| Commit message (Collapse) | Author | Age | Files | Lines |
|
|
|
|
| |
Reviewed-by: Roland Scheidegger <[email protected]>
Reviewed-by: Neha Bhende <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
ARB_gl_spirv adds the ability to use SPIR-V binaries, and a new
method, glSpecializeShader. Here we add a new function to do the
validation for this function:
From OpenGL 4.6 spec, section 7.2.1"
"Shader Specialization", error table:
INVALID_VALUE is generated if <pEntryPoint> does not name a valid
entry point for <shader>.
INVALID_VALUE is generated if any element of <pConstantIndex>
refers to a specialization constant that does not exist in the
shader module contained in <shader>.""
v2: rebase update (spirv_to_nir options added, changes on the warning
logging, and others)
v3: include passing options on common initialization, doesn't call
setjmp on common_initialization
v4: (after Jason comments):
* Rename common_initialization to vtn_builder_create
* Move validation method and their helpers to own source file.
* Create own handle_constant_decoration_cb instead of reuse existing one
v5: put vtn_build_create refactoring to their own patch (Jason)
v6: update after vtn_builder_create method renamed, add explanatory
comment, tweak existing comment and commit message (Timothy)
|
|
|
|
|
|
|
|
|
| |
Refactored from spirv_to_nir, in order to be reused later.
Reviewed-by: Timothy Arceri <[email protected]>
v2: renamed method (from vtn_builder_create), add explanatory comment
(Timothy)
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Future changes will add generated files used only from
src/compiler/glsl. These can't be built from Makefile.nir.am, and we
can't move all the rules from Makefile.nir.am to Makefile.spirv.am (and
it would be silly anyway).
v2: Do it for meson too.
Signed-off-by: Ian Romanick <[email protected]>
Reviewed-by: Eric Engestrom <[email protected]> (the meson bits)
Reviewed-by: Alejandro Piñeiro <[email protected]> (the automake bits)
|
|
|
|
|
|
|
|
| |
This slightly simplifies later changes that add more Makefile.*.am
files.
Signed-off-by: Ian Romanick <[email protected]>
Reviewed-by: Eduardo Lima Mitev <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Previously bitset.h would include u_math.h to get bitscan.h. u_math.h
lives in src/gallium/auxiliary/util while both bitset.h and bitscan.h
live in src/util. Having the one file directly include another file
that lives in the same directory makes much more sense.
As a side-effect, several files need to directly include standard header
files that were previously indirectly included.
v2: Fix build break in src/amd/common/ac_nir_to_llvm.c.
Signed-off-by: Ian Romanick <[email protected]>
Reviewed-by: Eduardo Lima Mitev <[email protected]>
|
|
|
|
|
| |
Signed-off-by: Ian Romanick <[email protected]>
Reviewed-by: Eduardo Lima Mitev <[email protected]>
|
|
|
|
|
|
|
| |
Co-authored-by: Daniel Schürmann <[email protected]>
Signed-off-by: Dave Airlie <[email protected]>
Reviewed-by: Bas Nieuwenhuizen <[email protected]>
Reviewed-by: Samuel Pitoiset <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
| |
These are needed for SPV_AMD_shader_trinary_minmax,
the AMD HW supports these.
Co-authored-by: Daniel Schürmann <[email protected]>
Signed-off-by: Dave Airlie <[email protected]>
Reviewed-by: Bas Nieuwenhuizen <[email protected]>
Reviewed-by: Ian Romanick <[email protected]>
Reviewed-by: Samuel Pitoiset <[email protected]>
|
|
|
|
|
|
|
| |
Fixes: 76dfed8ae2d5 ("nir: mako all the intrinsics")
Signed-off-by: Stefan Schake <[email protected]>
Acked-by: Rob Clark <[email protected]>
Reviewed-by: Tapani Pälli <[email protected]>
|
|
|
|
|
|
| |
Reviewed-by: Iago Toral Quiroga <[email protected]>
Reviewed-by: Marek Olšák <[email protected]>
Reviewed-by: Samuel Pitoiset <[email protected]>
|
|
|
|
|
|
|
|
| |
I have no idea why but having dest_components == -1 was causing a memory
leak somewhere. Without this, you can't get through a full shader-db
run without running out of memory.
