maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Add intrinsics to represent fp16 <-> fp32 conversions 

llvm-svn: 98497
This commit is contained in:
Anton Korobeynikov 2010-03-14 18:41:50 +00:00
parent a30d4ce194
commit 77bbbf782a
1 changed files with 8 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
llvm/include/llvm/Intrinsics.td
View File

@ -450,6 +450,14 @@ def int_flt_rounds : Intrinsic<[llvm_i32_ty]>,
def int_trap : Intrinsic<[llvm_void_ty]>, def int_trap : Intrinsic<[llvm_void_ty]>,
GCCBuiltin<"__builtin_trap">; GCCBuiltin<"__builtin_trap">;
// Intrisics to support half precision floating point format
def int_convert_to_fp16 : Intrinsic<[llvm_i16_ty],
[llvm_float_ty]>,
GCCBuiltin<"__gnu_f2h_ieee">;
def int_convert_from_fp16 : Intrinsic<[llvm_float_ty],
[llvm_i16_ty]>,
GCCBuiltin<"__gnu_h2f_ieee">;
// These convert intrinsics are to support various conversions between // These convert intrinsics are to support various conversions between
// various types with rounding and saturation. NOTE: avoid using these // various types with rounding and saturation. NOTE: avoid using these
// intrinsics as they might be removed sometime in the future and // intrinsics as they might be removed sometime in the future and