Cycles: require Experimental to be set to enable CUDA on cards with shader model

lower than 1.3, since we're not officially supporting these. We're already not
providing CUDA binaries for these, so better make it clear when compiling from
source too.

7 files changed, 32 insertions, 11 deletions

diff --git a/intern/cycles/blender/blender_sync.cpp b/intern/cycles/blender/blender_sync.cpp
index b66004bee58..4c8fe350b88 100644
--- a/intern/cycles/blender/blender_sync.cpp
+++ b/intern/cycles/blender/blender_sync.cpp
@@ -257,7 +257,7 @@ SessionParams BlenderSync::get_session_params(BL::Scene b_scene, bool background
 	PointerRNA cscene = RNA_pointer_get(&b_scene.ptr, "cycles");
 
 	/* feature set */
-	bool experimental = (RNA_enum_get(&cscene, "feature_set") != 0);
+	params.experimental = (RNA_enum_get(&cscene, "feature_set") != 0);
 
 	/* device type */
 	params.device_type = DEVICE_CPU;
@@ -266,14 +266,14 @@ SessionParams BlenderSync::get_session_params(BL::Scene b_scene, bool background
 		vector<DeviceType> types = Device::available_types();
 		DeviceType dtype;
 		
-		if(!experimental || RNA_enum_get(&cscene, "gpu_type") == 0)
+		if(!params.experimental || RNA_enum_get(&cscene, "gpu_type") == 0)
 			dtype = DEVICE_CUDA;
 		else
 			dtype = DEVICE_OPENCL;
 
 		if(device_type_available(types, dtype))
 			params.device_type = dtype;
-		else if(experimental && device_type_available(types, DEVICE_OPENCL))
+		else if(params.experimental && device_type_available(types, DEVICE_OPENCL))
 			params.device_type = DEVICE_OPENCL;
 		else if(device_type_available(types, DEVICE_CUDA))
 			params.device_type = DEVICE_CUDA;
diff --git a/intern/cycles/device/device.h b/intern/cycles/device/device.h
index 5552e6ab7e2..5b87b11b6b8 100644
--- a/intern/cycles/device/device.h
+++ b/intern/cycles/device/device.h
@@ -112,7 +112,7 @@ public:
 	virtual void *osl_memory() { return NULL; }
 
 	/* load/compile kernels, must be called before adding tasks */ 
-	virtual bool load_kernels() { return true; }
+	virtual bool load_kernels(bool experimental) { return true; }
 
 	/* tasks */
 	virtual void task_add(DeviceTask& task) = 0;
diff --git a/intern/cycles/device/device_cuda.cpp b/intern/cycles/device/device_cuda.cpp
index 83d3f79d96f..eb0e20db355 100644
--- a/intern/cycles/device/device_cuda.cpp
+++ b/intern/cycles/device/device_cuda.cpp
@@ -214,6 +214,21 @@ public:
 		return string("CUDA ") + deviceName;
 	}
 
+	bool support_device(bool experimental)
+	{
+		if(!experimental) {
+			int major, minor;
+			cuDeviceComputeCapability(&major, &minor, cuDevId);
+
+			if(major <= 1 && minor <= 2) {
+				cuda_error(string_printf("CUDA device supported only with shader model 1.3 or up, found %d.%d.", major, minor));
+				return false;
+			}
+		}
+
+		return true;
+	}
+
 	string compile_kernel()
 	{
 		/* compute cubin name */
@@ -236,11 +251,11 @@ public:
 		if(path_exists(cubin))
 			return cubin;
 
-#ifdef WITH_CUDA_BINARIES
+#if defined(WITH_CUDA_BINARIES) && defined(_WIN32)
 		if(major <= 1 && minor <= 2)
 			cuda_error(string_printf("CUDA device supported only with shader model 1.3 or up, found %d.%d.", major, minor));
 		else
-			cuda_error("CUDA binary kernel for this graphics card not found.");
+			cuda_error("CUDA binary kernel for this graphics card shader model (%d.%d) not found.", major, minor);
 		return "";
 #else
 		/* if not, find CUDA compiler */
@@ -283,12 +298,15 @@ public:
 #endif
 	}
 
-	bool load_kernels()
+	bool load_kernels(bool experimental)
 	{
 		/* check if cuda init succeeded */
 		if(cuContext == 0)
 			return false;
 
+		if(!support_device(experimental))
+			return false;
+
 		/* get kernel */
 		string cubin = compile_kernel();
 
diff --git a/intern/cycles/device/device_multi.cpp b/intern/cycles/device/device_multi.cpp
index 128c80ac396..fc5348ad168 100644
--- a/intern/cycles/device/device_multi.cpp
+++ b/intern/cycles/device/device_multi.cpp
@@ -132,10 +132,10 @@ public:
 		return desc.str();
 	}
 
-	bool load_kernels()
+	bool load_kernels(bool experimental)
 	{
 		foreach(SubDevice& sub, devices)
-			if(!sub.device->load_kernels())
+			if(!sub.device->load_kernels(experimental))
 				return false;
 
 		return true;
diff --git a/intern/cycles/device/device_opencl.cpp b/intern/cycles/device/device_opencl.cpp
index d783ae6c174..8eaaebc6629 100644
--- a/intern/cycles/device/device_opencl.cpp
+++ b/intern/cycles/device/device_opencl.cpp
@@ -365,7 +365,7 @@ public:
 		return md5.get_hex();
 	}
 
-	bool load_kernels()
+	bool load_kernels(bool experimental)
 	{
 		/* verify if device was initialized */
 		if(!device_initialized) {
diff --git a/intern/cycles/render/session.cpp b/intern/cycles/render/session.cpp
index 73ac033623d..42b4a2bb7e4 100644
--- a/intern/cycles/render/session.cpp
+++ b/intern/cycles/render/session.cpp
@@ -410,7 +410,7 @@ void Session::run()
 	/* load kernels */
 	progress.set_status("Loading render kernels (may take a few minutes the first time)");
 
-	if(!device->load_kernels()) {
+	if(!device->load_kernels(params.experimental)) {
 		string message = device->error_message();
 		if(message == "")
 			message = "Failed loading render kernel, see console for errors";
diff --git a/intern/cycles/render/session.h b/intern/cycles/render/session.h
index 82c14227d03..ce7f420096a 100644
--- a/intern/cycles/render/session.h
+++ b/intern/cycles/render/session.h
@@ -43,6 +43,7 @@ public:
 	string output_path;
 
 	bool progressive;
+	bool experimental;
 	int samples;
 	int tile_size;
 	int min_size;
@@ -59,6 +60,7 @@ public:
 		output_path = "";
 
 		progressive = false;
+		experimental = false;
 		samples = INT_MAX;
 		tile_size = 64;
 		min_size = 64;
@@ -75,6 +77,7 @@ public:
 		&& output_path == params.output_path
 		/* && samples == params.samples */
 		&& progressive == params.progressive
+		&& experimental == params.experimental
 		&& tile_size == params.tile_size
 		&& min_size == params.min_size
 		&& threads == params.threads