Reviewed-by: Rob Clark <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
When an if nesting inside anouther if is optimised away we can
end up with a loop terminator and following block that looks like
this:
if ssa_596 {
block block_5:
/* preds: block_4 */
vec1 32 ssa_601 = load_const (0xffffffff /* -nan */)
break
/* succs: block_8 */
} else {
block block_6:
/* preds: block_4 */
/* succs: block_7 */
}
block block_7:
/* preds: block_6 */
vec1 32 ssa_602 = phi block_6: ssa_552
vec1 32 ssa_603 = phi block_6: ssa_553
vec1 32 ssa_604 = iadd ssa_551, ssa_66
The problem is the phis. Loop unrolling expects the last block in
the loop to be empty once we splice the instructions in the last
block into the continue branch. The problem is we cant move phis
so here we lower the phis to regs when preparing the loop for
unrolling. As it could be possible to have multiple additional
blocks/ifs following the terminator we just convert all phis at
the top level of the loop body for simplicity.
We also add some comments to loop_prepare_for_unroll() while we
are here.
Fixes: 51daccb289eb "nir: add a loop unrolling pass"
Reviewed-by: Jason Ekstrand <[email protected]>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=105670
|
|
|
|
|
|
|
|
|
|
| |
Apparently it is not happy about things like: .foo = {}
So skip over initializers for empty lists.
Fixes: 76dfed8ae2d5c6c509eb2661389be3c6a25077df
Reported-by: Roland Scheidegger <[email protected]>
Signed-off-by: Rob Clark <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
I threatened to do this a long time ago.. I probably *should* have done
it a long time ago when there where many fewer intrinsics. But the
system of macro/#include magic for dealing with intrinsics is a bit
annoying, and python has the nice property of optional fxn params,
making it possible to define new intrinsics while ignoring parameters
that are not applicable (and naming optional params). And not having to
specify various array lengths explicitly is nice too.
I think the end result makes it easier to add new intrinsics.
v2: couple small fixes found with a test program to compare the old and
new tables
v3: misc comments, don't rely on capture=true for meson.build, get rid
of system_values table to avoid return value of intrinsic() and
*mostly* remove side-effects, add autotools build support
v4: scons build
Signed-off-by: Rob Clark <[email protected]>
Acked-by: Dylan Baker <[email protected]>
Acked-by: Jason Ekstrand <[email protected]>
|
|
|
|
|
|
|
|
|
| |
This is supposed to have both BASE and COMPONENT but num_indices was
inadvertantly set to 1.
Cc: <[email protected]>
Signed-off-by: Rob Clark <[email protected]>
Reviewed-by: Jason Ekstrand <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The VECN() macro was taking advantage of a GCC specific feature that is
not available on lesser compilers, mostly for the purposes of avoiding a
macro that encoded a return statement.
But as suggested by Ian, we could just have the macro produce the entire
method body and avoid the need for this. So let's do that instead.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=105740
Fixes: f407edf3407396379e16b0be74b8d3b85d2ad7f0
Cc: Emil Velikov <[email protected]>
Cc: Timothy Arceri <[email protected]>
Cc: Roland Scheidegger <[email protected]>
Cc: Ian Romanick <[email protected]>
Signed-off-by: Rob Clark <[email protected]>
Acked-by: Timothy Arceri <[email protected]>
Reviewed-by: Roland Scheidegger <[email protected]>
Reviewed-by: Ian Romanick <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Just checking for 2 jumps is not enough to be sure we can do a
complex loop unroll. We need to make sure we also have also found
2 loop terminators.
Without this we were attempting to unroll a loop where the second
jump was nested inside multiple ifs which loop analysis is unable
to detect as a terminator. We ended up splicing out the first
terminator but failed to actually unroll the loop, this resulted
in the creation of a possible infinite loop.
Fixes: 646621c66da9 "glsl: make loop unrolling more like the nir unrolling path"
Tested-by: Gert Wollny <[email protected]>
Reviewed-by: Ian Romanick <[email protected]>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=105670
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Now that i965 recognizes that a-b generates the same conditions as 'a <
b', there is no reason to condition this transformation on 'is not used
by conditional.'
Since this was the only user of the is_not_used_by_conditional function,
delete it.
All Gen6+ platforms had similar results. (Skylake shown)
total instructions in shared programs: 14400775 -> 14400595 (<.01%)
instructions in affected programs: 36712 -> 36532 (-0.49%)
helped: 182
HURT: 26
helped stats (abs) min: 1 max: 2 x̄: 1.13 x̃: 1
helped stats (rel) min: 0.15% max: 1.82% x̄: 0.70% x̃: 0.62%
HURT stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
HURT stats (rel) min: 0.24% max: 1.02% x̄: 0.82% x̃: 0.90%
95% mean confidence interval for instructions value: -0.97 -0.76
95% mean confidence interval for instructions %-change: -0.59% -0.43%
Instructions are helped.
