Commit Graph

  • a448ccf20c Merge branch 'master' into nomosoa james.brodman 2013-12-04 13:52:44 -05:00
  • d5b7c51e40 Merge pull request #676 from dbabokin/alloy_34 jbrodman 2013-12-04 10:39:45 -08:00
  • 2d2d14744b Fixing --opt=force-aligned-memory for LLVM 3.3+ Dmitry Babokin 2013-12-04 19:00:02 +04:00
  • f61f1a2020 Fixing run_tests.py to understand LLVM 3.4 Dmitry Babokin 2013-12-03 19:52:11 +04:00
  • 31ee2951ce Adding LLVM 3.4 definition to alloy.py Dmitry Babokin 2013-12-03 19:40:30 +04:00
  • d46a54348a Merge branch 'master' of https://github.com/ispc/ispc Vsevolod Livinskij 2013-12-02 23:30:44 +04:00
  • 4a53ed1201 Merge pull request #674 from dbabokin/vs2013 jbrodman 2013-12-02 08:49:12 -08:00
  • d2e57cfcac Merge pull request #671 from dbabokin/select jbrodman 2013-12-02 08:43:30 -08:00
  • e172d7f1a9 Update build messages (Windows) Dmitry Babokin 2013-12-01 16:18:06 +04:00
  • 3bc4788acb Fix errors with VS2013 Dmitry Babokin 2013-12-01 03:45:00 +04:00
  • 4faff1a63c structural change Vsevolod Livinskij 2013-11-30 10:48:18 +04:00
  • 4c330bc38b Add code generation of saturation Vsevolod Livinskij 2013-11-29 18:40:04 +04:00
  • 67d1985550 Merge pull request #672 from ifilippov/master Dmitry Babokin 2013-11-29 02:47:55 -08:00
  • b94b89ba68 support of LLVM trunk Ilia Filippov 2013-11-29 14:24:21 +04:00
  • bec6662338 Some cganges for avx1 and avx1.1 in saturation Vsevolod Livinskij 2013-11-29 03:45:25 +04:00
  • 42c148bf75 Changes for sse2 and sse4 in saturation Vsevolod Livinskij 2013-11-29 03:33:40 +04:00
  • d6dfbcd743 Run alloy -j<num cores> by default Dmitry Babokin 2013-11-28 21:44:12 +04:00
  • be813ea0a2 Select optimization for LLVM 3.3 Dmitry Babokin 2013-11-14 15:32:47 +04:00
  • c751e44c6c Merge pull request #670 from dbabokin/sext_patch Dmitry Babokin 2013-11-28 01:56:09 -08:00
  • eaa483d6e4 fail_db update (Linux) Dmitry Babokin 2013-11-28 13:51:20 +04:00
  • 672d43a6cf Adding patch for sse4-i16x8 and sse4-i8x16 targets Dmitry Babokin 2013-11-27 23:22:50 +04:00
  • 9b19f0aaba Merge pull request #669 from dbabokin/fail_db Dmitry Babokin 2013-11-26 15:28:00 -08:00
  • 218d2892e8 fail_db.txt update with LLVM 3.5 (trunk) results on Linux Dmitry Babokin 2013-11-27 03:24:17 +04:00
  • 35a4d1b3a2 Add some AVX2 intrinsics Vsevolod Livinskij 2013-11-27 00:55:57 +04:00
  • f6fa63bdef Merge pull request #668 from ifilippov/tests Dmitry Babokin 2013-11-26 07:15:50 -08:00
  • f3ff1fcbeb supporting targets in perf windows Ilia Filippov 2013-11-25 23:37:42 +04:00
  • 935800d7f6 making common.props Ilia Filippov 2013-11-25 13:31:26 +04:00
  • 726fc93634 Merge pull request #667 from ifilippov/warning Dmitry Babokin 2013-11-26 05:23:43 -08:00
  • 8b972f2ed6 Changing error to warning: mismatch in size/layout of global variable Ilia Filippov 2013-11-26 17:08:06 +04:00
