04a46bf0a2
This is only really needed for VI+ ASICs. However, llvm would cast the value to i32 for older asics anyway. The proper fix is in LLVM-7 (r326535). Fixes CTS popcount on carrizo. Reviewer: Aaron Watry <awatry@gmail.com> Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 327044
18 lines
799 B
C++
18 lines
799 B
C++
_CLC_OVERLOAD _CLC_DEF __CLC_GENTYPE popcount(__CLC_GENTYPE x) {
|
|
/* LLVM-4+ implements i16 ops for VI+ ASICs. However, ctpop implementation
|
|
* is missing until r326535. Therefore we have to convert sub i32 types to uint
|
|
* as a workaround. */
|
|
#if __clang_major__ < 7 && __clang_major__ > 3 && __CLC_GENSIZE < 32
|
|
/* Prevent sign extension on uint conversion */
|
|
const __CLC_U_GENTYPE y = __CLC_XCONCAT(as_, __CLC_U_GENTYPE)(x);
|
|
/* Convert to uintX */
|
|
const __CLC_XCONCAT(uint, __CLC_VECSIZE) z = __CLC_XCONCAT(convert_uint, __CLC_VECSIZE)(y);
|
|
/* Call popcount on uintX type */
|
|
const __CLC_XCONCAT(uint, __CLC_VECSIZE) res = __clc_native_popcount(z);
|
|
/* Convert the result back to gentype. */
|
|
return __CLC_XCONCAT(convert_, __CLC_GENTYPE)(res);
|
|
#else
|
|
return __clc_native_popcount(x);
|
|
#endif
|
|
}
|