common: fix return value check for setpriority (#18412)

* common: fix return value check for setpriority

* tools: add logging for process priority setting

common/common.cpp

@@ -251,7 +251,7 @@ bool set_process_priority(enum ggml_sched_priority prio) {
         case GGML_SCHED_PRIO_REALTIME: p = -20; break;
     }
 
-    if (!setpriority(PRIO_PROCESS, 0, p)) {
+    if (setpriority(PRIO_PROCESS, 0, p) != 0) {
         LOG_WRN("failed to set process priority %d : %s (%d)\n", prio, strerror(errno), errno);
         return false;
     }

ggml/src/ggml-cuda/CMakeLists.txt

@@ -35,6 +35,20 @@ if (CUDAToolkit_FOUND)
             if (CUDAToolkit_VERSION VERSION_GREATER_EQUAL "11.8")
                 list(APPEND CMAKE_CUDA_ARCHITECTURES 89-real)
             endif()
+
+            if (CUDAToolkit_VERSION VERSION_GREATER_EQUAL "12.8")
+                # The CUDA architecture 120f-virtual would in principle work for Blackwell support
+                #     but the newly added "f" suffix conflicted with a preexising regex for validating CUDA architectures in CMake.
+                # So either a recent CMake version or one with the backported fix is needed.
+                # The following versions should work:
+                #   - CMake >= v3.31.8 && CMake < v4.0.0
+                #   - CMake >= v4.0.2
+                # This is NOT documented in the CMake release notes,
+                #     check Modules/Internal/CMakeCUDAArchitecturesValidate.cmake in the CMake git repository instead.
+                # However, the architectures 120a-real and 121a-real should work with basically any CMake version and
+                #     until the release of e.g. Rubin there is no benefit to shipping virtual architectures for Blackwell.
+                list(APPEND CMAKE_CUDA_ARCHITECTURES 120a-real 121a-real)
+            endif()
         endif()
     endif()
     message(STATUS "Using CUDA architectures: ${CMAKE_CUDA_ARCHITECTURES}")
@@ -62,7 +76,7 @@ if (CUDAToolkit_FOUND)
     else()
         foreach(ARCH ${CMAKE_CUDA_ARCHITECTURES})
             if(ARCH MATCHES "^12[0-9](-real|-virtual)?$")
-                message(FATAL_ERROR "Compute capability ${ARCH} used, use ${ARCH}a or ${ARCH}f for Blackwell specific optimizations")
+                message(FATAL_ERROR "Compute capability ${ARCH} used, use ${ARCH}a or ${ARCH}f for Blackwell-specific optimizations")
             endif()
         endforeach()
     endif()

tools/completion/completion.cpp

@@ -175,7 +175,10 @@ int main(int argc, char ** argv) {
     struct ggml_threadpool_params tpp =
             ggml_threadpool_params_from_cpu_params(params.cpuparams);
 
-    set_process_priority(params.cpuparams.priority);
+    if (!set_process_priority(params.cpuparams.priority)) {
+        LOG_ERR("%s: error: failed to set process priority\n", __func__);
+        return 1;
+    }
 
     struct ggml_threadpool * threadpool_batch = NULL;
     if (!ggml_threadpool_params_match(&tpp, &tpp_batch)) {

tools/llama-bench/llama-bench.cpp

@@ -2037,7 +2037,10 @@ int main(int argc, char ** argv) {
     llama_backend_init();
     llama_numa_init(params.numa);
 
-    set_process_priority(params.prio);
+    if (!set_process_priority(params.prio)) {
+        fprintf(stderr, "%s: error: failed to set process priority\n", __func__);
+        return 1;
+    }
 
     // initialize printer
     std::unique_ptr<printer> p     = create_printer(params.output_format);