From 4ccb3366ade6ec9493f8ca20ab73b0da4b9816db Mon Sep 17 00:00:00 2001 From: Tobias Burnus Date: Wed, 29 May 2024 15:14:38 +0200 Subject: libgomp: Enable USM for some nvptx devices A few high-end nvptx devices support the attribute CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS; for those, unified shared memory is supported in hardware. This patch enables support for those - if all installed nvptx devices have this feature (as the capabilities are per device type). This exposes a bug in gomp_copy_back_icvs as it did before use omp_get_mapped_ptr to find mapped variables, but that returns the unchanged pointer in cased of shared memory. But in this case, we have a few actually mapped pointers - like the ICV variables. Additionally, there was a mismatch with regards to '-1' for the device number as gomp_copy_back_icvs and omp_get_mapped_ptr count differently. Hence, do the lookup manually. include/ChangeLog: * cuda/cuda.h (CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS): Add. libgomp/ChangeLog: * libgomp.texi (nvptx): Update USM description. * plugin/plugin-nvptx.c (GOMP_OFFLOAD_get_num_devices): Claim support when requesting USM and all devices support CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS. * target.c (gomp_copy_back_icvs): Fix device ptr lookup. (gomp_target_init): Set GOMP_OFFLOAD_CAP_SHARED_MEM is the devices supports USM. --- libgomp/plugin/plugin-nvptx.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'libgomp/plugin') diff --git a/libgomp/plugin/plugin-nvptx.c b/libgomp/plugin/plugin-nvptx.c index 5aad344..4cedc53 100644 --- a/libgomp/plugin/plugin-nvptx.c +++ b/libgomp/plugin/plugin-nvptx.c @@ -1201,8 +1201,23 @@ GOMP_OFFLOAD_get_num_devices (unsigned int omp_requires_mask) if (num_devices > 0 && ((omp_requires_mask & ~(GOMP_REQUIRES_UNIFIED_ADDRESS + | GOMP_REQUIRES_UNIFIED_SHARED_MEMORY | GOMP_REQUIRES_REVERSE_OFFLOAD)) != 0)) return -1; + /* Check whether host page access (direct or via migration) is supported; + if so, enable USM. Currently, capabilities is per device type, hence, + check all devices. */ + if (num_devices > 0 + && (omp_requires_mask & GOMP_REQUIRES_UNIFIED_SHARED_MEMORY)) + for (int dev = 0; dev < num_devices; dev++) + { + int pi; + CUresult r; + r = CUDA_CALL_NOCHECK (cuDeviceGetAttribute, &pi, + CU_DEVICE_ATTRIBUTE_PAGEABLE_MEMORY_ACCESS, dev); + if (r != CUDA_SUCCESS || pi == 0) + return -1; + } return num_devices; } -- cgit v1.1