total cycles in shared programs: 532929592 -> 532926345 (<.01%)
cycles in affected programs: 478660 -> 475413 (-0.68%)
helped: 187
HURT: 22
helped stats (abs) min: 2 max: 200 x̄: 20.99 x̃: 18
helped stats (rel) min: 0.23% max: 24.10% x̄: 1.48% x̃: 1.03%
HURT stats (abs) min: 1 max: 214 x̄: 30.86 x̃: 11
HURT stats (rel) min: 0.01% max: 23.06% x̄: 3.12% x̃: 0.86%
95% mean confidence interval for cycles value: -19.50 -11.57
95% mean confidence interval for cycles %-change: -1.42% -0.58%
Cycles are helped.
GM45 and Iron Lake had similar results. (Iron Lake shown)
total cycles in shared programs: 177851578 -> 177851810 (<.01%)
cycles in affected programs: 24408 -> 24640 (0.95%)
helped: 2
HURT: 4
helped stats (abs) min: 4 max: 4 x̄: 4.00 x̃: 4
helped stats (rel) min: 0.42% max: 0.47% x̄: 0.44% x̃: 0.44%
HURT stats (abs) min: 24 max: 108 x̄: 60.00 x̃: 54
HURT stats (rel) min: 0.52% max: 1.62% x̄: 1.04% x̃: 1.02%
95% mean confidence interval for cycles value: -7.75 85.08
95% mean confidence interval for cycles %-change: -0.39% 1.49%
Inconclusive result (value mean confidence interval includes 0).
Signed-off-by: Ian Romanick <[email protected]>
Reviewed-by: Matt Turner <[email protected]>
|
|
|
|
|
|
|
| |
Not used in GL but 8 and 16 component vectors exist in OpenCL.
Signed-off-by: Rob Clark <[email protected]>
Reviewed-by: Timothy Arceri <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Refactor things so there isn't so much typing involved to add new
things.
Also drops a pointless conditional (out of bounds rows or columns
already returns error_type in all paths.. might as well drop it
rather than make the check more convoluted in the next patch by
adding the vec8/vec16 case).
Signed-off-by: Rob Clark <[email protected]>
Reviewed-by: Timothy Arceri <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
I don't think it actually fixes anything, but that's nice not to have valgrind warnings.
It manifests itself when running the piglit test : glsl-fs-raytrace-bug27060
==2058== Uninitialised byte(s) found during client check request
==2058== at 0xC5BB040: blob_write_bytes (blob.c:152)
==2058== by 0xC595359: write_variable (nir_serialize.c:144)
==2058== by 0xC59560C: write_var_list (nir_serialize.c:192)
==2058== by 0xC5982E4: nir_serialize (nir_serialize.c:1124)
==2058== by 0xC0B729D: brw_program_serialize_nir (brw_program.c:835)
==2058== by 0xC0AB2D6: brw_link_shader (brw_link.cpp:358)
==2058== by 0xC32FE3F: _mesa_glsl_link_shader (ir_to_mesa.cpp:3169)
==2058== by 0xC36C7ED: create_new_program(gl_context*, state_key*) (ff_fragment_shader.cpp:1127)
==2058== by 0xC36C8A6: _mesa_get_fixed_func_fragment_program (ff_fragment_shader.cpp:1157)
==2058== by 0xC1B50AF: update_program (state.c:134)
==2058== by 0xC1B56DF: _mesa_update_state_locked (state.c:352)
==2058== by 0xC1B579A: _mesa_update_state (state.c:386)
==2058== Address 0xf1eab8a is 58 bytes inside a block of size 96 alloc'd
==2058== at 0x4C2CB8F: malloc (vg_replace_malloc.c:299)
==2058== by 0xC0FD306: ralloc_size (ralloc.c:121)
==2058== by 0xC0FD5B1: ralloc_array_size (ralloc.c:208)
==2058== by 0xC452B3B: (anonymous namespace)::nir_visitor::visit(ir_variable*) (glsl_to_nir.cpp:448)
==2058== by 0xC45CE8B: ir_variable::accept(ir_visitor*) (ir.h:428)
==2058== by 0xC46D0B5: visit_exec_list(exec_list*, ir_visitor*) (ir.cpp:1898)
==2058== by 0xC451D2F: glsl_to_nir (glsl_to_nir.cpp:162)
==2058== by 0xC0B5223: brw_create_nir (brw_program.c:79)
==2058== by 0xC0AAB67: brw_link_shader (brw_link.cpp:257)
==2058== by 0xC32FE3F: _mesa_glsl_link_shader (ir_to_mesa.cpp:3169)
==2058== by 0xC36C7ED: create_new_program(gl_context*, state_key*) (ff_fragment_shader.cpp:1127)
==2058== by 0xC36C8A6: _mesa_get_fixed_func_fragment_program (ff_fragment_shader.cpp:1157)
Signed-off-by: Lionel Landwerlin <[email protected]>
Reviewed-by: Tapani Pälli <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
| |
Generated with
git grep -l nir_intrinsic_image | xargs \
sed -i 's/nir_intrinsic_image/nir_intrinsic_image_var/g'
and some manual fixing in nir_intrinsics.h
Reviewed-by: Timothy Arceri <[email protected]>
|
|
|
|
| |
Reviewed-by: Emil Velikov <[email protected]>
|
|
|
|
| |
Reviewed-by: Bas Nieuwenhuizen <[email protected]>
|
|
|
|
|
|
|
|
|
|
| |
The implementation is inspired by
lower_instructions_visitor::dfrexp_sig_to_arith.
