 Cyril Roelandt
|
2787e1fa46
Added an SSE codelet to the vector scaling example.
|
14 år sedan |
 Ludovic Courtès
|
886913ffe3
gcc: Support interleaved declarations & definitions of task implementations.
|
14 år sedan |
|
Ludovic Courtès
|
68b2f37506
gcc: Simplify `task' attribute handling.
|
14 år sedan |
 Samuel Thibault
|
ed747c4790
typo
|
14 år sedan |
|
Samuel Thibault
|
77007ead6a
revert r4190, it's completely bogus, we need to add -L for the AC_HAVE_LIBRARY. AC_HAVE_LIBRARY actually does not add -lcudart to LDFLAGS because it has a non-empty action. Let's thus add CUDA_LDFLAGS before the cublas test
|
14 år sedan |
|
Samuel Thibault
|
89f3df6586
keep -lcudart when checking for libcublas. This is needed for linking when that library path is not in LD_LIBRARY_PATH
|
14 år sedan |
 Olivier Aumage
|
6c4d62d0b0
- code disabled for years
|
14 år sedan |
|
Olivier Aumage
|
4a747573b4
- add missing ifdefs
|
14 år sedan |
|
Samuel Thibault
|
3d15b9bbb1
drop debugging
|
14 år sedan |
 Nathalie Furmento
|
fd06148167
configure.ac: remove trailing whitespaces
|
14 år sedan |
|
Nathalie Furmento
|
6db2c372ca
merge branch gpumem_prefetch
|
14 år sedan |
|
Samuel Thibault
|
61eda0dcef
Fix asynchronicity of the wt mechanism by keeping a read reference on the data
|
14 år sedan |
|
Samuel Thibault
|
4a0ed0dc25
Fix asynchronous prefetch: we also need to notify data dependencies in that case. Allocate the wrapper structure dynamically to permit asynchronous termination. Permit prefetch in callbacks and codelets
|
14 år sedan |
|
Samuel Thibault
|
b9f24287b1
Fix replicate reference counting
|
14 år sedan |
|
Samuel Thibault
|
d7c53078b1
avoid crashing on no model name
|
14 år sedan |
|
Olivier Aumage
|
1c6a3ad8b0
- fix initialization
|
14 år sedan |
|
Samuel Thibault
|
6f253ca156
do not make _starpu_prefetch_data_on_node_with_mode wait for the request when async is true
|
14 år sedan |
|
Samuel Thibault
|
73123b92d6
Count the number of workers in memory nodes, to avoid scheduling transfers from memory nodes without a worker (e.g. 0 cpus). Fixes at least the wt mask when no CPU is enabled.
|
14 år sedan |
|
Samuel Thibault
|
5c4a4e9c84
Add gdb functions to print data requests
|
14 år sedan |
|
Samuel Thibault
|
73ac11ecf8
provide file and line of errors
|
14 år sedan |
|
Samuel Thibault
|
0e3edeee5c
provide file and line of errors
|
14 år sedan |
|
Samuel Thibault
|
96c23945a0
revert 4155, there is another exp_end actually...
|
14 år sedan |
|
Samuel Thibault
|
6847e9ac82
exp_end is not actually the expected end, only estimations with the new task
|
14 år sedan |
|
Olivier Aumage
|
66e35b6222
- add support for complex number cases in the LU example
|
14 år sedan |
|
Cyril Roelandt
|
d7f7328c29
src/sched_policies/detect_combined_workers.c: replacing find_combinations_without_hwloc by find_and_assign_combinations_without_hwloc.
|
14 år sedan |
 Nicolas Collin
|
0e82138ef3
Fixed the functions used for combining cpus in several combined workers, using hwloc data.
|
14 år sedan |
|
Nathalie Furmento
|
f641bbcf02
mp/examples/cholesky: code cleaning
|
14 år sedan |
|
Cyril Roelandt
|
2b60aedf3b
Replacing _starpu_topology_get_nhwcpu(config) by config->topology.ncpus
|
14 år sedan |
|
Cyril Roelandt
|
b29709b352
src/core/perfmodel/perfmodel_bus.c:replacing cudaGetDeviceCount by _starpu_get_cuda_device_count
|
14 år sedan |
|
Nathalie Furmento
|
ce10465a8c
gcc-plugin/examples/Makefile.am: only enable cholesky example if a blas library is enabled
|
14 år sedan |
