Evghenii
1c2dbd6a27
a fix for .b0 ptx and some other code improvements
2014-01-27 08:51:05 +01:00
Evghenii
09ea9c9fd6
added function name mangling for operators
2014-01-25 18:06:12 +01:00
Evghenii
fcbdd93043
half/scan for 64 bit/clock/num_cores and other additions
2014-01-25 16:43:33 +01:00
Evghenii
6931f87fcd
added support to run test via NVVM
2014-01-22 10:16:37 +01:00
Evghenii
bc99897fbb
+fixed some example, found some bugs, and bugs in ptxas/cuda
2014-01-21 14:51:27 +01:00
Evghenii
63d3ac6679
Merge branch 'master' into nvptx
2014-01-20 13:47:24 +01:00
Dmitry Babokin
6d59ef49f7
Merge pull request #713 from ifilippov/perf_correction
...
Support of LLVM trunk after changes in 198438, 199041, 199082 revisions.
2014-01-15 03:49:15 -08:00
Ilia Filippov
5fa8bd3c78
changes for support LLVM trunk
2014-01-15 14:17:35 +04:00
Evghenii
f98a8cc22f
allow declaratoin of varying arrays in global scope. seems to work autmatically. needs more testing
2014-01-08 13:39:31 +01:00
Evghenii
de4d66c56f
added addrspace(4)/constant memory for const uniform declarations
2014-01-08 13:27:24 +01:00
Evghenii
f011b3cb22
added Error when varying variable is defined in global scope with nvptx target
2014-01-08 11:46:36 +01:00
Evghenii
8347c766f0
added uniform memory test.
2014-01-08 11:16:51 +01:00
Evghenii
0a66f17897
experimental support for non-constant [non-static] uniform arrays mapped to addrspace(3)
2014-01-08 11:06:14 +01:00
Evghenii
3972d740a6
added mask for tasking function
2014-01-06 16:18:28 +01:00
Evghenii
91d4ae46f6
sort --fails
2014-01-06 15:38:30 +01:00
Evghenii
546f9cb409
MAJOR CHANGE--- STOP WITH THIS BRANCH--
2014-01-06 13:51:02 +01:00
james.brodman
4a4da858cf
Clean up exported varyings and add support for querying program count from C/C++
2013-12-17 15:55:59 -05:00
Evghenii
ddfe782151
merged
2013-12-13 11:56:43 +01:00
james.brodman
01432670fd
Fix header file for multi-target output with pointers to varying in exported functions.
2013-12-12 13:27:23 -05:00
james.brodman
d10c0d9545
Add dynamic dispatch support for export functions with pointers to varying data as arguments
2013-12-05 17:47:58 -05:00
james.brodman
a448ccf20c
Merge branch 'master' into nomosoa
2013-12-04 13:52:44 -05:00
Ilia Filippov
8b972f2ed6
Changing error to warning: mismatch in size/layout of global variable
2013-11-26 17:08:06 +04:00
evghenii
bb46b561fd
Merged with upstream/master
2013-11-22 08:13:16 +01:00
Evghenii
1445202e0e
identified bug due to llvm-3.4
2013-11-14 21:18:25 +01:00
Evghenii
f1fc3bdfba
added nvptx declaration to other target & fixed nvptx64 recognition
2013-11-14 20:12:58 +01:00
Evghenii
7aa37b19a9
added some more macros as quick hack...
2013-11-14 20:04:05 +01:00
Evghenii
25df23fed3
workaround for programIndex via preprocessor
2013-11-14 19:48:50 +01:00
Dmitry Babokin
e100040f28
Fix bug with fail when --target=avx1.1-i32x8,avx2-i32x8 - avx11 is not a valid target anymore, need more complete string
2013-11-14 15:37:11 +04:00
Evghenii
fd17ad236a
export functions are now also generated... next add proper CDP calls..
2013-11-12 14:05:12 +01:00
Evghenii
dbb96c1885
need to fix launch code
2013-11-12 13:41:03 +01:00
Evghenii
4cd7e10ad3
reversed to original changes. Here is the plan to use CDP and genarate only device code with host wrapper..
2013-11-12 12:51:56 +01:00
Evghenii
2cef101022
now emits host object file with ptx in it... next step .. testing
2013-10-31 18:05:04 +01:00
Evghenii
8db3d25844
moved PtxString to Globals
2013-10-30 21:05:22 +01:00
Evghenii
f9ec1a0097
.. work in programm to embed PTX into host code ..
2013-10-30 16:47:30 +01:00
Evghenii
f15cdc03e3
nvptx64 generates 2 targets: task and normal function for nvptx64 and export for avx only
2013-10-29 14:46:51 +01:00
Evghenii
b31fc6f66d
now can generate both targets for npvtx64. m_isPTX is set true, to distuish when to either skip or exlcusive euse export
2013-10-29 14:17:11 +01:00
Evghenii
ac700d4860
checkpoint
2013-10-29 13:36:31 +01:00
Evghenii
b2baa35c3d
added correct datalayout for nvptx64
2013-10-29 11:34:01 +01:00
Evghenii
57aefdf830
accepts ptx extension when target is nvptx64
2013-10-29 10:21:48 +01:00
Evghenii
68ced6ce46
automatically adds -D__NVPTX__ when nvptx64 target is chosen
2013-10-28 14:08:32 +01:00
Evghenii
1bd5360d3b
added now NVPTX64 automatically emits unmasked extern "C" for task function with kernel attributes
2013-10-28 13:58:01 +01:00
Evghenii
a7aa1ac1cf
now nvptx allows extern "C" task void, which is emits a kernel that should (?) be callable by driver API from external code
2013-10-28 12:57:09 +01:00
james.brodman
44912e6b1e
Fix segfault when using both -g and -MMM
2013-10-08 18:27:03 -04:00
james.brodman
9f7a4aa867
Update to include latest changes.
...
Merge branch 'master' into nomosoa
2013-09-25 19:17:56 -04:00
james.brodman
090dec8549
Output regular header for multiple targets + fix exported varying types.
2013-08-22 13:23:22 -04:00
JCB
0452b77169
Generate multiple headers for multiple targets.
2013-08-20 15:25:53 -04:00
JCB
10b8c481f5
initial support for exported varying
2013-08-20 15:14:15 -04:00
Matt Pharr
1276ea9844
Revert "Remove support for building with LLVM 3.1"
...
This reverts commit d3c567503b
2013-08-06 17:00:35 -07:00
Matt Pharr
d3c567503b
Remove support for building with LLVM 3.1
2013-07-31 06:46:45 -07:00
Matt Pharr
ab3b633733
Add 8-bit and 16-bit specialized NEON targets.
...
Like SSE4-8 and SSE4-16, these use 8-bit and 16-bit values for mask
elements, respectively, and thus should generate the best code when used
for computation with datatypes of those sizes.
2013-07-30 08:44:16 -07:00