This has been tested against the arb_gpu_shader_fp64/fs-frexp-dvec4
test using the ARB_gl_spirv branch.
Reviewed-by: Jason Ekstrand <[email protected]>
|
|
|
|
|
|
|
|
|
| |
Shader-db runtime change avarage of five runs:
Before 125,77 seconds (+/- 0,09%)
After 124,48 seconds (+/- 0,07%)
Tested-by: Dieter Nützel <Dieter at nuetzel-hh.de>
Reviewed-by: Eric Anholt <eric at anholt.net>
|
|
|
|
|
|
|
|
|
|
| |
Make a simple worklist by basically just wrapping u_vector.
This is intended used in nir_opt_dce to reduce the number of calls
to ralloc, as we are currenlty spamming ralloc quite bad. It should
also give better cache locality and much lower memory usage.
Tested-by: Dieter Nützel <Dieter at nuetzel-hh.de>
Reviewed-by: Eric Anholt <eric at anholt.net>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Generalize the code for remove dead loops to also remove dead if
nodes. The conditions are the same in both cases, if the node (and
it's children) don't have side-effects AND the nodes after it don't
use the values produced by the node.
The only difference is when evaluating side effects: loops consider
only return jumps as a side-effect -- they can stop execution of nodes
after it; 'if' nodes outside loops should consider all kinds of
jumps (return, break, continue) since all of them can cause execution
of nodes after it to be skipped.
After this patch, empty ifs (those which both then and else blocks are
empty) will be removed by nir_opt_dead_cf.
It caused no change to shader-db, in part because the removal of empty
ifs is currently covered by nir_opt_peephole_select.
v2: Improve the identification of cases where break/continue can cause
side-effects. (Jason)
v3: Move code comment changes to a different patch. (Jason)
Reviewed-by: Jason Ekstrand <[email protected]>
|
|
|
|
| |
Reviewed-by: Jason Ekstrand <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
i965 and gallium handle the atomic buffer index differently. It was
just by luck that the single piglit test for this was passing.
For gallium we use the atomic binding so that we match the handling
in st_bind_atomics().
On radeonsi this fixes the CTS test:
KHR-GL43.shader_storage_buffer_object.advanced-write-fragment
It also fixes tressfx hair rendering in Tomb Raider.
Reviewed-by: Marek Olšák <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This will only ever be used by gallium drivers so it probably doesn't
belong in the nir toolkit. Also we want to pass it some non NIR
things in the following patch.
To avoid regressions we wrap the lowering calls that have been moved
to st_glsl_to_nir with a quick hack so that they are only called for
radeonsi, we will replace the hack with a check for uniform packing
in a following patch.
Reviewed-by: Marek Olšák <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Currently everything is padded to 4 components. Making the list
more flexible will allow us to do uniform packing.
V2 (suggestions from Nicolai):
- always pass existing calls to _mesa_add_parameter() true for padd_and_align
- fix bindless param value offsets
- remove left over wip logic from pad and align code
- zero out param value padding
- whitespace fix
Reviewed-by: Marek Olšák <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
All of the shaders that had loops changed were in Tomb Raider. The one
shader that lost SIMD16 is one of those.
