Merge pull request #29 from CNugteren/development

Update to version 0.5.0

.gitignore

@@ -1,3 +1,4 @@
 build
 stash
-.*
+.*
+*.pyc

.travis.yml

@@ -21,5 +21,9 @@ before_script:
 script:
   - make
   - make install
+branches:
+  only:
+    - master
+    - development
 notifications:
   email: false

CHANGELOG

@@ -1,4 +1,24 @@
 
+Version 0.5.0
+- Improved structure and performance of level-2 routines (xSYMV/xHEMV)
+- Reduced compilation time of level-3 OpenCL kernels
+- Added level-1 routines:
+  * SSWAP/DSWAP/CSWAP/ZSWAP
+  * SSCAL/DSCAL/CSCAL/ZSCAL
+  * SCOPY/DCOPY/CCOPY/ZCOPY
+  * SDOT/DDOT
+  * CDOTU/ZDOTU
+  * CDOTC/ZDOTC
+- Added level-2 routines:
+  * SGBMV/DGBMV/CGBMV/ZGBMV
+  * CHBMV/ZHBMV
+  * CHPMV/ZHPMV
+  * SSBMV/DSBMV
+  * SSPMV/DSPMV
+  * STRMV/DTRMV/CTRMV/ZTRMV
+  * STBMV/DTBMV/CTBMV/ZTBMV
+  * STPMV/DTPMV/CTPMV/ZTPMV
+
 Version 0.4.0
 - Now using the Claduc C++11 interface to OpenCL
 - Added plain C API for increased compatibility (clblast_c.h)

CMakeLists.txt

@@ -13,7 +13,7 @@
 cmake_minimum_required(VERSION 2.8.10)
 project("clblast" C CXX)
 set(clblast_VERSION_MAJOR 0)
-set(clblast_VERSION_MINOR 4)
+set(clblast_VERSION_MINOR 5)
 set(clblast_VERSION_PATCH 0)
 
 # Options and their default values
@@ -102,11 +102,11 @@ include_directories(${clblast_SOURCE_DIR}/include ${OPENCL_INCLUDE_DIRS})
 # ==================================================================================================
 
 # Sets the supported routines and the used kernels. New routines and kernels should be added here.
-set(KERNELS copy pad transpose padtranspose xaxpy xgemv xgemm)
+set(KERNELS copy pad transpose padtranspose xaxpy xdot xgemv xgemm)
 set(SAMPLE_PROGRAMS_CPP sgemm)
 set(SAMPLE_PROGRAMS_C sgemm)
-set(LEVEL1_ROUTINES xaxpy)
-set(LEVEL2_ROUTINES xgemv xhemv xsymv)
+set(LEVEL1_ROUTINES xswap xscal xcopy xaxpy xdot xdotu xdotc)
+set(LEVEL2_ROUTINES xgemv xgbmv xhemv xhbmv xhpmv xsymv xsbmv xspmv xtrmv xtbmv xtpmv)
 set(LEVEL3_ROUTINES xgemm xsymm xhemm xsyrk xherk xsyr2k xher2k xtrmm)
 set(ROUTINES ${LEVEL1_ROUTINES} ${LEVEL2_ROUTINES} ${LEVEL3_ROUTINES})
 set(PRECISIONS 32 3232 64 6464)

README.md

@@ -6,7 +6,7 @@ CLBlast: The tuned OpenCL BLAS library
 
 CLBlast is a modern, lightweight, performant and tunable OpenCL BLAS library written in C++11. It is designed to leverage the full performance potential of a wide variety of OpenCL devices from different vendors, including desktop and laptop GPUs, embedded GPUs, and other accelerators. CLBlast implements BLAS routines: basic linear algebra subprograms operating on vectors and matrices.
 
-__Note that the CLBlast library is actively being developed, and is not mature enough for production environments__. This preview-version doesn't support all routines yet: others will be added in due time. It also lacks extensive tuning on some common OpenCL platforms: __out-of-the-box performance on some devices might be poor__. See below for more details.
+__Note that the CLBlast library is actively being developed, and is not mature enough for production environments__. This preview-version doesn't support the less commonly used routines yet: they will be added in due time. It also lacks extensive tuning on some common OpenCL platforms: __out-of-the-box performance on some devices might be poor__. See below for more details.
 
 
 Why CLBlast and not clBLAS or cuBLAS?
@@ -130,22 +130,21 @@ These graphs can be generated automatically on your own device. First, compile C
 Supported routines
 -------------
 
-CLBlast is in active development and currently does not support the full set of BLAS routines. The currently supported routines are marked with '✔' in the following tables:
+CLBlast is in active development but already supports the majority of BLAS routines. The currently supported routines are marked with '✔' in the following tables:
 
 | Level-1  | S | D | C | Z | Notes   |
 | ---------|---|---|---|---|---------|
 | xROTG    |   |   | - | - |         |
 | xROTMG   |   |   | - | - |         |
 | xROT     |   |   | - | - |         |
 | xROTM    |   |   | - | - |         |
-| xSWAP    |   |   |   |   |         |
-| xSCAL    |   |   |   |   | +CS +ZD |
-| xCOPY    |   |   |   |   |         |
+| xSWAP    | ✔ | ✔ | ✔ | ✔ |         |
+| xSCAL    | ✔ | ✔ | ✔ | ✔ | +CS +ZD |
+| xCOPY    | ✔ | ✔ | ✔ | ✔ |         |
 | xAXPY    | ✔ | ✔ | ✔ | ✔ |         |
-| xDOT     |   |   | - | - | +DS     |
-| xDOTU    | - | - |   |   |         |
-| xDOTC    | - | - |   |   |         |
-| xxxDOT   | - | - | - | - | +SDS    |
+| xDOT     | ✔ | ✔ | - | - |         |
+| xDOTU    | - | - | ✔ | ✔ |         |
+| xDOTC    | - | - | ✔ | ✔ |         |
 | xNRM2    |   |   | - | - | +SC +DZ |
 | xASUM    |   |   | - | - | +SC +DZ |
 | IxAMAX   |   |   |   |   |         |
@@ -154,16 +153,16 @@ CLBlast is in active development and currently does not support the full set of
 | Level-2  | S | D | C | Z | Notes   |
 | ---------|---|---|---|---|---------|
 | xGEMV    | ✔ | ✔ | ✔ | ✔ |         |
-| xGBMV    |   |   |   |   |         |
+| xGBMV    | ✔ | ✔ | ✔ | ✔ |         |
 | xHEMV    | - | - | ✔ | ✔ |         |
-| xHBMV    | - | - |   |   |         |
-| xHPMV    | - | - |   |   |         |
+| xHBMV    | - | - | ✔ | ✔ |         |
+| xHPMV    | - | - | ✔ | ✔ |         |
 | xSYMV    | ✔ | ✔ | - | - |         |
-| xSBMV    |   |   | - | - |         |
-| xSPMV    |   |   | - | - |         |
-| xTRMV    |   |   |   |   |         |
-| xTBMV    |   |   |   |   |         |
-| xTPMV    |   |   |   |   |         |
+| xSBMV    | ✔ | ✔ | - | - |         |
+| xSPMV    | ✔ | ✔ | - | - |         |
+| xTRMV    | ✔ | ✔ | ✔ | ✔ |         |
+| xTBMV    | ✔ | ✔ | ✔ | ✔ |         |
+| xTPMV    | ✔ | ✔ | ✔ | ✔ |         |
 | xTRSV    |   |   |   |   |         |
 | xTBSV    |   |   |   |   |         |
 | xTPSV    |   |   |   |   |         |