AI/rocm-systems
2
0
Форкнуть 0
Код Задачи Запросы на слияние Действия Пакеты Проекты Релизы Вики Активность

fix scatter_perf crash (#1493)

Просмотр исходного кода 
* fix scatter_perf crash

* Update src/misc/msccl/msccl_lifecycle.cc

Co-authored-by: corey-derochie-amd <161367113+corey-derochie-amd@users.noreply.github.com>

* Update src/misc/msccl/msccl_lifecycle.cc

Co-authored-by: corey-derochie-amd <161367113+corey-derochie-amd@users.noreply.github.com>

* More buffsRegisteredNonGraphMode spelling fixes.

---------

Co-authored-by: corey-derochie-amd <161367113+corey-derochie-amd@users.noreply.github.com>

[ROCm/rccl commit: ff130cce7a]
Этот коммит содержится в:
isaki001
2025-01-21 09:24:32 -06:00
коммит произвёл GitHub
родитель 25150b1f20
Коммит 835c708a92
3 изменённых файлов: 22 добавлений и 24 удалений
Скачать Patch файл Скачать Diff файл Показать все файлы Свернуть все файлы
projects/rccl/src/misc/msccl/msccl_lifecycle.cc
+8 -8
Просмотреть файл
@@ -524,13 +524,13 @@ ncclResult_t mscclEnqueueCheck(
NCCLCHECK(mscclGetCaptureStatus(comm->rank, stream));
}
const bool sendBuffRegistered = mscclpp_BuffIsRegistered(comm->mscclpp_comm, sendBuff, count);
const bool recvBuffRegistered = mscclpp_BuffIsRegistered(comm->mscclpp_comm, recvBuff, count);
const bool sendBuffRegistered = mscclpp_BuffIsRegistered(comm->mscclpp_comm, sendBuff);
const bool recvBuffRegistered = mscclpp_BuffIsRegistered(comm->mscclpp_comm, recvBuff);
const bool graphMode = threadLocalStatus.captureStatus != mscclNoCapture;
const bool buffsRegistedNonGraphMode = !graphMode && sendBuffRegistered && recvBuffRegistered;
const bool buffsRegisteredNonGraphMode = !graphMode && sendBuffRegistered && recvBuffRegistered;
/* check if one rank per GPU and graph mode is enabled */
if ((graphMode || buffsRegistedNonGraphMode) && comm->mscclCompatible && nBytes > 0 && (nBytes & 31) == 0) {
if ((graphMode || buffsRegisteredNonGraphMode) && comm->mscclCompatible && nBytes > 0 && (nBytes & 31) == 0) {
bool isManagedBuffer = false;
if (sendBuff) CUDACHECK(hipPointerGetAttribute(&isManagedBuffer, HIP_POINTER_ATTRIBUTE_IS_MANAGED, const_cast<void*>(sendBuff)));
if (!isManagedBuffer && recvBuff) CUDACHECK(hipPointerGetAttribute(&isManagedBuffer, HIP_POINTER_ATTRIBUTE_IS_MANAGED, const_cast<void*>(recvBuff)));
@@ -570,13 +570,13 @@ ncclResult_t mscclEnqueueCheck(
NCCLCHECK(mscclGetCaptureStatus(comm->rank, stream));
}
const bool sendBuffRegistered = mscclpp_BuffIsRegistered(comm->mscclpp_comm, sendBuff, count);
const bool recvBuffRegistered = mscclpp_BuffIsRegistered(comm->mscclpp_comm, recvBuff, count);
const bool sendBuffRegistered = mscclpp_BuffIsRegistered(comm->mscclpp_comm, sendBuff);
const bool recvBuffRegistered = mscclpp_BuffIsRegistered(comm->mscclpp_comm, recvBuff);
const bool graphMode = threadLocalStatus.captureStatus != mscclNoCapture;
const bool buffsRegistedNonGraphMode = !graphMode && sendBuffRegistered && recvBuffRegistered;
const bool buffsRegisteredNonGraphMode = !graphMode && sendBuffRegistered && recvBuffRegistered;
/* check if one rank per GPU and graph mode is enabled */
if ((graphMode || buffsRegistedNonGraphMode) && comm->mscclCompatible && nBytes > 0 && (nBytes & 31) == 0) {
if ((graphMode || buffsRegisteredNonGraphMode) && comm->mscclCompatible && nBytes > 0 && (nBytes & 31) == 0) {
bool isManagedBuffer = false;
if (sendBuff) CUDACHECK(hipPointerGetAttribute(&isManagedBuffer, HIP_POINTER_ATTRIBUTE_IS_MANAGED, const_cast<void*>(sendBuff)));
if (!isManagedBuffer && recvBuff) CUDACHECK(hipPointerGetAttribute(&isManagedBuffer, HIP_POINTER_ATTRIBUTE_IS_MANAGED, const_cast<void*>(recvBuff)));