- 15 Oct, 2017 2 commits
-
-
Tianqi Chen committed
-
* [CODEGEN] Force not inline compute core for better debug * also support llvm4
Tianqi Chen committed
-
- 14 Oct, 2017 3 commits
-
-
* [TVM] Introduce target generic dispatch system * fix target warning
Tianqi Chen committed -
masahi committed
-
* [CODEGEN] Detect broadcast(cast(x)) pattern in FMA * [CODEGEN] Improve * [CODEGEN] Fix
ziheng committed
-
- 13 Oct, 2017 6 commits
-
-
* Add same_as to NodeBase 1. Most class inherited from NodeBase(Schedule, Stage, etc) still have the convenience of using '==' for object identity. And this is the right behavior for non-Expr classes. 2. subclasses of ExprOp now create EQ expression when '==' is used. `__nonzero__` and `__bool__` in EQ and NE is a comprise that in some cases object identity semantics is still useful, like in unit test. For instance: ```` assert a == b ```` "a == b" will create EQ expression, assert then calls `__nonzero__` of the result expression. `Expr.__nonzero__` throws exception since it prohibits evaluating IR expression. More complex case like: ```` assert a in b # b is dict ```` it will call `__eq__` on a and all keys of b, then `__bool__` on the result expression. This could not easily be done by same_as. * Retain __hash__ from NodeBase in Python3
Wei Chen committed -
* added support for rocm gpu autodetect * changed type casting from old style to static_cast * fixed code to generate gfx specific code object * fixed namespaces
Aditya Atluri committed -
Hu Shiwen committed
-
* add masahi to contributors * enable rocm target in topi tests
masahi committed -
Tianqi Chen committed
-
ziheng committed
-
- 12 Oct, 2017 4 commits
-
-
Tianqi Chen committed
-
also improve comment and unit test
陳煒 committed -
masahi committed
-
* [RUNTIME] Enable ext_dev type for quick plugin of device * [TEST] Update testcase to cover all computation
Tianqi Chen committed
-
- 11 Oct, 2017 3 commits
-
-
* [PASS] copy intrin * update comment thanks to derisavi
Tianqi Chen committed -
Vsevolod Rodionov committed
-
* Case-sensitive CMake module for OpenCL Case-sensitive CMake module for OpenCL, see https://github.com/Kitware/CMake/blob/master/Modules/FindOpenCL.cmake . * fix in case Metal locates OpenCL as well fix in case Metal locates OpenCL as well
Liangfu Chen committed
-
- 10 Oct, 2017 1 commit
-
-
* [ARITH] Improve detect linear equation * fix doc
Tianqi Chen committed
-
- 09 Oct, 2017 1 commit
-
-
Daniel M. Weeks committed
-
- 08 Oct, 2017 3 commits
-
-
Tianqi Chen committed
-
Tianqi Chen committed
-
Tianqi Chen committed
-
- 06 Oct, 2017 3 commits
-
-
* add argmax argmin * remove coder saver
Xingjian Shi committed -
* conv2d tweaked for better end-to-end performance * syntax changed
Leyuan Wang committed -
* conv2d layout change bug fixed * remove debug msg * misaligned error fixed
Leyuan Wang committed
-
- 05 Oct, 2017 3 commits
-
-
Tianqi Chen committed
-
Leyuan Wang committed
-
Tianqi Chen committed
-
- 04 Oct, 2017 1 commit
-
-
Tianqi Chen committed
-
- 03 Oct, 2017 1 commit
-
-
* [TOPI] Add left_shift, right_shift, clip, cast * [TOPI] Add test * [TOPI] Fix
ziheng committed
-
- 01 Oct, 2017 1 commit
-
-
* [LANG] Support for Bitwise Operation * Add test
ziheng committed
-
- 30 Sep, 2017 2 commits
-
-
Tianqi Chen committed
-
ziheng committed
-
- 29 Sep, 2017 1 commit
-
-
* [DOCS] How to deploy TVM Modules * More comments
Tianqi Chen committed
-
- 28 Sep, 2017 2 commits
-
-
Xingjian Shi committed
-
ziheng committed
-
- 27 Sep, 2017 1 commit
-
-
* [TOP] Initial Schedule of MobileNet on Rasp * Fix * Fix
ziheng committed
-
- 26 Sep, 2017 2 commits
-
-
* Move target to tvm; rename convolution as conv2d * Fix * Fix
ziheng committed -
* add squeeze * should be squeeze
Xingjian Shi committed
-