[Openmp-commits] [PATCH] D127505: [Libomptarget] Add checks for CUDA subarchitecture using new info

[Joseph Huber via Phabricator via Openmp-commits]

This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rGe01ce4e88a84: [Libomptarget] Add checks for CUDA subarchitecture using new info (authored by jhuber6).

Changed prior to commit:
  https://reviews.llvm.org/D127505?vs=436409&id=446557#toc

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D127505/new/

https://reviews.llvm.org/D127505

Files:
  openmp/libomptarget/plugins/cuda/src/rtl.cpp
  openmp/libomptarget/plugins/exports


Index: openmp/libomptarget/plugins/exports
===================================================================
--- openmp/libomptarget/plugins/exports
+++ openmp/libomptarget/plugins/exports
@@ -1,6 +1,7 @@
 VERS1.0 {
   global:
     __tgt_rtl_is_valid_binary;
+    __tgt_rtl_is_valid_binary_info;
     __tgt_rtl_is_data_exchangable;
     __tgt_rtl_number_of_devices;
     __tgt_rtl_init_requires;
Index: openmp/libomptarget/plugins/cuda/src/rtl.cpp
===================================================================
--- openmp/libomptarget/plugins/cuda/src/rtl.cpp
+++ openmp/libomptarget/plugins/cuda/src/rtl.cpp
@@ -1519,6 +1519,43 @@
   return elf_check_machine(Image, /* EM_CUDA */ 190);
 }
 
+int32_t __tgt_rtl_is_valid_binary_info(__tgt_device_image *image,
+                                       __tgt_image_info *info) {
+  if (!__tgt_rtl_is_valid_binary(image))
+    return false;
+
+  // A subarchitecture was not specified. Assume it is compatible.
+  if (!info->Arch)
+    return true;
+
+  int32_t NumberOfDevices = 0;
+  if (cuDeviceGetCount(&NumberOfDevices) != CUDA_SUCCESS)
+    return false;
+
+  for (int32_t DeviceId = 0; DeviceId < NumberOfDevices; ++DeviceId) {
+    CUdevice Device;
+    if (cuDeviceGet(&Device, DeviceId) != CUDA_SUCCESS)
+      return false;
+
+    int32_t Major, Minor;
+    if (cuDeviceGetAttribute(&Major,
+                             CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR,
+                             Device) != CUDA_SUCCESS)
+      return false;
+    if (cuDeviceGetAttribute(&Minor,
+                             CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR,
+                             Device) != CUDA_SUCCESS)
+      return false;
+
+    std::string ArchStr = "sm_" + std::to_string(Major) + std::to_string(Minor);
+    if (ArchStr != info->Arch)
+      return false;
+  }
+
+  DP("Image has compatible compute capability: %s\n", info->Arch);
+  return true;
+}
+
 int32_t __tgt_rtl_number_of_devices() { return DeviceRTL.getNumOfDevices(); }
 
 int64_t __tgt_rtl_init_requires(int64_t RequiresFlags) {


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D127505.446557.patch
Type: text/x-patch
Size: 2068 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/openmp-commits/attachments/20220721/db8decc9/attachment.bin>