This website requires JavaScript.
a5782dfb2d
Merge pull request #586 from dbabokin/double
2013-09-19 01:51:13 -07:00
1c527ae34c
Adding tests and vim support for double constant of the form .1d41
2013-09-18 11:48:24 +04:00
f45f6cb32a
Test, documentation and vim support for double precision constants
2013-09-17 23:36:16 +04:00
00cd90c6b0
test system
2013-09-17 17:30:34 +04:00
406e2eb8d0
fix double precision input to support .123d321 type of input
2013-09-19 09:16:37 +02:00
3cf63362a4
small tuning
2013-09-18 20:03:08 +03:00
e4b1f58595
performance fix.. still some issues left with equal_i1 for __vec8_i1
2013-09-18 19:14:41 +03:00
4b1a0b4bc4
added fails
2013-09-18 18:41:22 +03:00
922edb1128
completed knc-i1x16.h and added knc-i1x8.h with knc-i1x8unsafe_fast.h that doesnt pass several tests..
2013-09-18 18:14:07 +03:00
0672289cb9
Merge branch 'double' of https://github.com/dbabokin/ispc
2013-09-18 15:24:35 +02:00
ff547fc6cb
Merge pull request #584 from egaburov/d-suffix
2013-09-17 12:46:59 -07:00
fa78d548cc
Test, documentation and vim support for double precision constants
2013-09-17 23:36:16 +04:00
191d9dede5
Merge pull request #585 from tkoziara/master
2013-09-16 10:08:49 -07:00
6e0b9ddc74
Sort description.
2013-09-16 18:02:07 +01:00
eef4e11768
now it is also case nonsensitive
2013-09-16 17:25:13 +02:00
6fd21d988d
fixed lexer to properly read fortran-notation double constants
2013-09-16 17:15:02 +02:00
2332490481
added fortran_double_constant
2013-09-16 16:31:41 +02:00
e2a91e6de5
added support for "d"-suffix
2013-09-16 15:54:32 +02:00
b258027061
Merge pull request #582 from tkoziara/master
2013-09-16 03:29:43 -07:00
97068765e8
Copyright reversed.
2013-09-14 18:09:04 +01:00
ec5cbb8117
Merge pull request #583 from dbabokin/win-fix
2013-09-13 15:02:09 -07:00
ce99b17616
Fix for Windows buils to include new target: avx-i64x4
2013-09-14 02:00:23 +04:00
06aa2067d9
Merge pull request #578 from egaburov/master
2013-09-13 09:40:24 -07:00
36886971e3
revert lex.ll parse.yy stdlib.ispc to state when all constants are floats
2013-09-13 16:02:53 +02:00
9861375f0c
renamed avx-i64x4 -> avx1-i64x4
2013-09-13 15:07:14 +02:00
ed825b3773
Uniform memory allocation fixed.
2013-09-13 13:14:31 +01:00
a9913c8337
changed lexer/parser to be able to read float constants, if they have "f"-suffix
2013-09-13 10:26:15 +02:00
a97eb7b7cb
added clamp in double precision
2013-09-13 09:32:59 +02:00
715b828266
fixed float constants to be read as doubles
2013-09-13 09:25:52 +02:00
40af8d6ed5
fixed segfault in tests/launch-*.ispc. nativeVectoWidth in avx-i64x4 was set to 4. Fixed
2013-09-12 20:25:44 +02:00
059d80cc11
included suggested changes, ./tests/launch-*.ispc still fails. something is mask64 related, not sure what. help...
2013-09-12 17:18:12 +02:00
7364e06387
added mask64
2013-09-12 12:02:42 +02:00
efc20c2110
added svml support to all sse/avx modes
2013-09-11 17:07:54 +02:00
19379db3b6
svml cleanup
2013-09-11 16:48:56 +02:00
9cf8e8cbf3
builtins fix for double precision svml and __stdlib_asin
2013-09-11 15:23:45 +02:00
7a32699573
added svml.m4
2013-09-11 15:18:03 +02:00
320c41ffcf
added svml support. experimental. for some reason all sybmols are visible..
2013-09-11 15:16:50 +02:00
9c79d4d182
addded avxh with vectorWidth=4 support, use --target=avxh to enable it
2013-09-11 12:58:02 +02:00
582cfe55b6
Merge pull request #575 from jbrodman/master
2013-09-05 10:31:23 -07:00
8db378b265
Revert "Remove support for using SVML for math lib routines."
2013-09-04 16:01:58 -04:00
71a7564317
Merge pull request #574 from jbrodman/uniftypedef
2013-09-03 13:14:00 -07:00
c14b035a46
Merge pull request #572 from ifilippov/master
2013-08-30 11:17:01 -07:00
cf2eaa0014
Merge pull request #569 from dbabokin/unmasked
2013-08-30 11:16:42 -07:00
cb92d54808
Merge pull request #570 from dbabokin/docs
2013-08-30 11:16:26 -07:00
97d430d5cd
Fix to respect uniform/varying qualifiers inside of typedefs.
2013-08-30 14:13:08 -04:00
320b1700ff
correction of adding -Werror option
2013-08-30 16:01:01 +04:00
e06267ef1b
Fix for incorrect implementation of reduce_[min|max]_[float|double], it showed up as -O0
2013-08-29 16:16:02 +04:00
501a23ad20
Typos fixes in docs
2013-08-29 14:48:09 +04:00
c1cc80b1d5
Merge pull request #568 from jbrodman/master
2013-08-27 14:08:12 -07:00
28080b0c22
Fix build against 3.4
2013-08-27 16:56:00 -04:00
be3a40e70b
Fix for 3.4
2013-08-27 15:15:16 -04:00
5d8ebf3ca1
Fixing r183327-AVX2-GATHER.patch file permissions
2013-08-27 18:27:06 +04:00
443987f536
fixing ispc.rst file properties (should not be executable)
2013-08-27 15:33:44 +04:00
f6ce969d9f
Merge pull request #567 from ifilippov/master
2013-08-26 03:26:28 -07:00
f620cdbaa1
Changes in perf.py functionality, unification of examples, correction build warnings
2013-08-26 14:04:59 +04:00
090dec8549
Output regular header for multiple targets + fix exported varying types.
