================
@@ -74,49 +72,53 @@ static int32_t nvptx_parallel_reduce_nowait(void
*reduce_data,
uint32_t NumThreads = omp_get_num_threads();
if (NumThreads == 1)
return 1;
- /*
- * This reduce function handles reduction within a team. It handles
- * parallel regions in both L1 and L2 parallelism levels. It also
- * supports Generic, SPMD, and NoOMP modes.
- *
- * 1. Reduce within a warp.
- * 2. Warp master copies value to warp 0 via shared memory.
- * 3. Warp 0 reduces to a single value.
- * 4. The reduced value is available in the thread that returns 1.
- */
-
-#if defined(__CUDA_ARCH__) && __CUDA_ARCH__ >= 700
- uint32_t WarpsNeeded =
- (NumThreads + mapping::getWarpSize() - 1) / mapping::getWarpSize();
- uint32_t WarpId = mapping::getWarpIdInBlock();
-
- // Volta execution model:
- // For the Generic execution mode a parallel region either has 1 thread and
- // beyond that, always a multiple of 32. For the SPMD execution mode we may
- // have any number of threads.
- if ((NumThreads % mapping::getWarpSize() == 0) || (WarpId < WarpsNeeded - 1))
- gpu_regular_warp_reduce(reduce_data, shflFct);
- else if (NumThreads > 1) // Only SPMD execution mode comes thru this case.
- gpu_irregular_warp_reduce(reduce_data, shflFct,
- /*LaneCount=*/NumThreads %
mapping::getWarpSize(),
- /*LaneId=*/mapping::getThreadIdInBlock() %
- mapping::getWarpSize());
- // When we have more than [mapping::getWarpSize()] number of threads
- // a block reduction is performed here.
//
- // Only L1 parallel region can enter this if condition.
- if (NumThreads > mapping::getWarpSize()) {
- // Gather all the reduced values from each warp
- // to the first warp.
- cpyFct(reduce_data, WarpsNeeded);
+ // This reduce function handles reduction within a team. It handles
+ // parallel regions in both L1 and L2 parallelism levels. It also
+ // supports Generic, SPMD, and NoOMP modes.
+ //
+ // 1. Reduce within a warp.
+ // 2. Warp master copies value to warp 0 via shared memory.
+ // 3. Warp 0 reduces to a single value.
+ // 4. The reduced value is available in the thread that returns 1.
+ //
- if (WarpId == 0)
- gpu_irregular_warp_reduce(reduce_data, shflFct, WarpsNeeded,
- BlockThreadId);
+#if __has_builtin(__nvvm_reflect)
+ if (__nvvm_reflect("__CUDA_ARCH") >= 700) {
----------------
shiltian wrote:
I'll try to make an AMDGPU counterpart for this one, though it doesn't look
like necessary for the purpose of OpenMP device runtime.
https://github.com/llvm/llvm-project/pull/119091
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