Skylake
total instructions in shared programs: 14391653 -> 14390468 (<.01%)
instructions in affected programs: 111891 -> 110706 (-1.06%)
helped: 501
HURT: 0
helped stats (abs) min: 1 max: 155 x̄: 2.37 x̃: 1
helped stats (rel) min: 0.05% max: 21.54% x̄: 1.61% x̃: 1.01%
95% mean confidence interval for instructions value: -3.23 -1.50
95% mean confidence interval for instructions %-change: -1.77% -1.45%
Instructions are helped.
total cycles in shared programs: 532793024 -> 532776598 (<.01%)
cycles in affected programs: 987682 -> 971256 (-1.66%)
helped: 348
nnHURT: 41
helped stats (abs) min: 1 max: 3074 x̄: 54.91 x̃: 18
helped stats (rel) min: 0.05% max: 32.24% x̄: 3.36% x̃: 1.68%
HURT stats (abs) min: 1 max: 422 x̄: 65.39 x̃: 24
HURT stats (rel) min: 0.09% max: 39.29% x̄: 9.50% x̃: 2.02%
95% mean confidence interval for cycles value: -64.08 -20.38
95% mean confidence interval for cycles %-change: -2.78% -1.23%
Cycles are helped.
total loops in shared programs: 4854 -> 4829 (-0.52%)
loops in affected programs: 27 -> 2 (-92.59%)
helped: 18
HURT: 0
LOST: 1
GAINED: 0
Signed-off-by: Ian Romanick <[email protected]>
Reviewed-by: Timothy Arceri <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
When the shader cache is used, this can be generated. In fact, the
shader cache uses this sha1 to lookup the serialized GL shader
program.
If a GL shader program is restored with ProgramBinary, the shaders are
not available, and therefore the correct sha1 cannot be generated. If
this is restored, then we can use the shader cache to restore the
binary programs to the program that was loaded with ProgramBinary.
Signed-off-by: Jordan Justen <[email protected]>
Reviewed-by: Timothy Arceri <[email protected]>
Reviewed-by: Tapani Pälli <[email protected]>
|
|
|
|
|
|
|
|
|
|
| |
We used this to prevent usage of the disk shader cache when transform
feedback was enabled via the GL API. This is no longer used.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=105444
Signed-off-by: Jordan Justen <[email protected]>
Reviewed-by: Tapani Pälli <[email protected]>
Reviewed-by: Timothy Arceri <[email protected]>
|
|
|
|
|
|
|
|
| |
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=105444
Suggested-by: Timothy Arceri <[email protected]>
Signed-off-by: Jordan Justen <[email protected]>
Reviewed-by: Tapani Pälli <[email protected]>
Reviewed-by: Timothy Arceri <[email protected]>
|
|
|
|
|
|
|
|
| |
This pass moves load UBO operations just before their first use,
loosely based on nir_opt_move_comparisons.
Signed-off-by: Samuel Pitoiset <[email protected]>
Reviewed-by: Timothy Arceri <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
So now, during spirv_to_nir, it uses the capability instead of the
extension. Note that we are really doing here is treating
SPV_AMD_gcn_shader as other supported extensions. SPV_AMD_gcn_shader
is not the first SPV extension supported. For example, the capability
draw_parameters infers if the extension SPV_KHR_shader_draw_parameters
is supported or not.
This could be seen as counter-intuitive, and that it would be easier
to define which extensions are supported, and based our checks on
that, but we need to take into account that some capabilities are
optional from core, and others came from new extensions.
Also this commit would make the implementation of ARB_spirv_extensions
easier.
v2: AMD_gcn_shader capability renamed to gcn_shader (Daniel Schürmann)
Reviewed-by: Daniel Schürmann <[email protected]>
Reviewed-by: Bas Nieuwenhuizen <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
| |
We don't need anymore the source and destination's data type, just
their bitsize.
v2:
- Use glsl_get_bit_size () instead (Jason).
Signed-off-by: Samuel Iglesias Gonsálvez <[email protected]>
Reviewed-by: Jason Ekstrand <[email protected]>
|
|
|
|
|
|
|
|
|
| |
There are some SPIRV opcodes (like UConvert and SConvert) have some
expectations of the output that doesn't depend on the operands
data type. Generalize the solution of all of them.
Signed-off-by: Samuel Iglesias Gonsálvez <[email protected]>
Reviewed-by: Jason Ekstrand <[email protected]>
|
|
|
|
|
|
|
|
|
|
| |
Walking the whole hash table, inserting entries by hashing them first
is just a really bad idea. We can simply memcpy the whole thing.
V2: Remove leftover creation of acp in two places
Reviewed-by: Eric Anholt <[email protected]>
Reviewed-by: Emil Velikov <[email protected]>
|
|
|
|
|
|
|
|
|
|
| |
OpenCL kernels also have int8/uint8.
v2: remove changes in nir_search as Jason posted a patch for that
Reviewed-by: Jason Ekstrand <[email protected]>
Signed-off-by: Rob Clark <[email protected]>
Signed-off-by: Karol Herbst <[email protected]>
|
|
|
|
|
|
|
|
|
|
| |
The code to handle mat multiplication by a scalar tries to pick either
imul or fmul depending on whether the matrix is float or integer.