2013-08-22 13:23:22 -04:00
3f2217646e
Merge pull request #562 from mmp/arm
2013-08-22 08:33:25 -07:00
611477e214
Revert change to lEmitVaryingSelect().
2013-08-22 07:50:25 -07:00
9bb5c314cd
Merge pull request #565 from dbabokin/run_tests
2013-08-22 01:48:22 -07:00
f31a31478b
Moving time calculation earlier
2013-08-22 12:41:57 +04:00
5fb30939be
Fix for #564 , using wrong ispc in run_tests.py
2013-08-21 19:46:18 +04:00
60b413a9cb
Adding --non-interactive switch to run_tests.py
2013-08-21 19:25:30 +04:00
3e9d784013
Support exported arrays of varyings
2013-08-20 16:14:29 -04:00
0452b77169
Generate multiple headers for multiple targets.
2013-08-20 15:25:53 -04:00
10b8c481f5
initial support for exported varying
2013-08-20 15:14:15 -04:00
502f8fd76b
Reduce debug spew on failing idiv.ispc tests
2013-08-20 09:22:09 -07:00
2b2905b567
Fix (preexisting) bugs in generic-32/64.h with type of "__any", etc.
2013-08-20 09:05:50 -07:00
e7f067d70c
Fix handling of __clock() builtin for "generic" targets.
2013-08-20 09:04:52 -07:00
d976da7559
Speed up idiv test (dont test int32 as thoroughly)
2013-08-20 08:49:51 -07:00
84dbd66d10
Merge pull request #563 from jbrodman/debugopt
2013-08-15 13:10:13 -07:00
6be3c24ee5
Separate -O and -g
2013-08-15 15:24:46 -04:00
42f31aed69
Another attempt at fixing the Windows build (added sse4-8/sse4-16 targets).
2013-08-14 11:02:45 -07:00
ed017c42f1
Fix ispc.vcxproj for Windows builds
2013-08-11 07:47:20 -07:00
4766467271
Revert ispc.vcxproj to version from top-of-tree.
2013-08-10 11:23:39 -07:00
ea8591a85a
Fix build with LLVM top-of-tree (link libcurses)
2013-08-10 11:22:43 -07:00
7ab4c5391c
Fix build with LLVM 3.2 and generic-4 / examples/sse4.h target.
2013-08-09 19:56:43 -07:00
0c5742b6f8
Implement new naming scheme for --target.
2013-08-08 19:23:44 -07:00
1d76f74b16
Fix compiler warnings
2013-08-07 12:53:39 -07:00
5e5d42b918
Fix build with LLVM 3.1
2013-08-06 17:55:37 -07:00
cd9afe946c
Merge branch 'master' into arm
2013-08-06 17:09:48 -07:00
1276ea9844
Revert "Remove support for building with LLVM 3.1"
2013-08-06 17:00:35 -07:00
0755e4f8ff
Merge pull request #561 from dbabokin/neon_condition
2013-08-06 13:45:30 -07:00
ccdbddd388
Add peephole optimization to match int8/int16 averages.
2013-08-06 08:59:46 -07:00
5b20b06bd9
Add avg_{up,down}_int{8,16} routines to stdlib
2013-08-03 20:44:25 -07:00
dff7735af9
Fix for Windows build and making NEON target optional
2013-08-02 19:24:34 -07:00
fb34fc5a85
Merge pull request #559 from ifilippov/debug_phases
2013-08-01 14:55:07 -07:00
43423c276f
Merge pull request #560 from ifilippov/perf
2013-08-01 13:20:01 -07:00
5ffc3a8f4c
Merge pull request #558 from dbabokin/win_examples
2013-08-01 08:02:42 -07:00
3c06924a02
Supporting perf.py on Mac OS
2013-08-01 12:47:37 +04:00
a174a90f86
Supporting dumping, switching off and debug printing of optimization phases
2013-08-01 11:37:52 +04:00
4f48d3258a
Documentation updates for NEON
2013-07-31 20:06:04 -07:00
d9c38b5c1f
Remove support for using SVML for math lib routines.
2013-07-18 09:24:23 -07:00
d3c567503b
Remove support for building with LLVM 3.1
2013-07-31 06:46:45 -07:00
d7562d3836
Merge branch 'master' into arm
2013-07-31 06:38:17 -07:00
220f0b0b40
Renaming mandelbrot_tasks files to be different from mandelbrot
2013-07-30 19:53:12 -07:00
48ff03112f
Remove __pause from stdlib_core() in utils.m4.
2013-07-29 16:20:46 -07:00
ab3b633733
Add 8-bit and 16-bit specialized NEON targets.
2013-07-29 16:14:58 -07:00
fa93cb7d0b
InterlockedAdd -> InterlockedExchangeAdd for better portability (InterlockedAdd is not always supported)
2013-07-29 22:46:36 -07:00
153fbc3d7d
some changes
2013-07-29 11:05:05 +02:00
307abc8db7
adding text folder to test ptx generator
2013-07-28 15:57:10 +02:00
Dmitry Babokin
Ilia Filippov
egaburov
evghenii
Tomasz Koziara
jbrodman
james.brodman
Matt Pharr