|
1 | 1 | Current development version (1.0-SNAPSHOT) |
2 | 2 |
|
3 | | -- Fixed handling of image2d_t and image3d_t in Maven plugin (contrib. from Remi Emonet, request #308 and issue #307) |
4 | | -- Fixed OpenGL interop on Windows (issue #312) |
5 | | -- Added CLEvent.FIRE_AND_FORGET to avoid returning events from all the methods that accept a vararg eventsToWaitFor. |
6 | | -- Optimized low-level bindings on OpenCL 1.1+ platforms, with dynamic runtime switch (removed synchronized keyword from all native calls) |
7 | | -- Optimized performance of many calls (CLKernel.setArgs/enqueueNDRange, CLBuffer.read/write...) |
8 | | - |
9 | | -- Update ATI download link |
10 | | -- Ignore mismatching byte order for byte buffers, and replaced mentions to getKernelsDefaultByteOrder() by ge (issue #336) |
11 | | -- Run tests on all detected devices, rather than just on the best one |
12 | | -- List devices in program errors |
13 | | -- Better CLDevice.toString (include platform name) |
14 | | -- Disabled byte order hack |
| 3 | +... |
| 4 | + |
| 5 | +Version 1.0.0-RC3 (20130107) |
| 6 | + |
15 | 7 | - Fixed nasty regression in getBestDevice ! |
16 | 8 | - Fixed ati byte order hack |
17 | 9 | - Fixed byte order hack for ATI platforms |
18 | | -- Started deprecating CLKernel.enqueueNDRange with int[] parameters |
| 10 | +- Fixes / optimized event callbacks (but broke API: CLEvent.EventCallback now only takes the completion status as argument, not the event anymore) |
| 11 | +- Fixed library probe |
| 12 | +- Fixed handling of image2d_t and image3d_t in Maven plugin (contrib. from Remi Emonet, request #308 and issue #307) |
| 13 | +- Fixed OpenGL interop on Windows (issue #312) |
| 14 | +- Fixed error about mismatching byte order for byte buffers, and replaced mentions to getKernelsDefaultByteOrder() by getByteOrder() (issue #336) |
| 15 | +- Fixed AMD App 2.7 Linux library loading code for |
| 16 | +- Fixed AMD download link in demos. |
| 17 | +- Added CLEvent.FIRE_AND_FORGET to avoid returning events from all the methods that accept a vararg eventsToWaitFor. |
| 18 | +- Added naive OSGi support to the main JAR. |
| 19 | +- Added list of devices in program errors. |
19 | 20 | - Added CLBuffer.allocateCompatibleMemory(CLDevice) |
20 | 21 | - Added client properties to CLContext (lazy + concurrent) |
21 | | -- Fixes / optimized event callbacks (but broke API: CLEvent.EventCallback now only takes the completion status as argument, not the event anymore) |
22 | | -- Un-deprecated + fixed CLContext.getKernelsDefaultByteOrder() ; |
| 22 | +- Optimized low-level bindings on OpenCL 1.1+ platforms, with dynamic runtime switch (removed synchronized keyword from all native calls), and made OpenCL 1.0 synchronization a warning. |
| 23 | +- Enhanced CLDevice.toString (include platform name) |
| 24 | +- Deprecated CLKernel.enqueueNDRange with int[] parameters |
23 | 25 | - Return CLUserEvent from CLContext.createUserEvent(); |
24 | | -- Make OpenCL 1.0 synchronization a warning |
25 | | -- Adapted Linux library loading code to AMD App 2.7 |
26 | | -- Fixed library probe |
27 | | -- Factorized some javadoc with macros |
28 | | -- Finish renaming |
29 | | -- Renamed getEntityPeer() to getEntity() |
30 | 26 |
|
31 | 27 | Version 1.0.0-RC2 (20120415, commit 6bc061dfce06b941086a29f696195e82fbaffbdc) |
32 | 28 |
|
|
0 commit comments