| Commit message (Collapse) | Author | Age | Files | Lines |
|---|
| |
|
|
|
|
|
|
|
|
|
| |
Previously, we treated the entire UNIFORM file as if it had two elements:
One for direct things and one for indirect. This is substantially
different from how the old visitor code handled it where each element was
effectively its own uniform. This commit makes the NIR path more like the
old ir_visitor path where each uniform is separate. This should allow us
to more easily make decisions about what to push.
Reviewed-by: Kenneth Graunke <[email protected]>
|
| |
|
|
| |
Reviewed-by: Kenneth Graunke <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
| |
In the i965 backend, we want to be able to "pull apart" the uniforms and
push some of them into the shader through a different path. In order to do
this effectively, we need to know which variable is actually being referred
to by a given uniform load. Previously, it was completely flattened by
nir_lower_io which made things difficult. This adds more information to
the intrinsic to make this easier for us.
Reviewed-by: Kenneth Graunke <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Previously, there were four type_size() functions in play - the i965
compiler backend defined scalar and vec4 type_size() functions, and
nir_lower_io contained its own similar functions.
In fact, the i965 driver used nir_lower_io() and then looped over the
components using its own type_size - meaning both were in play. The
two are /basically/ the same, but not exactly in obscure cases like
subroutines and images.
This patch removes nir_lower_io's functions, and instead makes the
driver supply a function pointer. This gives the driver ultimate
flexibility in deciding how it wants to count things, reduces code
duplication, and improves consistency.
v2 (Jason Ekstrand):
- One side-effect of passing in a function pointer is that nir_lower_io is
now aware of and properly allocates space for image uniforms, allowing
us to drop hacks in the backend
Signed-off-by: Kenneth Graunke <[email protected]>
Reviewed-by: Jason Ekstrand <[email protected]>
v2 Reviewed-by: Kenneth Graunke <[email protected]>
|
| |
|
|
|
|
|
|
| |
I want to use C function pointers to these, and they don't use anything
in the visitor classes anyway.
Signed-off-by: Kenneth Graunke <[email protected]>
Reviewed-by: Jason Ekstrand <[email protected]>
|
| |
|
|
|
|
|
|
| |
This way they don't implicitly increment the uniforms variable and don't
have to be called in-sequence during uniform setup.
Reviewed-by: Francisco Jerez <[email protected]>
Reviewed-by: Kenneth Graunke <[email protected]>
|
| |
|
|
|
|
|
| |
The new name more accurately represents what it does: Set up a single vec4
uniform value.
Reviewed-by: Kenneth Graunke <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
On the older platforms where we don't have logical contexts preserving
state across batches, we emit the invariant state setup on every batch
using the brw_invariant_state atom. This includes the pipeline selection
which is cached with the introduction of
commit 0e0e23ef537c9add672ff322f34e129a07edc55e
Author: Jordan Justen <[email protected]>
Date: Wed Apr 22 11:43:50 2015 -0700
i965/state: Emit pipeline select when changing pipelines
However, we do not reset the cache between batches on context-less
platforms resulting in us not setting the pipeline selection and can
cause GPU hangs if a media pipelined was loaded in the meantime (e.g.
mixing mplayer/gstreamer using libva and gnome-shell). A simple solution
is to just forcibly re-emit the pipeline select along with the invariant
state and reset the cache at that point.
Reported-and-tested-by: Tomasz C. <[email protected]>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=91254
Signed-off-by: Chris Wilson <[email protected]>
Cc: Jordan Justen <[email protected]>
Cc: Kenneth Graunke <[email protected]>
Reviewed-by: Jordan Justen <[email protected]>
Cc: "10.6 11.0" <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
When the edge flag element is enabled then the elements are slightly
reordered so that the edge flag is always the last one. This was
confusing the code to upload the 3DSTATE_VF_INSTANCING state because
that is uploaded with a separate loop which has an instruction for
each element. The indices used in these instructions weren't taking
into account the reordering so the state would be incorrect.
