fuos
The memory pool is a RAM pool OR buffer to stream data to the GPU, it's not the total device memory to use. To see more info:
hconfig -H HOUDINI_OCL_MEMORY_POOL_SIZE
HOUDINI_OCL_MEMORY_POOL_SIZE
Houdini uses a memory pool for allocating device memory through
OpenCL for improved performance and to decrease fragmentation. This
variable is the percentage of total device memory to allocate for
the pool. For example, the default setting of 0.125 will allocate
1/8 of device memory for the memory pool. Note that if the specified
OpenCL device is 32-bit, the total device memory is clamped to 4GB
before being multiplied by this percentage.
Thx Fuos,
this is my reported OpenCL hgpuinfo.exe:
OpenCL Platform NVIDIA CUDA
Platform Vendor NVIDIA Corporation
Platform Version OpenCL 1.2 CUDA 10.0.132
OpenCL Device GeForce RTX 2070
OpenCL Type GPU
Device Version OpenCL 1.2 CUDA
Frequency 1725 MHz
Compute Units 36
Device Address Bits 64
Global Memory 8192 MB
Max Allocation 2048 MB
Global Cache 576 KB
Max Constant Args 9
Max Constant Size 64 KB
Local Mem Size 48 KB
2D Image Support 32768x32768
3D Image Support 16384x16384x16384
Max allocation is reported as 2048GB and I think this is what confused me, but you are right, once I added:
HOUDINI_OCL_REPORT_MEMORY_USE = 1
and checked the console while simming I could read: total memory allocated values higher than 4096.
Thanks for the heads up!
Cheers,