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

[hip] Re-implement ballot using AMDGCN builtins
这个提交包含在:
Maneesh Gupta 编写, GitHub 于 2019-05-03 17:48:19 +05:30 提交
2 父节点 ad070d4da5 a7a4d80f54
当前提交 2eafa5dcf9
1 个文件已更改
+8
@@ -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