Enabled ACL_SUPPORT_DOUBLE to support cl_khr_fp64 #230
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Due to this SYCL change intel/llvm#6982, this is a critical issue. Because if we don't solve this, we will lose double support in oneAPI. This change should go into 2023.1. Hao already tested the previous failed tests in simulation and hardware. |
zibaiwan
approved these changes
Jan 3, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Our FPGA runtime failed in HW runs with error "Required aspect fp64 is not supported on the device" because we claim supporting double precision floating-point in kernels but don't support thecl_khr_fp64 extension.
According to OpenCL 1.2 spec (cl_khr_fp64 (khronos.org)), cl_khr_fp64 should be supported if CL_DEVICE_DOUBLE_FP_CONFIG for clGetDeviceInfo for a device is not zero.
Our FPGA runtime already supports CL_FP_DENORM, CL_FP_INF_NAN, CL_FP_ROUND_TO_NEAREST, CL_FP_ROUND_TO_ZERO, CL_FP_ROUND_TO_INF, and CL_FP_FMA for CL_DEVICE_DOUBLE_FP_CONFIG, so cl_khr_fp64 should also be enabled.
It can be enabled by setting ACL_SUPPORT_DOUBLE to 1 in the Cmakelist here.