Displaying 3 results from an estimated 3 matches for "cl_khr_fp64".
Did you mean:
dcl_khr_fp64
2011 Sep 08
1
[LLVMdev] [cfe-dev] Proposal: floating point accuracy metadata (OpenCL related)
...fferent accuracy requirements, especially if LTO
is done on the combined module.
2) Some LLVM optimisations will create operations with a accuracy
requirement different from the language specified accuracy.
For example, consider the following OpenCL kernel:
-----
#pragma OPENCL EXTENSION cl_khr_fp64: enable
__kernel void dpdiv(__global float *result, float x, float y) {
*result = (double) x / (double) y;
}
-----
When compiled to LLVM with optimisations turned off, the function
looks like this:
-----
define void @dpdiv(float* %result, float %x, float %y) nounwind uwtable {
entry:
%result...
2011 Sep 08
0
[LLVMdev] [cfe-dev] Proposal: floating point accuracy metadata (OpenCL related)
Peter,
Is there a way to make this flag globally available? Metadata can be fairly expensive to handle at each node when in many cases it is a global flag and not a per operation flag.
> -----Original Message-----
> From: llvmdev-bounces at cs.uiuc.edu [mailto:llvmdev-bounces at cs.uiuc.edu]
> On Behalf Of Robert Quill
> Sent: Thursday, September 08, 2011 3:24 AM
> To: Peter
2011 Sep 08
1
[LLVMdev] [cfe-dev] Proposal: floating point accuracy metadata (OpenCL related)
Hi Peter,
This sounds like I really good idea. One thing that did occur to me
though from an OpenCL point of view is that ULP accuracy requirements
can differ for embedded and full profile so that may need to be handled
somehow.
Thanks,
Rob
On Wed, 2011-09-07 at 21:55 +0100, Peter Collingbourne wrote:
> Hi,
>
> This is my proposal to add floating point accuracy support to LLVM.
>