diff options
| author | Zhigang Gong <zhigang.gong@linux.intel.com> | 2013-10-22 15:06:32 +0800 |
|---|---|---|
| committer | Zhigang Gong <zhigang.gong@linux.intel.com> | 2013-10-22 15:06:32 +0800 |
| commit | 2bc1af2c9ea2b48dd55699bb99b99350d0fc0762 (patch) | |
| tree | e853093d23352af823c89e4a31919701ed8a7913 | |
| parent | 8a97d70d650dd60d3643e6f73307c23a8505b0ff (diff) | |
Bump to version 0.3.
Also update some documents accordingly.
Signed-off-by: Zhigang Gong <zhigang.gong@linux.intel.com>
| -rw-r--r-- | CMakeLists.txt | 2 | ||||
| -rw-r--r-- | docs/Beignet.mdwn | 5 | ||||
| -rw-r--r-- | docs/Beignet/Backend/TODO.mdwn | 9 |
3 files changed, 2 insertions, 14 deletions
diff --git a/CMakeLists.txt b/CMakeLists.txt index 3d18f500..2ec6c089 100644 --- a/CMakeLists.txt +++ b/CMakeLists.txt @@ -9,7 +9,7 @@ CMAKE_MINIMUM_REQUIRED(VERSION 2.6.0) PROJECT(OCL) set (LIBCL_DRIVER_VERSION_MAJOR 0) -set (LIBCL_DRIVER_VERSION_MINOR 2) +set (LIBCL_DRIVER_VERSION_MINOR 3) set (LIBCL_C_VERSION_MAJOR 1) set (LIBCL_C_VERSION_MINOR 1) diff --git a/docs/Beignet.mdwn b/docs/Beignet.mdwn index 86a235ea..97b568bf 100644 --- a/docs/Beignet.mdwn +++ b/docs/Beignet.mdwn @@ -101,14 +101,9 @@ do: as clCreateFromGLBuffer,clCreateFromGLRenderbuffer,clGetGLObjectInfo... Currently, the working APIs are clCreateFromGLTexture,clCreateFromGLTexture2D. -- Support for events. - - Check that NDRangeKernels can be pushed into _different_ queues from several threads. -- Support for nonblocking mode Enqueue\*Buffer. Now we only use the map extension to - implement those Enqueue\*Buffer functions. - - No state tracking at all. One batch buffer is created at each "draw call" (i.e. for each NDRangeKernels). This is really inefficient since some expensive pipe controls are issued for each batch buffer diff --git a/docs/Beignet/Backend/TODO.mdwn b/docs/Beignet/Backend/TODO.mdwn index f14433de..adc7fd28 100644 --- a/docs/Beignet/Backend/TODO.mdwn +++ b/docs/Beignet/Backend/TODO.mdwn @@ -31,8 +31,6 @@ many things must be implemented: - From LLVM 3.3, we use SPIR IR. We need to use the compiler defined type to represent sampler_t/image2d_t/image1d_t/.... -- Adding support for long (int64). - Gen IR ------ @@ -56,17 +54,12 @@ The code is defined in `src/ir`. Main things to do are: This will obviously impact both instruction selection and the register allocation. -- Adding support for long (int64). - Backend ------- The code is defined in `src/backend`. Main things to do are: -- Int64 support? - -- Implementing register spilling (see the [[compiler backend - description|compiler_backend]] for more details) +- Optimize register spilling (see the [[compiler backend description|compiler_backend]] for more details) - Implementing proper instruction selection. A "simple" tree matching algorithm should provide good results for Gen |