:13 +01:00 |
|
|
Evghenii
|
4196c723eb
|
merged with nvptx
|
2014-02-20 11:01:58 +01:00 |
|
|
Dmitry Babokin
|
ea0a514e03
|
Fix for generic-1
|
2014-02-11 15:33:23 +04:00 |
|
|
Vsevolod Livinskij
|
65d947e449
|
Else branch with error report was added
|
2014-02-10 15:18:48 +04:00 |
|
|
Vsevolod Livinskij
|
cef5b2eb04
|
Some changes in saturation arithmetic
|
2014-02-10 12:40:53 +04:00 |
|
|
Vsevolod Livinskij
|
1c1614d207
|
Some errors in comments and code were fixed
|
2014-02-09 21:39:42 +04:00 |
|
|
Evghenii
|
70a9b286e5
|
added support for native and double precision trigonometry/transendentals
|
2014-02-07 15:28:39 +01:00 |
|
|
Evghenii
|
14e76108cb
|
optimization for _all
|
2014-02-06 14:24:50 +01:00 |
|
|
Evghenii
|
c23dd8a951
|
fixed __puts_nvptx
|
2014-02-05 17:48:04 +01:00 |
|
|
Evghenii
|
7b2ceba128
|
added "internal" for helper functions to avoid them being exported to PTX
|
2014-02-05 17:02:05 +01:00 |
|
|
evghenii
|
09e8381ec7
|
change {rsqrt,rcp}_double to {rsqrt,rcp}d_decl
|
2014-02-05 13:05:04 +01:00 |
|
|
Evghenii
|
686c1d676d
|
improvements
|
2014-02-05 12:04:36 +01:00 |
|
|
Evghenii
|
048da693c5
|
fix sqrt
|
2014-02-05 10:52:08 +01:00 |
|
|
Evghenii
|
d3a6693eef
|
adding __have_native_{rsqrtd,rcpd} to select between native support for double precision reciprocals and using slower but safe version in stdlib
|
2014-02-04 16:29:23 +01:00 |
|
|
Evghenii
|
fe98fe8cdc
|
added fast approximate rcp(double) accurate to 15 digits
|
2014-02-04 15:23:34 +01:00 |
|
|
Evghenii
|
eb1a495a7a
|
added support for fast approximate rsqrt(double). Provide 16 digit accurancy but is over 3x faster than 1/sqrt(double)
|
2014-02-04 14:44:54 +01:00 |
|
|
Evghenii
|
c2ed214a74
|
added declaretion for movmsk_ptx
|
2014-02-03 08:57:27 +01:00 |
|
|
Evghenii
|
98c82242c5
|
allowed static and disable memcpy/memmove/memset operations
|
2014-02-03 08:02:50 +01:00 |
|
|
evghenii
|
3a72e05c3e
|
+1
|
2014-02-02 18:16:48 +01:00 |
|
|
Evghenii
|
673d814a45
|
first commit for __do_print in ptx.
|
2014-01-27 11:56:21 +01:00 |
|
|
Evghenii
|
a3b00fdcd6
|
added support for global atomics
|
2014-01-26 14:23:26 +01:00 |
|
|
Evghenii
|
a7d4a3f922
|
fix for __any
|
2014-01-26 13:15:13 +01:00 |
|
|
Evghenii
|
3e86dfe480
|
fix for __any
|
2014-01-25 17:09:11 +01:00 |
|
|
Evghenii
|
fcbdd93043
|
half/scan for 64 bit/clock/num_cores and other additions
|
2014-01-25 16:43:33 +01:00 |
|
|
Evghenii
|
805196a6a0
|
fixed doubles
|
2014-01-25 15:31:56 +01:00 |
|
|
Evghenii
|
bd34729217
|
added floor/ceil/round for float/double
|
2014-01-25 12:20:38 +01:00 |
|
|
Evghenii
|
6917c161c8
|
fixed reduce_equal
|
2014-01-25 11:39:37 +01:00 |
|
|
Evghenii
|
156aa4c139
|
partial support for reduce equal
|
2014-01-24 17:29:26 +01:00 |
|
|
Evghenii
|
ddb9b2fc47
|
added basic printing from ptx
|
2014-01-24 13:44:38 +01:00 |
|