v2: Use nr_elements instead of brw->vb.nr_enabled so that it will cope
when gl_VertexID is used.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=91292
Cc: <[email protected]>
Reviewed-by: Ben Widawsky <[email protected]>
Signed-off-by: Ben Widawsky <[email protected]>
Tested-by: Mark Janes <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The edge flag data on Gen6+ is passed through the fixed function hardware as
an extra attribute. According to the PRM it must be the last valid
VERTEX_ELEMENT structure. However if the vertex ID is also used then another
extra element is added to source the VID. This made it so the vertex ID is in
the wrong register in the vertex shader and the edge attribute is no longer in
the last element.
v2: Also implement for BDW+
v3 [by Ben]: Remove 10.5 tag. Too late.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=84677
Cc: <[email protected]>
Reviewed-by: Kristian Høgsberg <[email protected]>
Signed-off-by: Ben Widawsky <[email protected]>
Tested-by: Ben Widawsky <[email protected]>
Tested-by: Mark Janes <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The nv_conditional_render piglits were sporadically failing. Moving
the control flush from the write and placing it just before the read
was sufficient to make the piglits pass a 1000/1000 times. The bspec
says that the flush enable bit "waits until all previous writes of
immediate data from post sync circles are complete before executing the
next command" - the operative word being previous!
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=90691
Signed-off-by: Chris Wilson <[email protected]>
Cc: Neil Roberts <[email protected]>
Cc: Kenneth Graunke <[email protected]>
Reviewed-by: Kenneth Graunke <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Shader-db results for vec4 on i965:
total instructions in shared programs: 1499894 -> 1502261 (0.16%)
instructions in affected programs: 1414224 -> 1416591 (0.17%)
helped: 2434
HURT: 10543
GAINED: 1
LOST: 0
Shader-db results for vec4 on g4x:
total instructions in shared programs: 1437411 -> 1439779 (0.16%)
instructions in affected programs: 1362402 -> 1364770 (0.17%)
helped: 2434
HURT: 10544
GAINED: 0
LOST: 0
Shader-db results for vec4 on Iron Lake:
total instructions in shared programs: 1437214 -> 1439593 (0.17%)
instructions in affected programs: 1362205 -> 1364584 (0.17%)
helped: 2433
HURT: 10544
GAINED: 1
LOST: 0
Shader-db results for vec4 on Sandy Bridge:
total instructions in shared programs: 2022092 -> 1941570 (-3.98%)
instructions in affected programs: 1886838 -> 1806316 (-4.27%)
helped: 7510
HURT: 10737
GAINED: 0
LOST: 0
Shader-db results for vec4 on Ivy Bridge:
total instructions in shared programs: 1853749 -> 1804960 (-2.63%)
instructions in affected programs: 1686736 -> 1637947 (-2.89%)
helped: 6735
HURT: 11101
GAINED: 0
LOST: 0
Shader-db results for vec4 on Haswell:
total instructions in shared programs: 1853749 -> 1804960 (-2.63%)
instructions in affected programs: 1686736 -> 1637947 (-2.89%)
helped: 6735
HURT: 11101
GAINED: 0
LOST: 0
Signed-off-by: Jason Ekstrand <[email protected]>
Acked-by: Kenneth Graunke <[email protected]>
Acked-by: Matt Turner <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
I pushed a half-baked version of "i965: handle nir_intrinsic_image_size" by
accident. Not having the Reviewed-by: tags on the last two commits should
have been a red flag but I somehow missed it after the QA check.
This patch should fix image-size for non-int images. I will add support to
the piglit test for all the other image types.
Sorry for the noise.
Signed-off-by: Martin Peres <[email protected]>
Reviewed-by: Francisco Jerez <[email protected]>
|
| |
|
|
| |
Signed-off-by: Martin Peres <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
v2, Review from Francisco Jerez:
- avoid the camelCase for the booleans
- init the booleans using the sampler type
- force the initialization of all the components of the output register
v3:
- Rename a variable from CubeMapArray to CubeArray to re-use GLSL's name (Ilia)
- Fix some indentation and drop parenthesis (Topi)
- Fix a signed/unsigned comparaison warning
Signed-off-by: Martin Peres <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
user.
