Confirmed users
753
edits
Platform/GFX/DeferredGPUs: Difference between revisions
no edit summary
No edit summary |
|||
| Line 108: | Line 108: | ||
== Overdraw is still expensive on tbd-rast GPUs == | == Overdraw is still expensive on tbd-rast GPUs == | ||
= | = Other performance pitfalls (not related to "deferred") = | ||
Here are some other performance pitfalls on mobile GPUS: | |||
= | == Use only triangle strips == | ||
Reason: Adreno 200's have a vertex cache size of 2. | |||
== Make sure that our framebuffer's bit depth matches the hardware framebuffer's == | |||
Or else we'll get inefficient conversions between 16bpp and 32bpp. The pitfall here is typically we may be requesting FBConfigs with ''at least'' 16bpp and blindly taking the first returned one, which may actually be 32bpp. | |||
== Avoid MakeCurrent's == | |||
The Adreno 200 document lists it as very expensive. On B2G at least we should be able to land {{bug|749678}}. | |||