_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 }