The spec requires that all layers of the image starting from the 0-th
are bound to the image unit regardless of the Layer parameter when
Layered is true, so I was setting gl_image_unit::Layer to zero in that
case for the convenience of the driver back-end. However the
ES31-CTS.shader_image_load_store.basic-api-bind conformance test
checks that the layer value returned by glGetInteger is the same that
was originally specified, regardless of the value of layered. Rename
Layer to _Layer as is usual for other derived state and keep track of
the original layer value as gl_image_unit::Layer.
Reviewed-by: Ian Romanick <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
MaxCombinedShaderOutputResources.
The name of both the GLSL built-in variable and the glGetInteger param
with the same value changed in GLSL ES 3.1 and GL 4.5. Its semantics
also changed slightly, since the limit now also takes into account the
number of SSBs in use. Switch our internal data structures to the
up-to-date name.
Reviewed-by: Timothy Arceri <[email protected]>
Reviewed-by: Ian Romanick <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
When gl_VertexID or gl_InstanceID is used a 3DSTATE_VF_SGVS
instruction is sent to create a sort of element to store the generated
values. The last instruction in this chunk of code looks like it was
trying to set the instancing state for the element using the
3DSTATE_VF_INSTANCING instruction. However it was sending
brw->vb.nr_buffers instead of the element index. This instruction is
supposed to take an element index and that is how it is used further
down in the function so the previous code looks wrong. Perhaps
previously the number of buffers coincidentally matched the number of
enabled elements so the value was generally correct anyway. In a
subsequent patch I want to change a bit how it chooses the SGVS
element index so this needs to be fixed.
v2 [by Ben]
Remove stable 10.5 stable tag (it's too late now)
Commit update as follows:
The number of vertex buffers emitted is always <= the number of vertex elements.
To maximize reuse (actually, to minimize relocations - according to the code
comments), a vertex buffer is only emitted once, even when we setup multiple
components (3DSTATE_VERTEX_ELEMENT) from that buffer. This meant that the
previous code would use the wrong indexed element for these reuse cases. This
patch by itself prevents hangs on BSW in the linked bug. It doesn't make the
test pass, the remaining patches are needed for that.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=91610
Signed-off-by: Ben Widawsky <[email protected]>
Reviewed-by: Ben Widawsky <[email protected]>
Tested-by: Mark Janes <[email protected]>
Cc: <[email protected]>
|
| |
|
|
|
|
|
|
|
| |
Since i965 is now using make_reg_conflicts_transitive and doesn't need
q-value computations, they are disabled on i965. They are enabled
everywhere else so that they get the old behavior. This reduces the time
spent in eglInitialize() on BDW by around 10-15%.
Reviewed-by: Eric Anholt <[email protected]>
|
| |
|
|
|
|
|
|
|
|
| |
Instead of adding transitive conflicts as we go, we now add regular
conflicts and them make them all transitive at the end. This reduces
screen creation time substantially on BDW. The time spent in eglInitialize
is reduced from 27.78 ms/call to 9.92 ms/call in debug mode and from 13.15
ms/call to 4.54 ms/call in release mode (about 65% in either case).
Reviewed-by: Eric Anholt <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
Appears to fix shader compilation. Tested by starting the client and observing
that the screen was correct after the trailers ran when previously, it was
blank. Play tested on amd64.
