v2:
* Don't rely on brw_eu* to generate the send instruction. We now
generate the send here, and drop the "i965/cs: Add support for the
SEND message that terminates a CS thread" brw_eu* patch.
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
v2:
* Do more work at the visitor level. g0 is loaded and sent to the
generator now.
v3:
* Use Ken's comment explaining g0 usage
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
At the moment it's not wired up to anything. Later patches will hook
it up to the compute shader back-end.
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Kristian Høgsberg <krh@bitplanet.net>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Also add code to brw_upload_state to set it when the compute program
changes.
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Kristian Høgsberg <krh@bitplanet.net>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
If a send message is emitted with a message length that is less than
required for the message then the remaining parameters default to
zero. We can take advantage of this to save a register when a shader
passes constant zeroes as the final coordinates to the sample
function.
I think this might be useful for GLES applications that are using 2D
textures to simulate 1D textures.
On Skylake it will be useful for shaders that do
texelFetch(tex,something,0) which I think is fairly common. This helps
more on Skylake because in that case the order of the instruction
operands are u,v,lod,r which is good for 2D textures whereas before
they were u,lod,v,r which is only good for 1D textures.
On Haswell:
total instructions in shared programs: 8535730 -> 8533261 (-0.03%)
instructions in affected programs: 236968 -> 234499 (-1.04%)
helped: 1174
On Skylake:
total instructions in shared programs: 10345646 -> 10341237 (-0.04%)
instructions in affected programs: 293011 -> 288602 (-1.50%)
helped: 1218
Reviewed-by: Matt Turner <mattst88@gmail.com>
v2: Applied suggestions by Kenneth Graunke:
- Only apply on Gen5+
- Apply to all texture opcodes, not just TEX and TXF.
Moved the optimisation into the loop as suggested by Matt Turner.
Fix the array index when there is a header.
On Gen9+ there needs to be a header when sampling using SIMD4x2. The
header is set up by copying from the g0 register. Commit 07c571a39f
tried to fix this mov instruction to always use an exec size of 8
because previously it was incorrectly using 4. It did this by casting
the type of the destination register to vec8. This was done because
there is code in brw_set_dest to guess the exec size based on the
width of the dest register. However I misunderstood how this works
because it is actually only used when the width is less than 8. That
means the patch actually changed it to use the default exec size which
on SIMD16 would be 16 and the MOV would clobber over the first
register in the send message. This patch makes it additionally set the
default exec size to 8. This is similar to how the message is set up
in fs_generator::generate_tex.
I think this wasn't picked up by any Piglit tests because we don't
have any fragment shaders that hit this code path so nothing was using
SIMD16. However the patch caused failures in deqp tests.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=90153
Reviewed-by: Matt Turner <mattst88@gmail.com>
Tested-by: Tapani Pälli <tapani.palli@intel.com>
The stage_abbrev and stage_name fields in backend_visitor provide what
we need without any additional effort. It also means we'll get the
right names for compute shaders, SIMD8 geometry shaders, and both kinds
of tessellation shaders.
This does unfortunately change the capitalization of the stage
abbreviation in the INTEL_DEBUG=optimizer output filenames. It doesn't
seem worth adding code to handle, though.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Anuj Phogat <anuj.phogat@gmail.com>
v2: - move interop.cpp to clover/api
- change intptr_t to void* in the interface
- add a virtual function fence() to simplify some code
v3: - use bool in the interface
v4: - enclose the last two interop functions in try..catch
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
src1 would contain the predicate, which would get emitted as a register
source by an undiscerning srcId helper. Work around this in the same way
as in emitTEX.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: mesa-stable@lists.freedesktop.org
This was causing src0 to always have the absolute value flag set.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: mesa-stable@lists.freedesktop.org
Original blorp writes only one buffer per shader invocation. Once
the launch mechanism is shared with glsl-based programs there will
be need for supporting multiple render targets.
Also drop the always constant color write disable settings.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Signed-off-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Note that the magic number of one in gen7 logic is replaced by
BRW_SF_URB_ENTRY_READ_OFFSET ( == 1 also) for clarity.
On gen6 the change from zero to one (BRW_SF_URB_ENTRY_READ_OFFSET)
has no effect for native blorp as blorp doesn't use any
additional attributes. In fact, regular pipeline setup always
uses BRW_SF_URB_ENTRY_READ_OFFSET even when there are no additional
attributes. Hence the change makes the two (blorp and regular)
consistent.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Signed-off-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
This was still needed when we had support for blorp clears but now
this is fixed to nop.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Signed-off-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
v2: Use SET_FIELD() for sampler count, and for that reason
added GEN7_PS_SAMPLER_COUNT_MASK.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Signed-off-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Now the uploading depends only on the input parameters instead
of consulting the current gl-state.
v2: Rebased on top of sampler count clamping
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Signed-off-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
v2 (Matt): Moved * to the name.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Signed-off-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Read and write parts of the state stage are also split into
explicit arguments allowing future patches to use constant
program data.
v2 (Ken): s/BRW_NEW_WM_PROG_DATA/BRW_NEW_FS_PROG_DATA/
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Signed-off-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Note that brw_update_renderbuffer_surfaces() already had a helper
variable which was used in parallel to direct access of the current
draw buffer of the context.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Signed-off-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Notice that in gen7_wm_surface_state.c there is also indentation
change in the surrounding code removing tabs.
v2 (Matt): Fixed whitespace: tabs -> spaces
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Signed-off-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
The value is actually clamped to 0-16 as sample state pointer
can be used to support more than 16 samplers.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Signed-off-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
In response to another patch, Emil asked for some clarification how this
stuff works. Rather than just reply to the e-mail, I decided to update
the exlanation in the code.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Cc: Emil Velikov <emil.l.velikov@gmail.com>