Merge pull request #1062 from mhbliao/hliao/master/icmp

[hip] Re-implement ballot using AMDGCN builtins
Esse commit está contido em:
Maneesh Gupta
2019-05-03 17:48:19 +05:30
commit de GitHub
+8
Ver Arquivo
@@ -736,13 +736,21 @@ int __any(int predicate) {
__device__
inline
unsigned long long int __ballot(int predicate) {
#if defined(__HCC__)
return __llvm_amdgcn_icmp_i32(predicate, 0, ICMP_NE);
#else
return __builtin_amdgcn_uicmp(predicate, 0, ICMP_NE);
#endif
}
__device__
inline
unsigned long long int __ballot64(int predicate) {
#if defined(__HCC__)
return __llvm_amdgcn_icmp_i32(predicate, 0, ICMP_NE);
#else
return __builtin_amdgcn_uicmp(predicate, 0, ICMP_NE);
#endif
}
// hip.amdgcn.bc - lanemask