  • ef9e212eec Merge remote-tracking branch 'upstream/master' into nvptx evghenii 2013-11-26 13:24:43 +01:00
  • 18d6986c22 Merge remote-tracking branch 'upstream/master' into sm35 evghenii 2013-11-26 13:24:32 +01:00
  • 19f73b2ede uniform signed/unsigned int8/16 Vsevolod Livinskij 2013-11-25 19:16:02 +04:00
  • b4102a4510 Merge pull request #665 from ifilippov/master Dmitry Babokin 2013-11-22 06:36:22 -08:00
  • e192e8ea9e +change static naming in IR to make it compatible with NVVM Evghenii 2013-11-22 14:43:14 +01:00
  • 18f90e6339 fix of perf.py Ilia Filippov 2013-11-22 17:06:19 +04:00
  • 406aad78fe first support for integration with NVCC/CUDART API Evghenii 2013-11-22 13:06:51 +01:00
  • 280f3515b5 +1 Evghenii 2013-11-22 11:23:34 +01:00
  • 522daa26a6 added PTX generator from NVVM Evghenii 2013-11-22 08:18:59 +01:00
  • bb46b561fd Merged with upstream/master evghenii 2013-11-22 08:13:16 +01:00
  • 828a5d45cd Merge remote-tracking branch 'upstream/master' into nvptx Evghenii 2013-11-22 08:10:08 +01:00
  • 0f7ac1cc90 Merge pull request #664 from ifilippov/3_5 Dmitry Babokin 2013-11-21 07:35:35 -08:00
  • 019ff4709c Merge pull request #663 from ifilippov/perf Dmitry Babokin 2013-11-21 07:11:35 -08:00
  • 3fd9d5a025 support of LLVM 3.5 Ilia Filippov 2013-11-21 19:09:43 +04:00
  • 924858509d checking targets in perf.py Ilia Filippov 2013-11-21 19:05:35 +04:00
  • 6f200d310f fixed to work with LLVM 3.2 Evghenii 2013-11-21 11:03:03 +01:00
  • 321b087039 added drviapierrorstrong Evghenii 2013-11-21 09:22:07 +01:00
  • 357f115f11 Merge pull request #661 from dbabokin/task_diagnostics jbrodman 2013-11-20 09:16:51 -08:00
  • 5531586c35 Fix for existing semaphore problem Dmitry Babokin 2013-11-20 19:19:15 +04:00
  • 40da411fa5 Fix task system dignostic to report real reason of the symaphore allocation fail Dmitry Babokin 2013-11-20 17:22:50 +04:00
  • 676c367db1 Merge pull request #660 from dbabokin/fail_db Dmitry Babokin 2013-11-19 09:20:30 -08:00
  • 5722d17924 fail_db.txt update on Linux with new passes Dmitry Babokin 2013-11-19 21:17:54 +04:00
  • 97298eb112 multiple targets in perf.py Ilia Filippov 2013-11-19 17:37:52 +04:00
  • b4df3663a9 Merge branch 'sm35_foreach' of github.com:egaburov/ispc into sm35_foreach Evghenii 2013-11-19 10:30:24 +01:00
  • 86567ba96f +1 Evghenii 2013-11-19 09:11:20 +01:00
  • 0cf7043f5f added Makefile_knc evghenii 2013-11-18 22:09:40 +01:00
  • 0df23312ac +1 evghenii 2013-11-18 22:00:01 +01:00
  • e8fc32a7dc Merge branch 'sm35_foreach' of github.com:egaburov/ispc into sm35_foreach evghenii 2013-11-18 21:59:09 +01:00
  • e4ee1692fb added KNC Makfile evghenii 2013-11-18 21:58:56 +01:00
  • 4bc8c79bd3 fixed cuda kernel Evghenii 2013-11-18 13:28:12 +01:00
  • 915dc4be7f +1 Evghenii 2013-11-18 13:24:01 +01:00
  • cf2116e167 +1 Evghenii 2013-11-18 13:16:30 +01:00
  • 64762c5acd +1 Evghenii 2013-11-18 13:15:05 +01:00
