-
Notifications
You must be signed in to change notification settings - Fork 745
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Support more image_channel_types in image_accessors read/write API for half4 datatype on host device. #1502
Conversation
dc20df7
to
4da30c4
Compare
int main() { | ||
// Checking only for dimension=1. | ||
// create image: | ||
char HostPtr[100]; |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Suggest using std::array with size = sizeof(sycl::cl_half4). And avoid using magic number on line 99 and 80.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think you are referring to range<1>{10} as the magic number.
The number of bytes needed in HostPtr is related to the image Element size . (See function: getImageElementSize () in image_impl.cpp )
With image of order rgba , with channel_type::fp16, each image element will take 8 bytes.
With image of order rgba, with channel_type::snorm_int8, each image element will take 4 bytes.
So when range is 10, We will need a total of 80 bytes (40 bytes for second case) in HostPtr and to safely write/read all elements.
You are right that 10 is a random number taken. The value of 100 is more of a safe limit taken. To make it exact I will have to initialize it for each image kind separately.
… API for half4 datatype on host device. Signed-off-by: Garima Gupta <garima.gupta@intel.com>
Enabled it for GPU. Signed-off-by: Garima Gupta <garima.gupta@intel.com>
Signed-off-by: Garima Gupta <garima.gupta@intel.com>
Signed-off-by: Garima Gupta <garima.gupta@intel.com>
Signed-off-by: Garima Gupta <garima.gupta@intel.com>
Signed-off-by: Garima Gupta <garima.gupta@intel.com>
fp16. Signed-off-by: Garima Gupta <garima.gupta@intel.com>
Signed-off-by: Garima Gupta <garima.gupta@intel.com>
edd3f55
to
7d48115
Compare
@AlexeySachkov @romanovvlad Let me know if you feel something is further needed in this PR. |
@romanovvlad Hi Vlad, Please have a quick look whenever you get sometime. |
@romanovvlad @AlexeySachkov @bader |
…versioning * origin/sycl: [XPTI][Framework] Reference implementation of the Xpti framework to be used with instrumentation in SYCL (intel#1557) [SYCL] Initial ABI checks implementation (intel#1528) [SYCL] Support connection with multiple plugins (intel#1490) [SYCL] Add a new header file with the reduction class definition (intel#1558) [SYCL] Add test for SYCL kernels with accessor and spec constant (intel#1536) [SYCL][CUDA] Move interop tests (intel#1570) [Driver][SYCL] Remove COFF object format designator for Windows device compiles (intel#1574) [SYCL] Fix conflicting visibility attributes (intel#1571) [SYCL][DOC] Update the SYCL Runtime Interface document with design details (intel#680) [SYCL] Improve image accessors support on a host device (intel#1502) [SYCL] Make queue's non-USM event ownership temporary (intel#1561) [SYCL] Added support of rounding modes for non-host devices (intel#1463) [SYCL] SemaSYCL significant refactoring (intel#1517) [SYCL] Support 0-dim accessor in handler::copy(accessor, accessor) (intel#1551)
Also, clean up done of image_accessor_readwrite test to enable it for GPU.