However it was doing this by checking whether the base type is float.
This was making it choose the int path for doubles (and presumably
float16s).
Reviewed-by: Jason Ekstrand <[email protected]>
|
|
|
|
|
| |
Signed-off-by: Rob Clark <[email protected]>
Reviewed-by: Jason Ekstrand <[email protected]>
|
|
|
|
|
|
|
|
|
| |
This is based heavily on 97f10934edf8ac, "ac/nir: Add vote_ieq/vote_feq
lowering pass." from Bas Nieuwenhuizen. This version is a bit more
general since it's in common code. It also properly handles NaN due to
not flipping the comparison for floats.
Reviewed-by: Bas Nieuwenhuizen <[email protected]>
|
|
|
|
|
|
| |
v2: Use assume() at the srcs[] definition instead.
Reviewed-by: Ian Romanick <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
A bunch of shaders have sequences like:
i2b(u2i(floatBitsToUint(intBitsToFloat(x == y ? -1 : 0))))
Other optimizations (and NIR's typeless nature) reduce this to
i2b(x == y)
which is silly.
Skylake
total instructions in shared programs: 14498698 -> 14497948 (<.01%)
instructions in affected programs: 74480 -> 73730 (-1.01%)
helped: 277
HURT: 0
helped stats (abs) min: 1 max: 32 x̄: 2.71 x̃: 2
helped stats (rel) min: 0.04% max: 13.79% x̄: 1.45% x̃: 0.68%
95% mean confidence interval for instructions value: -3.35 -2.06
95% mean confidence interval for instructions %-change: -1.74% -1.16%
Instructions are helped.
total cycles in shared programs: 532015500 -> 531999238 (<.01%)
cycles in affected programs: 5943878 -> 5927616 (-0.27%)
helped: 251
HURT: 74
helped stats (abs) min: 1 max: 13149 x̄: 127.89 x̃: 14
helped stats (rel) min: 0.01% max: 17.31% x̄: 1.55% x̃: 0.53%
HURT stats (abs) min: 1 max: 4550 x̄: 214.04 x̃: 15
HURT stats (rel) min: <.01% max: 44.43% x̄: 2.81% x̃: 0.33%
95% mean confidence interval for cycles value: -158.51 58.43
95% mean confidence interval for cycles %-change: -1.07% -0.04%
Inconclusive result (value mean confidence interval includes 0).
total loops in shared programs: 4753 -> 4735 (-0.38%)
loops in affected programs: 18 -> 0
helped: 18
HURT: 0
helped stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
helped stats (rel) min: 100.00% max: 100.00% x̄: 100.00% x̃: 100.00%
95% mean confidence interval for loops value: -1.00 -1.00
95% mean confidence interval for loops %-change: -100.00% -100.00%
Loops are helped.
Haswell and Broadwell had simliar results. (Broadwell shown)
total instructions in shared programs: 14791877 -> 14791127 (<.01%)
instructions in affected programs: 77326 -> 76576 (-0.97%)
helped: 278
HURT: 1
helped stats (abs) min: 1 max: 32 x̄: 2.70 x̃: 2
helped stats (rel) min: 0.04% max: 13.79% x̄: 1.42% x̃: 0.68%
HURT stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
HURT stats (rel) min: 0.49% max: 0.49% x̄: 0.49% x̃: 0.49%
95% mean confidence interval for instructions value: -3.33 -2.05
95% mean confidence interval for instructions %-change: -1.70% -1.13%
Instructions are helped.
total cycles in shared programs: 558250067 -> 558252872 (<.01%)
cycles in affected programs: 5806328 -> 5809133 (0.05%)
helped: 235
HURT: 83
helped stats (abs) min: 1 max: 10630 x̄: 81.73 x̃: 16
helped stats (rel) min: 0.03% max: 18.58% x̄: 1.60% x̃: 0.51%
HURT stats (abs) min: 1 max: 10590 x̄: 265.19 x̃: 20
HURT stats (rel) min: <.01% max: 15.28% x̄: 1.89% x̃: 0.54%
95% mean confidence interval for cycles value: -89.87 107.51
95% mean confidence interval for cycles %-change: -1.06% -0.32%
Inconclusive result (value mean confidence interval includes 0).
