| Commit message (Collapse) | Author | Age | Files | Lines |
|
|
|
|
|
|
| |
Reviewed-by: Tom Stellard <[email protected]>
CC: "10.0" <[email protected]>
(cherry picked from commit 862f55c29c50798942e58ea75c5294921c0489f8)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The spec allows clGetProgramInfo() to return information about either
the devices associated with the program or the devices associated
with the context. If there are no devices associated with the program,
then we return devices associated with the context.
https://bugs.freedesktop.org/show_bug.cgi?id=52171
Reviewed-by: Francisco Jerez <[email protected]>
CC: "10.0" <[email protected]>
(cherry picked from commit a84dd2398f75c672293122408828ac66bb7052a0)
|
|
|
|
|
|
|
|
|
|
| |
v2:
- Use clGetDeviceIDs to query devices.
Reviewed-by: Francisco Jerez <[email protected]>
CC: "10.0" <[email protected]>
(cherry picked from commit 17af4dd52b0530b671fb7ae64345500f62ed7ee3)
|
|
|
|
|
|
|
|
|
|
|
|
| |
range sizes.
Fixes infinite loop in find_grid_optimal_factor() in cases where the
user specifies a grid size with less dimensions than the device
supports.
Reported-by: Tom Stellard <[email protected]>
Cc: "10.0" <[email protected]>
(cherry picked from commit 99d447cc5dafa3a36b970068961989cced62e3b6)
|
|
|
|
|
|
|
|
| |
Inspired by a patch sent to the mailing list by Tom Stellard, but
using a different algorithm to calculate the optimal block size that
has been found to be considerably more effective.
Reviewed-by: Tom Stellard <[email protected]>
|
| |
|
|
|
|
|
| |
Variadic template aliases make these versions of GCC very confused,
write down the full type spec instead.
|
|
|
|
|
|
|
|
| |
dso_list was added as an argument for createInternalizePass in 3.4, and then
it was removed again in the same llvm version.
Tested-by: Mike Lothian <[email protected]>
Reviewed-by: Tom Stellard <[email protected]>
|
|
|
|
|
|
|
| |
The ICD loader should be responsible for installing headers.
Reviewed and Tested-by: Aaron Watry <[email protected]>
Reviewed-by: Francisco Jerez <[email protected]>
|
|
|
|
|
|
| |
Fixes https://bugs.freedesktop.org/show_bug.cgi?id=70891.
Reported-by: Bruno Jiménez <[email protected]>
|
|
|
|
|
|
|
|
| |
kernel object.
Based on a similar fix from Aaron Watry. It seems unlikely that we
will ever need a kernel-specific setting for this, and the Gallium API
doesn't support it. Remove kernel::max_block_size() altogether.
|
| |
|
|
|
|
| |
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
| |
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
| |
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
| |
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
| |
Signed-off-by: Francisco Jerez <[email protected]>
|
|
|
|
| |
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
| |
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
| |
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
|
| |
[ Tom Stellard: Make sure to bind global arguments before retrieving handles. ]
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
| |
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
|
|
| |
non-copiable objects.
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
| |
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
| |
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
|
|
| |
objects.
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
| |
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
| |
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
| |
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
| |
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
| |
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
| |
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
| |
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
| |
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
| |
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
|
|
| |
helper class.
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
| |
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
| |
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
|
|
|
|
| |
Identifiers with double underscores are reserved, and using them has
undefined behavior according to the C++ spec. It's unlikely to make
any difference, but...
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
| |
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
| |
Tested-by: Tom Stellard <[email protected]>
|
|
|
|
|
|
| |
This prevents a build failure on some systems.
Reviewed-by: Francisco Jerez <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This is required in order for clang to correctly handle the OpenCL C
barrier() builtin which has the following restrictions acording to
the OpenCL 1.1 Specification:
If barrier is inside a conditional statement, then all work-items must
enter the conditional if any work-item enters the conditional statement
and executes the barrier.
If barrier is inside a loop, all work-items must execute the barrier for
each iteration of the loop before any are allowed to continue execution
beyond the barrier.
By linking before otimizations, we can replace calls to barrier() with
calls to a target specific intrinsic which has the noduplicate attribute
This attribute prevents clang from performing optimizations which could
violate the above rules.
This attribute must be applied to the call instruction that invokes
the function, so it is not enough to add this attribute the barrier()
declaration.
As a bonus this will probably speed up compile times since we will no
longer need to run link-time optimizations.
|
|
|
|
| |
http://llvm.org/viewvc/llvm-project?view=revision&revision=191922
|
| |
|
| |
|
|
|
|
|
| |
Signed-off-by: Emil Velikov <[email protected]>
Reviewed-by: Tom Stellard <[email protected]>
|
|
|
|
|
|
| |
CC: "9.2" <[email protected]>
Reviewed-by: Francisco Jerez <[email protected]>
|
|
|
|
|
|
|
|
| |
The command is submitted once the event has been triggered, but it might not
have completed yet. Therefore, we have to add it to deps in order to wait on it.
Signed-off-by: Niels Ole Salscheider <[email protected]>
Reviewed-by: Francisco Jerez <[email protected]>
|
|
|
|
|
| |
Signed-off-by: Niels Ole Salscheider <[email protected]>
Acked-by: Francisco Jerez <[email protected]>
|