diff options
| author | Kenneth Graunke <kenneth@whitecape.org> | 2014-09-10 15:41:40 -0700 |
|---|---|---|
| committer | Ian Romanick <ian.d.romanick@intel.com> | 2014-09-12 16:35:35 -0700 |
| commit | 6b6145204dd4a1112f6e1fe10162636141495b79 (patch) | |
| tree | 30809a5f9ef2d22f67b7a3677e75c2025b81ee4f /src/mesa/drivers/dri/i965/brw_draw_upload.c | |
| parent | e980fe607155c79ccba56ef78854093b7730bef6 (diff) | |
| download | external_mesa3d-6b6145204dd4a1112f6e1fe10162636141495b79.zip external_mesa3d-6b6145204dd4a1112f6e1fe10162636141495b79.tar.gz external_mesa3d-6b6145204dd4a1112f6e1fe10162636141495b79.tar.bz2 | |
i965: Separate gl_InstanceID and gl_VertexID uploading.
We always uploaded them together, mostly out of laziness - both required
an additional vertex element. However, gl_VertexID now also requires an
additional vertex buffer for storing gl_BaseVertex; for non-indirect
draws this also means uploading (a small amount of) data. This is extra
overhead we don't need if the shader only uses gl_InstanceID.
In particular, our clear shaders currently use gl_InstanceID for doing
layered clears, but don't need gl_VertexID.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Cc: "10.3" <mesa-stable@lists.freedesktop.org>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Tested-by: Ian Romanick <ian.d.romanick@intel.com>
Diffstat (limited to 'src/mesa/drivers/dri/i965/brw_draw_upload.c')
| -rw-r--r-- | src/mesa/drivers/dri/i965/brw_draw_upload.c | 29 |
1 files changed, 22 insertions, 7 deletions
diff --git a/src/mesa/drivers/dri/i965/brw_draw_upload.c b/src/mesa/drivers/dri/i965/brw_draw_upload.c index d59ca8b..2162624 100644 --- a/src/mesa/drivers/dri/i965/brw_draw_upload.c +++ b/src/mesa/drivers/dri/i965/brw_draw_upload.c @@ -671,14 +671,16 @@ emit_vertex_buffer_state(struct brw_context *brw, static void brw_emit_vertices(struct brw_context *brw) { - GLuint i, nr_elements; + GLuint i; brw_prepare_vertices(brw); brw_prepare_shader_draw_parameters(brw); brw_emit_query_begin(brw); - nr_elements = brw->vb.nr_enabled + brw->vs.prog_data->uses_vertexid; + unsigned nr_elements = brw->vb.nr_enabled; + if (brw->vs.prog_data->uses_vertexid || brw->vs.prog_data->uses_instanceid) + ++nr_elements; /* If the VS doesn't read any inputs (calculating vertex position from * a state variable for some reason, for example), emit a single pad @@ -824,13 +826,26 @@ static void brw_emit_vertices(struct brw_context *brw) (BRW_VE1_COMPONENT_STORE_0 << BRW_VE1_COMPONENT_3_SHIFT)); } - if (brw->vs.prog_data->uses_vertexid) { + if (brw->vs.prog_data->uses_vertexid || brw->vs.prog_data->uses_instanceid) { uint32_t dw0 = 0, dw1 = 0; + uint32_t comp0 = BRW_VE1_COMPONENT_STORE_0; + uint32_t comp1 = BRW_VE1_COMPONENT_STORE_0; + uint32_t comp2 = BRW_VE1_COMPONENT_STORE_0; + uint32_t comp3 = BRW_VE1_COMPONENT_STORE_0; - dw1 = (BRW_VE1_COMPONENT_STORE_SRC << BRW_VE1_COMPONENT_0_SHIFT) | - (BRW_VE1_COMPONENT_STORE_0 << BRW_VE1_COMPONENT_1_SHIFT) | - (BRW_VE1_COMPONENT_STORE_VID << BRW_VE1_COMPONENT_2_SHIFT) | - (BRW_VE1_COMPONENT_STORE_IID << BRW_VE1_COMPONENT_3_SHIFT); + if (brw->vs.prog_data->uses_vertexid) { + comp0 = BRW_VE1_COMPONENT_STORE_SRC; + comp2 = BRW_VE1_COMPONENT_STORE_VID; + } + + if (brw->vs.prog_data->uses_instanceid) { + comp3 = BRW_VE1_COMPONENT_STORE_IID; + } + + dw1 = (comp0 << BRW_VE1_COMPONENT_0_SHIFT) | + (comp1 << BRW_VE1_COMPONENT_1_SHIFT) | + (comp2 << BRW_VE1_COMPONENT_2_SHIFT) | + (comp3 << BRW_VE1_COMPONENT_3_SHIFT); if (brw->gen >= 6) { dw0 |= GEN6_VE0_VALID | |