total loops in shared programs: 4735 -> 4717 (-0.38%)
loops in affected programs: 18 -> 0
helped: 18
HURT: 0
helped stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
helped stats (rel) min: 100.00% max: 100.00% x̄: 100.00% x̃: 100.00%
95% mean confidence interval for loops value: -1.00 -1.00
95% mean confidence interval for loops %-change: -100.00% -100.00%
Loops are helped.
total fills in shared programs: 83111 -> 83110 (<.01%)
fills in affected programs: 28 -> 27 (-3.57%)
helped: 1
HURT: 0
Ivy Bridge
total instructions in shared programs: 11774173 -> 11773436 (<.01%)
instructions in affected programs: 70819 -> 70082 (-1.04%)
helped: 267
HURT: 0
helped stats (abs) min: 1 max: 48 x̄: 2.76 x̃: 2
helped stats (rel) min: 0.21% max: 19.51% x̄: 1.57% x̃: 0.63%
95% mean confidence interval for instructions value: -3.51 -2.01
95% mean confidence interval for instructions %-change: -1.94% -1.21%
Instructions are helped.
total cycles in shared programs: 257153833 -> 257148932 (<.01%)
cycles in affected programs: 585341 -> 580440 (-0.84%)
helped: 167
HURT: 100
helped stats (abs) min: 1 max: 1327 x̄: 44.89 x̃: 16
helped stats (rel) min: 0.04% max: 26.54% x̄: 2.41% x̃: 0.88%
HURT stats (abs) min: 1 max: 200 x̄: 25.95 x̃: 16
HURT stats (rel) min: 0.04% max: 9.81% x̄: 1.34% x̃: 0.65%
95% mean confidence interval for cycles value: -33.25 -3.46
95% mean confidence interval for cycles %-change: -1.47% -0.54%
Cycles are helped.
total loops in shared programs: 3416 -> 3398 (-0.53%)
loops in affected programs: 18 -> 0
helped: 18
HURT: 0
helped stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
helped stats (rel) min: 100.00% max: 100.00% x̄: 100.00% x̃: 100.00%
95% mean confidence interval for loops value: -1.00 -1.00
95% mean confidence interval for loops %-change: -100.00% -100.00%
Loops are helped.
LOST: 2
GAINED: 0
Sandy Bridge
total instructions in shared programs: 10499306 -> 10499094 (<.01%)
instructions in affected programs: 6051 -> 5839 (-3.50%)
helped: 43
HURT: 0
helped stats (abs) min: 1 max: 32 x̄: 4.93 x̃: 2
helped stats (rel) min: 0.39% max: 12.90% x̄: 4.29% x̃: 2.45%
95% mean confidence interval for instructions value: -7.66 -2.20
95% mean confidence interval for instructions %-change: -5.47% -3.12%
Instructions are helped.
total cycles in shared programs: 145862568 -> 145861370 (<.01%)
cycles in affected programs: 61733 -> 60535 (-1.94%)
helped: 36
HURT: 2
helped stats (abs) min: 16 max: 66 x̄: 36.61 x̃: 35
helped stats (rel) min: 0.45% max: 17.31% x̄: 4.92% x̃: 2.81%
HURT stats (abs) min: 18 max: 102 x̄: 60.00 x̃: 60
HURT stats (rel) min: 1.10% max: 1.85% x̄: 1.48% x̃: 1.48%
95% mean confidence interval for cycles value: -41.28 -21.77
95% mean confidence interval for cycles %-change: -6.16% -3.00%
Cycles are helped.
total loops in shared programs: 1803 -> 1785 (-1.00%)
loops in affected programs: 18 -> 0
helped: 18
HURT: 0
helped stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
helped stats (rel) min: 100.00% max: 100.00% x̄: 100.00% x̃: 100.00%
95% mean confidence interval for loops value: -1.00 -1.00
95% mean confidence interval for loops %-change: -100.00% -100.00%
Loops are helped.
LOST: 4
GAINED: 0
No changes on Iron Lake of GM45.
Signed-off-by: Ian Romanick <[email protected]>
Reviewed-by: Samuel Iglesias Gonsálvez <[email protected]>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
On vector platforms, this helps elide some constant loads.
v2: Reorder the transformations.
No changes on Broadwell or Skylake.