This was suggested by "Kuuchan" on the Steam forums:
https://steamcommunity.com/app/200390/discussions/0/540731690861139279/?insideModal=1#c594820656479479870
Acked-by: Matt Turner <[email protected]>
Signed-off-by: Richard Yao <[email protected]>
|
| |
|
|
|
|
|
|
|
|
| |
mesa/src/mesa/drivers/dri/i965/gen7_sol_state.c: In function 'gen7_upload_3dstate_so_decl_list':
mesa/src/mesa/drivers/dri/i965/gen7_sol_state.c:119:22: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (int i = 0; i < linked_xfb_info->NumOutputs; i++) {
^
Signed-off-by: Rhys Kidd <[email protected]>
Reviewed-by: Thomas Helland <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
mesa/src/mesa/drivers/dri/i965/gen6_vs_state.c: In function 'gen6_upload_push_constants':
mesa/src/mesa/drivers/dri/i965/gen6_vs_state.c:85:21: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (i = 0; i < prog_data->nr_params; i++) {
^
mesa/src/mesa/drivers/dri/i965/gen6_vs_state.c:92:17: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (i = 0; i < prog_data->nr_params; i++) {
^
Signed-off-by: Rhys Kidd <[email protected]>
Reviewed-by: Thomas Helland <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
mesa/src/mesa/drivers/dri/i965/brw_vs_surface_state.c: In function 'brw_upload_pull_constants':
mesa/src/mesa/drivers/dri/i965/brw_vs_surface_state.c:84:18: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (i = 0; i < prog_data->nr_pull_params; i++) {
^
mesa/src/mesa/drivers/dri/i965/brw_vs_surface_state.c:89:21: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (i = 0; i < ALIGN(prog_data->nr_pull_params, 4) / 4; i++) {
^
Signed-off-by: Rhys Kidd <[email protected]>
Reviewed-by: Thomas Helland <[email protected]>
|
| |
|
|
|
|
|
|
|
|
| |
mesa/src/mesa/drivers/dri/i965/brw_wm_surface_state.c: In function 'brw_upload_abo_surfaces':
mesa/src/mesa/drivers/dri/i965/brw_wm_surface_state.c:961:22: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (int i = 0; i < prog->NumAtomicBuffers; i++) {
^
Signed-off-by: Rhys Kidd <[email protected]>
Reviewed-by: Thomas Helland <[email protected]>
|
| |
|
|
|
|
|
|
|
|
| |
mesa/src/mesa/drivers/dri/i965/brw_wm_surface_state.c: In function 'brw_upload_ubo_surfaces':
mesa/src/mesa/drivers/dri/i965/brw_wm_surface_state.c:901:22: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (int i = 0; i < shader->NumUniformBlocks; i++) {
^
Signed-off-by: Rhys Kidd <[email protected]>
Reviewed-by: Thomas Helland <[email protected]>
|
| |
|
|
|
|
|
|
|
|
| |
mesa/src/mesa/drivers/dri/i965/brw_tex_layout.c: In function 'brw_miptree_layout_texture_array':
mesa/src/mesa/drivers/dri/i965/brw_tex_layout.c:560:25: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (int q = 0; q < mt->level[level].depth; q++) {
^
Signed-off-by: Rhys Kidd <[email protected]>
Reviewed-by: Thomas Helland <[email protected]>
|
| |
|
|
|
|
|
|
|
|
| |
mesa/src/mesa/drivers/dri/i965/brw_state_cache.c: In function 'brw_try_upload_using_copy':
mesa/src/mesa/drivers/dri/i965/brw_state_cache.c:216:18: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (i = 0; i < cache->size; i++) {
^
Signed-off-by: Rhys Kidd <[email protected]>
Reviewed-by: Thomas Helland <[email protected]>
|
| |
|
|
|
|
|
|
|
|
| |
mesa/src/mesa/drivers/dri/i965/brw_primitive_restart.c: In function 'can_cut_index_handle_prims':
mesa/src/mesa/drivers/dri/i965/brw_primitive_restart.c:94:22: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (int i = 0; i < nr_prims; i++) {
^
Signed-off-by: Rhys Kidd <[email protected]>
Reviewed-by: Thomas Helland <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
mesa/src/mesa/drivers/dri/i965/brw_draw_upload.c: In function 'brw_prepare_vertices':
mesa/src/mesa/drivers/dri/i965/brw_draw_upload.c:434:22: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (i = j = 0; i < brw->vb.nr_enabled; i++) {
^
mesa/src/mesa/drivers/dri/i965/brw_draw_upload.c:557:17: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (i = 0; i < nr_uploads; i++) {
^
mesa/src/mesa/drivers/dri/i965/brw_draw_upload.c:569:18: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (i = 0; i < nr_uploads; i++) {
