User override for the CPU local mem size

Added a new POCL_CPU_LOCAL_MEM_SIZE environment for overriding the
local memory size for the CPU devices.

Also added better error message for when total automatic local size
gets over the local memory size.

CHANGES

@@ -9,7 +9,7 @@ Notable User Facing Changes
 - Added support for generic address spaces in the CPU drivers
 - Added basic support for cl_khr_subgroups for CPUs: A single
   subgroup that always executes the whole X-dimension's WIs.
-- Added initial (incomplete) support for 
+- Added initial (incomplete) support for
   cl_intel_required_subgroup_size for CPUs
 - AlmaIF's OpenASIP backend now supports a standalone mode.
   It generates a standalone C program from a kernel launch, which
@@ -23,7 +23,9 @@ Notable User Facing Changes
   CBS is expected to work for kernels that POCL's current kernel compiler
   does not support. Currently, CBS can be manually enabled by setting
   the environment variable `POCL_WORK_GROUP_METHOD=cbs`.
-  
+- Added a new POCL_CPU_LOCAL_MEM_SIZE environment for overriding the
+  local memory size for the CPU devices.
+
 Notable Fixes
 -------------
 

doc/sphinx/source/using.rst

@@ -145,6 +145,11 @@ pocl.
  default cache directory will be used, which is ``$XDG_CACHE_HOME/pocl/kcache``
  (if set) or ``$HOME/.cache/pocl/kcache/`` on Unix-like systems.
 
+- **POCL_CPU_LOCAL_MEM_SIZE**
+
+ Set the local memory size of the CPU devices (pthread, basic) to the
+ given amount in bytes instead of the default one.
+
 - **POCL_DEBUG**
 
  Enables debug messages to stderr. This will be mostly messages from error

lib/CL/devices/basic/basic.c

@@ -247,9 +247,9 @@ pocl_basic_init (unsigned j, cl_device_id device, const char* parameters)
 #endif
 
   /* hwloc probes OpenCL device info at its initialization in case
-     the OpenCL extension is enabled. This causes to printout 
+     the OpenCL extension is enabled. This causes to printout
      an unimplemented property error because hwloc is used to
-     initialize global_mem_size which it is not yet. Just put 
+     initialize global_mem_size which it is not yet. Just put
      a nonzero there for now. */
   device->global_mem_size = 1;
   err = pocl_topology_detect_device_info(device);
@@ -266,6 +266,9 @@ pocl_basic_init (unsigned j, cl_device_id device, const char* parameters)
   pocl_cpuinfo_detect_device_info(device);
   pocl_set_buffer_image_limits(device);
 
+  device->local_mem_size = pocl_get_int_option ("POCL_CPU_LOCAL_MEM_SIZE",
+                                                device->local_mem_size);
+
   if (device->vendor_id == 0)
     device->vendor_id = CL_KHRONOS_VENDOR_ID_POCL;
 

lib/CL/devices/pthread/pthread.c

@@ -222,6 +222,9 @@ pocl_pthread_init (unsigned j, cl_device_id device, const char* parameters)
   pocl_cpuinfo_detect_device_info(device);
   pocl_set_buffer_image_limits(device);
 
+  device->local_mem_size = pocl_get_int_option ("POCL_CPU_LOCAL_MEM_SIZE",
+                                                device->local_mem_size);
+
   /* in case hwloc doesn't provide a PCI ID, let's generate
      a vendor id that hopefully is unique across vendors. */
   const char *magic = "pocl";

lib/CL/devices/pthread/pthread_utils.c

@@ -235,9 +235,21 @@ setup_kernel_arg_array_with_locals (void **arguments, void **arguments2,
           size_t size = meta->local_sizes[i];
           arguments[j] = &arguments2[j];
           arguments2[j] = start;
+          if ((size_t)(start - local_mem + size) > local_mem_size)
+            {
+              size_t total_auto_local_size = 0;
+              for (i = 0; j < meta->num_locals; ++j)
+                {
+                  total_auto_local_size += meta->local_sizes[j];
+                }
+              POCL_ABORT (
+                  "PoCL detected an OpenCL program error: "
+                  "%d automatic local buffer(s) with total size %lu "
+                  "bytes doesn't fit to the local memory of size %lu\n",
+                  meta->num_locals, total_auto_local_size, local_mem_size);
+            }
           start += size;
           start = align_ptr (start);
-          assert ((size_t)(start - local_mem) <= local_mem_size);
         }
     }
 }