Cycles: Metal integrator state size tuning

This patch tunes the integrator state sizing for Metal (`num_concurrent_states` and `num_concurrent_busy_states`).

On all GPUs architecture, we adjust the busy:total states ratio to be 1:4 which gives better rendering performance than the previous 1:16 ratio (independent of total state count). This gives a small performance uplift (e.g. 2-3% on M1 Ultra).

Additionally for M2 architectures, we double the overall state size if there is available headroom. Inclusive of the first change, we can expect uplift of close to 10% in future, as this results in larger dispatch sizes and minimises work submission overheads. In order to make an accurate determination of available headroom, we defer the calculation of `num_concurrent_states` and `num_concurrent_busy_states` until the time of integrator state allocation (i.e. after all of the scene data has been allocated). We also refactor `alloc_integrator_soa` to calculate an *exact* single-state-size in a first pass, right before allocating the integrator SoA buffers in a second pass.

Reviewed By: brecht

Differential Revision: https://developer.blender.org/D16313

1 files changed, 1 insertions, 1 deletions

diff --git a/intern/cycles/device/queue.h b/intern/cycles/device/queue.h
index 1d6a8d736b7..e27e081a407 100644
--- a/intern/cycles/device/queue.h
+++ b/intern/cycles/device/queue.h
@@ -103,7 +103,7 @@ class DeviceQueue {
   /* Number of states which keeps the device occupied with work without losing performance.
    * The renderer will add more work (when available) when number of active paths falls below this
    * value. */
-  virtual int num_concurrent_busy_states() const = 0;
+  virtual int num_concurrent_busy_states(const size_t state_size) const = 0;
 
   /* Number of elements in a partition of sorted shaders, that improves memory locality of
    * integrator state fetch at the cost of decreased coherence for shader kernel execution. */