^
Signed-off-by: Rhys Kidd <[email protected]>
Reviewed-by: Thomas Helland <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
mesa/src/mesa/drivers/dri/i965/brw_draw.c: In function 'brw_draw_destroy':
mesa/src/mesa/drivers/dri/i965/brw_draw.c:630:18: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (i = 0; i < brw->vb.nr_buffers; i++) {
^
mesa/src/mesa/drivers/dri/i965/brw_draw.c:636:18: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (i = 0; i < brw->vb.nr_enabled; i++) {
^
Signed-off-by: Rhys Kidd <[email protected]>
Reviewed-by: Thomas Helland <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
mesa/src/mesa/drivers/dri/i965/intel_screen.c: In function 'intel_screen_make_configs':
mesa/src/mesa/drivers/dri/i965/intel_screen.c:1222:22: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (int i = 0; i < ARRAY_SIZE(formats); i++) {
^
mesa/src/mesa/drivers/dri/i965/intel_screen.c:1259:22: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (int i = 0; i < ARRAY_SIZE(formats); i++) {
^
mesa/src/mesa/drivers/dri/i965/intel_screen.c:1291:22: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (int i = 0; i < ARRAY_SIZE(formats); i++) {
^
Signed-off-by: Rhys Kidd <[email protected]>
Reviewed-by: Thomas Helland <[email protected]>
|
| |
|
|
|
|
|
|
|
|
| |
mesa/src/mesa/drivers/dri/i965/intel_fbo.c: In function 'intel_validate_framebuffer':
mesa/src/mesa/drivers/dri/i965/intel_fbo.c:734:18: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (i = 0; i < ARRAY_SIZE(fb->Attachment); i++) {
^
Signed-off-by: Rhys Kidd <[email protected]>
Reviewed-by: Thomas Helland <[email protected]>
|
| |
|
|
|
|
|
|
|
|
| |
mesa/src/mesa/drivers/dri/common/utils.c: In function 'driGetConfigAttrib':
mesa/src/mesa/drivers/dri/common/utils.c:457:19: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (i = 0; i < ARRAY_SIZE(attribMap); i++)
^
Signed-off-by: Rhys Kidd <[email protected]>
Reviewed-by: Thomas Helland <[email protected]>
|
| |
|
|
|
|
|
|
|
|
| |
mesa/src/mesa/drivers/dri/i965/intel_screen.c: In function 'aub_dump_bmp':
mesa/src/mesa/drivers/dri/i965/intel_screen.c:125:22: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (int i = 0; i < fb->_NumColorDrawBuffers; i++) {
^
Signed-off-by: Rhys Kidd <[email protected]>
Reviewed-by: Thomas Helland <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
| |
mesa/src/mesa/drivers/dri/i965/intel_fbo.c: In function 'intel_blit_framebuffer_with_blitter':
mesa/src/mesa/drivers/dri/i965/intel_fbo.c:836:21: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (i = 0; i < drawFb->_NumColorDrawBuffers; i++) {
^
V2 (Thomas Helland):
-Use unsigned instead of GLuint (trivial)
Signed-off-by: Rhys Kidd <[email protected]>
Reviewed-by: Thomas Helland <[email protected]>
|
| |
|
|
|
|
|
|
|
|
| |
mesa/src/mesa/drivers/dri/i965/brw_wm_state.c: In function 'brw_color_buffer_write_enabled':
mesa/src/mesa/drivers/dri/i965/brw_wm_state.c:53:18: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (i = 0; i < ctx->DrawBuffer->_NumColorDrawBuffers; i++) {
^
Signed-off-by: Rhys Kidd <[email protected]>
Reviewed-by: Thomas Helland <[email protected]>
|
| |
|
|
|
|
|
|
|
|
| |
mesa/src/mesa/drivers/dri/i965/brw_draw.c: In function 'brw_postdraw_set_buffers_need_resolve':
mesa/src/mesa/drivers/dri/i965/brw_draw.c:390:22: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
for (int i = 0; i < fb->_NumColorDrawBuffers; i++) {
^
Signed-off-by: Rhys Kidd <[email protected]>
Reviewed-by: Thomas Helland <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
| |
If an immediate is written to multiple channels, we can load it in a
single writemasked MOV.
total instructions in shared programs: 6285144 -> 6261991 (-0.37%)
instructions in affected programs: 718991 -> 695838 (-3.22%)
helped: 5762
Reviewed-by: Jason Ekstrand <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
We do not want bug reports from this early stepping of SKL. Few if any were ever
shipped outside of Intel to early enabling partners, and none will be sold.
