diff --git a/sycl/cmake/modules/FetchUnifiedRuntime.cmake b/sycl/cmake/modules/FetchUnifiedRuntime.cmake index 6ba5ec936259a..fdef7c89a93d4 100644 --- a/sycl/cmake/modules/FetchUnifiedRuntime.cmake +++ b/sycl/cmake/modules/FetchUnifiedRuntime.cmake @@ -116,13 +116,13 @@ if(SYCL_PI_UR_USE_FETCH_CONTENT) endfunction() set(UNIFIED_RUNTIME_REPO "https://github.com/oneapi-src/unified-runtime.git") - # commit 83f7ad9551ce0134931b44804b5a254ae2e93068 - # Merge: ab9baf57 8fb6824d + # commit 3c12bbceec33cf5cf5fc4fa85e641b4f95e820b7 + # Merge: 83f7ad95 ac7eb171 # Author: Omar Ahmed - # Date: Thu Aug 8 11:11:13 2024 +0100 - # Merge pull request #1860 from PietroGhg/pietro/fill - # [NATIVECPU] Fix pointer arithmetic in USMfill - set(UNIFIED_RUNTIME_TAG 83f7ad9551ce0134931b44804b5a254ae2e93068) + # Date: Fri Aug 9 10:51:05 2024 +0100 + # Merge pull request #1910 from Bensuo/sync_point + # [CUDA][HIP] Improve command-buffer sync points + set(UNIFIED_RUNTIME_TAG 3c12bbceec33cf5cf5fc4fa85e641b4f95e820b7) set(UMF_BUILD_EXAMPLES OFF CACHE INTERNAL "EXAMPLES") # Due to the use of dependentloadflag and no installer for UMF and hwloc we need diff --git a/sycl/doc/design/CommandGraph.md b/sycl/doc/design/CommandGraph.md index 2c8d21d7dc4d8..2f83d42a3c57c 100644 --- a/sycl/doc/design/CommandGraph.md +++ b/sycl/doc/design/CommandGraph.md @@ -480,6 +480,14 @@ An executable CUDA Graph, which contains all commands and synchronization information, is saved in the UR command-buffer to allow for efficient graph resubmission. +#### Prefetch & Advise + +The `urCommandBufferAppendUSMPrefetchExp` and +`urCommandBufferAppendUSMAdviseExp` UR entry-points used to implement +`handler::prefetch` and `handler::mem_advise` are implemented in the CUDA UR +adapter as empty nodes enforcing the node dependencies. As such the +optimization hints are a no-op. + ### HIP The HIP backend offers a graph management API very similar to CUDA Graph @@ -502,6 +510,14 @@ An executable HIP Graph, which contains all commands and synchronization information, is saved in the UR command-buffer to allow for efficient graph resubmission. +#### Prefetch & Advise + +The `urCommandBufferAppendUSMPrefetchExp` and +`urCommandBufferAppendUSMAdviseExp` UR entry-points used to implement +`handler::prefetch` and `handler::mem_advise` are implemented in the HIP UR +adapter as empty nodes enforcing the node dependencies. As such the +optimization hints are a no-op. + ### OpenCL SYCL-Graph is only enabled for an OpenCL backend when the