diff options
author | Michael Jones <michael_p_jones@apple.com> | 2022-10-24 12:23:56 +0300 |
---|---|---|
committer | Michael Jones <michael_p_jones@apple.com> | 2022-10-24 19:14:33 +0300 |
commit | 8dd7b5b26b394207b5941d49750f7e3abadaf82a (patch) | |
tree | fe7425665e435667fc8977cce3b32919dffd9f67 /intern/cycles/device/queue.h | |
parent | 4c6e07230f76c21e67f0d5ef15464ca7d55c404a (diff) |
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
Diffstat (limited to 'intern/cycles/device/queue.h')
-rw-r--r-- | intern/cycles/device/queue.h | 2 |
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. */ |