  • 4f9b8ebc73 +1 Evghenii 2013-11-18 13:11:57 +01:00
  • ee61a265f4 fixed kernel Evghenii 2013-11-18 13:01:36 +01:00
  • db4abfe198 +1 Evghenii 2013-11-18 12:58:30 +01:00
  • 4b7dbbf43b added cuda kernel Evghenii 2013-11-18 12:46:30 +01:00
  • db13639460 change # options Evghenii 2013-11-18 12:42:23 +01:00
  • 1cdb4c21c2 makefile fix evghenii 2013-11-18 12:25:36 +01:00
  • 008d9371b1 added Makefile for KNC evghenii 2013-11-18 12:19:45 +01:00
  • 6640dd0a6c added Makefile for KNC evghenii 2013-11-18 12:19:33 +01:00
  • 589538bf39 added stencil code Evghenii 2013-11-18 12:04:00 +01:00
  • 8d4dd13750 changes Evghenii 2013-11-18 11:58:19 +01:00
  • 754a3208f2 Merge pull request #659 from ifilippov/master Dmitry Babokin 2013-11-18 02:46:15 -08:00
  • 4d278a654e +1 Evghenii 2013-11-18 10:58:24 +01:00
  • 9eaec6d58a changed avx->avx-x2 Evghenii 2013-11-18 10:56:22 +01:00
  • 616cd3316c +1 Evghenii 2013-11-18 10:54:29 +01:00
  • 4579d339ea patch for LLVM 3.3 and test correction at avx2 Ilia Filippov 2013-11-18 13:44:59 +04:00
  • 36f584d341 +1 Evghenii 2013-11-18 10:51:54 +01:00
  • 6387bbf193 Merge branch 'sm35_foreach' of github.com:egaburov/ispc into sm35_foreach Evghenii 2013-11-18 10:45:02 +01:00
  • de177e7529 +using kernels1 in deferred Evghenii 2013-11-18 10:44:52 +01:00
  • f17fdfdbef added KNC makefile evghenii 2013-11-18 10:41:52 +01:00
  • 45d6bf196a change timings to ms Evghenii 2013-11-18 10:37:17 +01:00
  • 5e2fff91f8 +1 evghenii 2013-11-18 10:33:04 +01:00
  • e13f8dd359 +1 evghenii 2013-11-18 10:30:18 +01:00
  • 0897f3c1c4 Merge branch 'sm35_foreach' of github.com:egaburov/ispc into sm35_foreach Evghenii 2013-11-18 10:17:02 +01:00
  • a82368956e added ms timer Evghenii 2013-11-18 10:16:24 +01:00
  • 6841d8ba9a added Makefile_mic evghenii 2013-11-18 09:59:41 +01:00
  • 927da8e861 change register allocation, makes code much faster Evghenii 2013-11-18 09:46:51 +01:00
  • 3c220a2813 loop unrolling, maks code 10x faster Evghenii 2013-11-18 09:37:25 +01:00
  • 5a01819fdc unrolled loops in binomial options cuda version Evghenii 2013-11-18 09:16:09 +01:00
  • 4977933d81 Merge pull request #658 from dbabokin/fail_db Dmitry Babokin 2013-11-17 15:42:51 -08:00
  • 953e467a85 fail_db.txt update on Linux Dmitry Babokin 2013-11-18 03:39:09 +04:00
  • 131ab07c2b Merge pull request #657 from dbabokin/avx-i32x4 jbrodman 2013-11-15 16:00:57 -08:00
  • 1d94667a15 +speed-up binomial options via use of shared memory Evghenii 2013-11-15 20:46:55 +01:00
  • 4421fb7e19 +1 Evghenii 2013-11-15 20:21:31 +01:00
  • 131ff50333 Adding avx1-i32x4 to alloy.py testing Dmitry Babokin 2013-11-15 22:09:13 +04:00
  • bc8b5b3896 added cuda versino Evghenii 2013-11-15 18:09:03 +01:00
  • a2d12517e7 +options Evghenii 2013-11-15 17:59:04 +01:00
  • 95d6647dce +1 Evghenii 2013-11-15 17:32:59 +01:00
  • 3454f51d2c added some ptx options Evghenii 2013-11-15 17:23:22 +01:00