DS_Max_Warp_Number = 16,
};
+enum : __kmpc_impl_lanemask_t {
+ __kmpc_impl_all_lanes = ~(__kmpc_impl_lanemask_t)0
+};
+
INLINE void __kmpc_impl_unpack(uint64_t val, uint32_t &lo, uint32_t &hi) {
lo = (uint32_t)(val & UINT64_C(0x00000000FFFFFFFF));
hi = (uint32_t)((val & UINT64_C(0xFFFFFFFF00000000)) >> 32);
return (((uint64_t)hi) << 32) | (uint64_t)lo;
}
-enum : __kmpc_impl_lanemask_t {
- __kmpc_impl_all_lanes = ~(__kmpc_impl_lanemask_t)0
-};
-
DEVICE __kmpc_impl_lanemask_t __kmpc_impl_lanemask_lt();
-
DEVICE __kmpc_impl_lanemask_t __kmpc_impl_lanemask_gt();
-
DEVICE uint32_t __kmpc_impl_smid();
-
DEVICE double __kmpc_impl_get_wtick();
-
DEVICE double __kmpc_impl_get_wtime();
INLINE uint64_t __kmpc_impl_ffs(uint64_t x) { return __builtin_ffsl(x); }
-
INLINE uint64_t __kmpc_impl_popc(uint64_t x) { return __builtin_popcountl(x); }
-template <typename T> INLINE T __kmpc_impl_min(T x, T y) {
- return x < y ? x : y;
-}
-
DEVICE __kmpc_impl_lanemask_t __kmpc_impl_activemask();
DEVICE int32_t __kmpc_impl_shfl_sync(__kmpc_impl_lanemask_t, int32_t Var,
return (s & ~(unsigned)(WARPSIZE - 1));
}
+INLINE static uint32_t kmpcMin(uint32_t x, uint32_t y) { return x < y ? x : y; }
+
DEVICE static volatile uint32_t IterCnt = 0;
DEVICE static volatile uint32_t Cnt = 0;
EXTERN int32_t __kmpc_nvptx_teams_reduce_nowait_v2(
// by returning 1 in the thread holding the reduction result.
// Check if this is the very last team.
- unsigned NumRecs = __kmpc_impl_min(NumTeams, uint32_t(num_of_records));
+ unsigned NumRecs = kmpcMin(NumTeams, uint32_t(num_of_records));
if (ChunkTeamCount == NumTeams - Bound - 1) {
//
// Last team processing.
//
if (ThreadId >= NumRecs)
return 0;
- NumThreads = roundToWarpsize(__kmpc_impl_min(NumThreads, NumRecs));
+ NumThreads = roundToWarpsize(kmpcMin(NumThreads, NumRecs));
if (ThreadId >= NumThreads)
return 0;
// When we have more than [warpsize] number of threads
// a block reduction is performed here.
- uint32_t ActiveThreads = __kmpc_impl_min(NumRecs, NumThreads);
+ uint32_t ActiveThreads = kmpcMin(NumRecs, NumThreads);
if (ActiveThreads > WARPSIZE) {
uint32_t WarpsNeeded = (ActiveThreads + WARPSIZE - 1) / WARPSIZE;
// Gather all the reduced values from each warp
DEVICE double __kmpc_impl_get_wtick();
DEVICE double __kmpc_impl_get_wtime();
-INLINE uint32_t __kmpc_impl_ffs(uint32_t x) { return __ffs(x); }
-
-INLINE uint32_t __kmpc_impl_popc(uint32_t x) { return __popc(x); }
-
-template <typename T> INLINE T __kmpc_impl_min(T x, T y) {
- return min(x, y);
-}
+INLINE uint32_t __kmpc_impl_ffs(uint32_t x) { return __builtin_ffs(x); }
+INLINE uint32_t __kmpc_impl_popc(uint32_t x) { return __builtin_popcount(x); }
#ifndef CUDA_VERSION
#error CUDA_VERSION macro is undefined, something wrong with cuda.