Haswell
total instructions in shared programs: 13093793 -> 13060163 (-0.26%)
instructions in affected programs: 1277532 -> 1243902 (-2.63%)
helped: 13216
HURT: 95
helped stats (abs) min: 1 max: 18 x̄: 2.56 x̃: 2
helped stats (rel) min: 0.21% max: 20.00% x̄: 3.63% x̃: 2.78%
HURT stats (abs) min: 1 max: 6 x̄: 1.77 x̃: 1
HURT stats (rel) min: 0.09% max: 5.56% x̄: 1.25% x̃: 1.19%
95% mean confidence interval for instructions value: -2.57 -2.49
95% mean confidence interval for instructions %-change: -3.65% -3.54%
Instructions are helped.
total cycles in shared programs: 409580819 -> 409268463 (-0.08%)
cycles in affected programs: 71730652 -> 71418296 (-0.44%)
helped: 9898
HURT: 2352
helped stats (abs) min: 2 max: 16014 x̄: 37.08 x̃: 16
helped stats (rel) min: <.01% max: 35.55% x̄: 6.26% x̃: 4.50%
HURT stats (abs) min: 2 max: 276 x̄: 23.25 x̃: 6
HURT stats (rel) min: <.01% max: 40.00% x̄: 3.54% x̃: 1.97%
95% mean confidence interval for cycles value: -33.19 -17.80
95% mean confidence interval for cycles %-change: -4.50% -4.26%
Cycles are helped.
total fills in shared programs: 82059 -> 82052 (<.01%)
fills in affected programs: 21 -> 14 (-33.33%)
helped: 7
HURT: 0
Sandy Bridge and Ivy Bridge had similar results (Ivy Bridge shown)
total instructions in shared programs: 11811851 -> 11780605 (-0.26%)
instructions in affected programs: 1155007 -> 1123761 (-2.71%)
helped: 12304
HURT: 95
helped stats (abs) min: 1 max: 18 x̄: 2.55 x̃: 2
helped stats (rel) min: 0.21% max: 20.00% x̄: 3.69% x̃: 2.86%
HURT stats (abs) min: 1 max: 6 x̄: 1.77 x̃: 1
HURT stats (rel) min: 0.09% max: 5.56% x̄: 1.25% x̃: 1.19%
95% mean confidence interval for instructions value: -2.56 -2.48
95% mean confidence interval for instructions %-change: -3.71% -3.59%
Instructions are helped.
total cycles in shared programs: 257618409 -> 257316805 (-0.12%)
cycles in affected programs: 71999580 -> 71697976 (-0.42%)
helped: 9155
HURT: 2380
helped stats (abs) min: 2 max: 16014 x̄: 38.44 x̃: 16
helped stats (rel) min: <.01% max: 35.75% x̄: 6.39% x̃: 4.62%
HURT stats (abs) min: 2 max: 290 x̄: 21.14 x̃: 4
HURT stats (rel) min: <.01% max: 41.55% x̄: 3.14% x̃: 1.33%
95% mean confidence interval for cycles value: -34.32 -17.97
95% mean confidence interval for cycles %-change: -4.55% -4.29%
Cycles are helped.
GM45 and Iron Lake had nearly identical results (Iron Lake shown)
total instructions in shared programs: 7886750 -> 7879944 (-0.09%)
instructions in affected programs: 373781 -> 366975 (-1.82%)
helped: 3715
HURT: 47
helped stats (abs) min: 1 max: 8 x̄: 1.86 x̃: 1
helped stats (rel) min: 0.22% max: 16.67% x̄: 2.88% x̃: 2.06%
HURT stats (abs) min: 1 max: 6 x̄: 2.55 x̃: 2
HURT stats (rel) min: 1.09% max: 5.00% x̄: 1.93% x̃: 2.35%
95% mean confidence interval for instructions value: -1.85 -1.77
95% mean confidence interval for instructions %-change: -2.91% -2.73%
Instructions are helped.
total cycles in shared programs: 178114636 -> 178095452 (-0.01%)
cycles in affected programs: 7227666 -> 7208482 (-0.27%)
helped: 3349
HURT: 301
helped stats (abs) min: 2 max: 90 x̄: 6.55 x̃: 4
helped stats (rel) min: <.01% max: 14.18% x̄: 0.95% x̃: 0.63%
HURT stats (abs) min: 2 max: 42 x̄: 9.13 x̃: 10
HURT stats (rel) min: 0.01% max: 11.19% x̄: 1.22% x̃: 1.50%
95% mean confidence interval for cycles value: -5.52 -4.99
95% mean confidence interval for cycles %-change: -0.81% -0.73%
Cycles are helped.
Signed-off-by: Ian Romanick <[email protected]>
Reviewed-by: Samuel Iglesias Gonsálvez <[email protected]> [v1]
|
|
|
|
|
|
| |
Fixes: 68a6a3b51acc "spirv: handle AMD_gcn_shader extended instructions"
Reviewed-by: Bas Nieuwenhuizen <[email protected]>
|