There is a functional change here. If you're using new mesa on an old
kernel/libdrm, the revid will be -1, and we'll use new SKL values instead of
early ones (a hopefully irrelevant improvement IMO).
v2: Remove hunk which warned before dying. Instead, default to normal SKL
support (Ken)
Signed-off-by: Ben Widawsky <[email protected]>
Reviewed-by: Kenneth Graunke <[email protected]>
Reviewed-by: Neil Roberts <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Items in the program cache consist of three things: key, the data
representing the instructions and auxiliary data representing
uniform storage. The data consisting of instructions is stored into
a drm buffer object while the key and the auxiliary data reside in
malloced section. Now the cache uploading is equipped with a check
that iterates over existing items and seeks to find a another item
using identical instruction data than the one being just uploaded.
If such is found there is no need to add another section into the
drm buffer object holding identical copy of the existing one. The
item just being uploaded should instead simply point to the same
offset in the underlying drm buffer object.
Unfortunately the check for the matching instruction data is
coupled with a check for matching auxiliary data also. This
effectively prevents the cache from ever containing two items
that could share a section in the drm buffer object.
The constraint for the instruction data and auxiliary data to
match is, fortunately, unnecessary strong. When items are stored
into the cache they will anyway contain their own copy of the
auxiliary data (even if they matched - which they in real world
never will). The only thing the items would be sharing is the
instruction data and hence we should only check for that to match
and nothing else.
No piglit regression in jenkins.
Reviewed-by: Kenneth Graunke <[email protected]>
Signed-off-by: Topi Pohjolainen <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
| |
Current logic re-writes the same data when existing data is found.
Not that this actually matters at the moment in practice, the
contraint for finding matching data is too severe to ever allow
data to be shared between two items in the cache.
Reviewed-by: Anuj Phogat <[email protected]>
Reviewed-by: Kenneth Graunke <[email protected]>
Signed-off-by: Topi Pohjolainen <[email protected]>
|
| |
|
|
|
|
|
|
|
|
| |
and simplify the interface to take directly the size and to return
the offset. The routine does nothing more than allocate, it doesn't
upload anything.
Reviewed-by: Anuj Phogat <[email protected]>
Reviewed-by: Kenneth Graunke <[email protected]>
Signed-off-by: Topi Pohjolainen <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
Shader-db results for vec4 programs using NIR on HSW:
total instructions in shared programs: 1838157 -> 1828469 (-0.53%)
instructions in affected programs: 275978 -> 266290 (-3.51%)
helped: 2827
HURT: 244
GAINED: 0
LOST: 0
Reviewed-by: Matt Turner <[email protected]>
Reviewed-by: Eduardo Lima Mitev <[email protected]>
|
| |
|
|
|
|
|
|
|
|
| |
Cuts about 2k of .text.
text data bss dec hex filename
5017141 197160 27672 5241973 4ffc75 i965_dri.so before
5014981 197160 27672 5239813 4ff405 i965_dri.so after
Reviewed-by: Kenneth Graunke <[email protected]>
|
| |
|
|
|
|
|
|
|
|
| |
Cuts about 1k of .text.
text data bss dec hex filename
5018165 197160 27672 5242997 500075 i965_dri.so before
5017141 197160 27672 5241973 4ffc75 i965_dri.so after
Reviewed-by: Kenneth Graunke <[email protected]>
|
| |
|
|
|
| |
Reviewed-by: Paul Berry <[email protected]>
Reviewed-by: Jason Ekstrand <[email protected]>
|
| |
|
|
|
|
|
|
|
|
|
| |
This fixes the spec@arb_shader_image_load_store@invalid index bounds
piglit tests on IVB, which were causing a GPU hang and then a crash
due to the invalid binding table index result of the array index
calculation. Other generations seem to behave sensibly when an
invalid surface is provided so it doesn't look like we need to care.
Reviewed-by: Jordan Justen <[email protected]>
Reviewed-by: Chris Forbes <[email protected]>
|
| |
|
|
|
|
| |
v2: Move array coordinate workaround into the surface builder.
Reviewed-by: Jason Ekstrand <[email protected]>
|
| |
|
|
|
|
| |
v2: Move the image_params array back to brw_stage_prog_data.
Reviewed-by: Jason Ekstrand <[email protected]>
|
