[cfe-commits] r143136 - in /cfe/trunk: lib/CodeGen/CGExpr.cpp lib/CodeGen/CGExprScalar.cpp lib/CodeGen/CodeGenFunction.h test/CodeGenOpenCL/fpaccuracy.cl
clattner at apple.com
Thu Oct 27 13:05:08 PDT 2011
On Oct 27, 2011, at 12:58 PM, Chris Lattner wrote:
> On Oct 27, 2011, at 12:19 PM, Peter Collingbourne wrote:
>> Author: pcc
>> Date: Thu Oct 27 14:19:51 2011
>> New Revision: 143136
>> URL: http://llvm.org/viewvc/llvm-project?rev=143136&view=rev
>> Annotate imprecise FP division with fpaccuracy metadata
>> The OpenCL single precision division operation is only required to
>> be accurate to 2.5ulp. Annotate the fdiv instruction with metadata
>> which signals to the backend that an imprecise divide instruction
>> may be used.
> Hi Peter,
> Please make sure that these annotations are documented in LangRef.
Ah, I see it now, looks great!
More information about the cfe-commits