AI/rocm-systems
2
0
Forka 0
Codice Problemi Pull Request Actions Pacchetti Progetti Rilasci Wiki Attività

Merge remote-tracking branch 'nccl/master' into develop

Sfoglia il codice sorgente
This commit is contained in:
BertanDogancay
2025-04-23 20:46:36 -07:00
parent 82afb2bcfe dcdc67c40b
commit a6bf9bfc9e
118 ha cambiato i file con 12789 aggiunte e 3358 eliminazioni
Scarica il file Patch Scarica il file Diff Expand all files Collapse all files
src/device/primitives.h
+5 -2
Vedi File
@@ -142,7 +142,7 @@ struct FanSymmetric {
};
// The primitives class. Specialized per protocol in the other headers.
template<typename T, typename RedOp, typename Fan, int Direct, typename Proto, int P2p>
template<typename T, typename RedOp, typename Fan, int Direct, typename Proto, int P2p, bool isNetOffload = false>
class Primitives;
// Used by LL & LL128 to implement direct members in the naive way.
@@ -160,9 +160,12 @@ struct PrimitivesWithoutDirect {
__device__ void directCopySend(intptr_t inpIx, intptr_t outIx, int eltN, bool postOp=false) {
static_cast<RealPrimitives*>(this)->copySend(inpIx, outIx, eltN, postOp);
}
__device__ void directRecvCopyDirectSend(intptr_t outIx, int eltN, bool postOp=false) {
__device__ void directRecvCopyDirectSend(intptr_t inpIx, intptr_t outIx, int eltN, bool postOp=false) {
static_cast<RealPrimitives*>(this)->recvCopySend(outIx, eltN, /*postOp=*/false);
}
__device__ void directRecvDirectSend(intptr_t inpIx, intptr_t outIx, int eltN, bool postOp=false) {
return;
}
__device__ void recvReduceCopyDirectSend(intptr_t inpIx, intptr_t outIx, int eltN, bool postOp=false) {
// Direct is only for the send part
static_cast<RealPrimitives*>(this)->recvReduceCopySend(inpIx, outIx, eltN, postOp);