[opencl] Better cn/r specific resource management.

src/backend/opencl/runners/OclCnRunner.cpp

@@ -75,6 +75,7 @@ xmrig::OclCnRunner::~OclCnRunner()
     }
 
     if (m_algorithm == Algorithm::CN_R) {
+        OclLib::release(m_cnr);
         OclCnR::clear();
     }
 }
@@ -130,10 +131,15 @@ void xmrig::OclCnRunner::set(const Job &job, uint8_t *blob)
     if (m_algorithm == Algorithm::CN_R && m_height != job.height()) {
         delete m_cn1;
 
-        m_height = job.height();
+        m_height     = job.height();
-        m_cnr    = OclCnR::get(*this, m_height);
+        auto program = OclCnR::get(*this, m_height);
-        m_cn1    = new Cn1Kernel(m_cnr, m_height);
+        m_cn1        = new Cn1Kernel(program, m_height);
         m_cn1->setArgs(m_input, m_scratchpads, m_states, m_intensity);
+
+        if (m_cnr != program) {
+            OclLib::release(m_cnr);
+            m_cnr = OclLib::retain(program);
+        }
     }
 
     for (auto kernel : m_branchKernels) {

src/backend/opencl/wrappers/OclLib.cpp

@@ -73,6 +73,7 @@ static const char *kReleaseDevice                    = "clReleaseDevice";
 static const char *kReleaseKernel                    = "clReleaseKernel";
 static const char *kReleaseMemObject                 = "clReleaseMemObject";
 static const char *kReleaseProgram                   = "clReleaseProgram";
+static const char *kRetainProgram                    = "clRetainProgram";
 static const char *kSetKernelArg                     = "clSetKernelArg";
 static const char *kSetMemObjectDestructorCallback   = "clSetMemObjectDestructorCallback";
 static const char *kUnloadPlatformCompiler           = "clUnloadPlatformCompiler";
@@ -105,6 +106,7 @@ typedef cl_int (CL_API_CALL *releaseDevice_t)(cl_device_id device);
 typedef cl_int (CL_API_CALL *releaseKernel_t)(cl_kernel);
 typedef cl_int (CL_API_CALL *releaseMemObject_t)(cl_mem);
 typedef cl_int (CL_API_CALL *releaseProgram_t)(cl_program);
+typedef cl_int (CL_API_CALL *retainProgram_t)(cl_program);
 typedef cl_int (CL_API_CALL *setKernelArg_t)(cl_kernel, cl_uint, size_t, const void *);
 typedef cl_int (CL_API_CALL *setMemObjectDestructorCallback_t)(cl_mem, void (CL_CALLBACK *)(cl_mem, void *), void *);
 typedef cl_int (CL_API_CALL *unloadPlatformCompiler_t)(cl_platform_id);
@@ -146,6 +148,7 @@ static releaseDevice_t pReleaseDevice                                       = nu
 static releaseKernel_t pReleaseKernel                                       = nullptr;
 static releaseMemObject_t pReleaseMemObject                                 = nullptr;
 static releaseProgram_t pReleaseProgram                                     = nullptr;
+static retainProgram_t pRetainProgram                                       = nullptr;
 static setKernelArg_t pSetKernelArg                                         = nullptr;
 static setMemObjectDestructorCallback_t pSetMemObjectDestructorCallback     = nullptr;
 static unloadPlatformCompiler_t pUnloadPlatformCompiler                     = nullptr;
@@ -235,6 +238,7 @@ bool xmrig::OclLib::load()
     DLSYM(UnloadPlatformCompiler);
     DLSYM(SetMemObjectDestructorCallback);
     DLSYM(CreateSubBuffer);
+    DLSYM(RetainProgram);
 
 #   if defined(CL_VERSION_2_0)
     uv_dlsym(&oclLib, kCreateCommandQueueWithProperties, reinterpret_cast<void**>(&pCreateCommandQueueWithProperties));
@@ -557,7 +561,7 @@ cl_int xmrig::OclLib::release(cl_program program) noexcept
         return CL_SUCCESS;
     }
 
-    LOG_REFS("%p %u ~program %s", program, getUint(program, CL_PROGRAM_REFERENCE_COUNT), getString(program, CL_PROGRAM_KERNEL_NAMES).data());
+    LOG_REFS("%p %u ~program %s", program, getUint(program, CL_PROGRAM_REFERENCE_COUNT), getString(program, CL_PROGRAM_KERNEL_NAMES).data()); // FIXME
 
     const cl_int ret = pReleaseProgram(program);
     if (ret != CL_SUCCESS) {
@@ -696,6 +700,18 @@ cl_program xmrig::OclLib::createProgramWithSource(cl_context context, cl_uint co
 }
 
 
+cl_program xmrig::OclLib::retain(cl_program program) noexcept
+{
+    assert(pRetainProgram != nullptr);
+
+    if (program != nullptr) {
+        pRetainProgram(program);
+    }
+
+    return program;
+}
+
+
 cl_uint xmrig::OclLib::getNumPlatforms() noexcept
 {
     cl_uint count = 0;

src/backend/opencl/wrappers/OclLib.h

@@ -81,6 +81,7 @@ public:
     static cl_mem createSubBuffer(cl_mem buffer, cl_mem_flags flags, size_t offset, size_t size);
     static cl_program createProgramWithBinary(cl_context context, cl_uint num_devices, const cl_device_id *device_list, const size_t *lengths, const unsigned char **binaries, cl_int *binary_status, cl_int *errcode_ret) noexcept;
     static cl_program createProgramWithSource(cl_context context, cl_uint count, const char **strings, const size_t *lengths, cl_int *errcode_ret) noexcept;
+    static cl_program retain(cl_program program) noexcept;
     static cl_uint getNumPlatforms() noexcept;
     static cl_uint getUint(cl_command_queue command_queue, cl_command_queue_info param_name, cl_uint defaultValue = 0) noexcept;
     static cl_uint getUint(cl_context context, cl_context_info param_name, cl_uint defaultValue = 0) noexcept;