i915: Emit a single relocation per vbo
Reducing the number of relocations has lots of nice knock-on effects, not least including reducing batch buffer size, auxilliary array sizes (vmalloced and copied into the kernel), processing of uncached relocations etc. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
This commit is contained in:
@@ -1422,6 +1422,10 @@ i915ValidateFragmentProgram(struct i915_context *i915)
|
||||
intel->vertex_attr_count,
|
||||
intel->ViewportMatrix.m, 0);
|
||||
|
||||
assert(intel->prim.current_offset == intel->prim.start_offset);
|
||||
intel->prim.start_offset = (intel->prim.current_offset + intel->vertex_size-1) / intel->vertex_size * intel->vertex_size;
|
||||
intel->prim.current_offset = intel->prim.start_offset;
|
||||
|
||||
intel->vertex_size >>= 2;
|
||||
|
||||
i915->state.Ctx[I915_CTXREG_LIS2] = s2;
|
||||
|
Reference in New Issue
Block a user