summaryrefslogtreecommitdiffstats
path: root/src/compiler
Commit message (Collapse)AuthorAgeFilesLines
* mesa/compiler: rework tear down of builtin/typesLionel Landwerlin2019-08-217-67/+31
| | | | | | | | | | | | | | | | | | | | | | | | | | The issue we're running into when running CTS is that glsl types are deleted while builtins depending on them are not. This happens because on one hand we have glsl types ref counted, but builtins are not. Instead builtins are destroyed when unloading libGL or explicitly calling glReleaseShaderCompiler(). This change removes almost entirely any dealing with glsl types ref/unref by letting the builtins deal with it instead. In turn we introduce a builtin ref count mechanism. Each GL context takes a reference on the builtins when compiling a shader for the first time. It releases the reference when the context is destroyed. It can also explicitly release those when glReleaseShaderCompiler() is called. Finally we also take a reference on the glsl types when loading libGL to avoid recreating glsl types too often. v2: Ensure we take a reference if we don't have one in link step (Lionel) Signed-off-by: Lionel Landwerlin <[email protected]> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=110796 Reviewed-by: Eric Anholt <[email protected]> Reviewed-by: Tapani Pälli <[email protected]>
* compiler: ensure glsl types are not created without a referenceLionel Landwerlin2019-08-211-1/+6
| | | | | | | | | We want to detect invalid refcounting so assert we have at least one use before creating types. Signed-off-by: Lionel Landwerlin <[email protected]> Reviewed-by: Eric Anholt <[email protected]> Reviewed-by: Tapani Pälli <[email protected]>
* nir/tests: take reference on glsl typesLionel Landwerlin2019-08-214-1/+16
| | | | | | Signed-off-by: Lionel Landwerlin <[email protected]> Reviewed-by: Eric Anholt <[email protected]> Reviewed-by: Tapani Pälli <[email protected]>
* glsl/tests: take refs on glsl typesLionel Landwerlin2019-08-219-18/+64
| | | | | | | | | Much like each driver, tests as standalone entities must take references on the glsl types. Signed-off-by: Lionel Landwerlin <[email protected]> Reviewed-by: Eric Anholt <[email protected]> Reviewed-by: Tapani Pälli <[email protected]>
* nir: add divergence analysis pass.Daniel Schürmann2019-08-203-0/+799
| | | | | | | | | | This pass expects the shader to be in LCSSA form. The algorithm is based on 'The Simple Divergence Analysis' from Diogo Sampaio, Rafael De Souza, Sylvain Collange, Fernando Magno Quintão Pereira. Divergence Analysis. ACM Transactions on Programming Languages and Systems (TOPLAS) Reviewed-by: Jason Ekstrand <[email protected]> Reviewed-by: Connor Abbott <[email protected]>
* nir/subgroups: Lower clustered reductions with cluster_size >= subgroup_size ↵Rhys Perry2019-08-201-1/+12
| | | | | | | | into reductions The behavior for reductions with cluster_size >= subgroup_size is implementation defined. Reviewed-by: Jason Ekstrand <[email protected]>
* nir/lcssa: allow to create LCSSA phis for loop-invariant booleansRhys Perry2019-08-202-3/+7
| | | | | | | ACO depends on LCSSA phis for divergent booleans to work correctly. Reviewed-by: Connor Abbott <[email protected]> Reviewed-by: Jason Ekstrand <[email protected]>
* nir/lcssa: Skip loop invariant variables when converting to LCSSA.Daniel Schürmann2019-08-202-14/+162
| | | | | | Co-authored-by: Rhys Perry <[email protected]> Reviewed-by: Connor Abbott <[email protected]> Reviewed-by: Jason Ekstrand <[email protected]>
* nir: make nir_to_lcssa() a general NIR pass.Rhys Perry2019-08-202-3/+42
| | | | | Reviewed-by: Connor Abbott <[email protected]> Reviewed-by: Jason Ekstrand <[email protected]>
* nir/lcssa: handle deref instructions properlyDaniel Schürmann2019-08-202-14/+26
| | | | | Reviewed-by: Jason Ekstrand <[email protected]> Fixes: 414148cdc124 "nir: Support deref instructions in loop_analyze"
* nir: Add more source types to nir_tex_instr_src_typeJason Ekstrand2019-08-191-3/+14
| | | | | Reviewed-by: Dave Airlie <[email protected]> Reviewed-by: Alyssa Rosenzweig <[email protected]>
* nir: Add missing dependency in Android.nir.gen.mkRoman Stratiienko2019-08-191-0/+1
| | | | | | | Fixes incremental build with Android Signed-off-by: Roman Stratiienko <[email protected]> Reviewed-by: Tapani Pälli <[email protected]>
* glsl/standalone: init shader stage in init_gl_program()Vasily Khoruzhick2019-08-171-2/+4
| | | | | | | | | | | Otherwise lima standalone compiler fails when trying to compile fragment shader with: lima_compiler: ../src/compiler/nir/nir.c:55: nir_shader_create: Assertion `si->stage == stage' failed Reviewed-by: Qiang Yu <[email protected]> Reviewed-by: Matt Turner <[email protected]> Signed-off-by: Vasily Khoruzhick <[email protected]>
* nir/algebraic: add a few masking-before-unpack optimizationsRhys Perry2019-08-161-1/+9
| | | | | | | | | | | | | | | | | | | Helps some Dawn of War 3 and F1 2017 shaders with ACO: Totals from affected shaders: SGPRS: 2136 -> 2128 (-0.37 %) VGPRS: 1624 -> 1628 (0.25 %) Spilled SGPRs: 0 -> 0 (0.00 %) Spilled VGPRs: 0 -> 0 (0.00 %) Private memory VGPRs: 0 -> 0 (0.00 %) Scratch size: 0 -> 0 (0.00 %) dwords per thread Code Size: 168068 -> 164332 (-2.22 %) bytes LDS: 44 -> 44 (0.00 %) blocks Max Waves: 222 -> 221 (-0.45 %) Wait states: 0 -> 0 (0.00 %) Signed-off-by: Rhys Perry <[email protected]> Reviewed-by: Ian Romanick <[email protected]> Reviewed-by: Eric Anholt <[email protected]>
* win32: unify strcasecmp definitionsErik Faye-Lund2019-08-151-0/+1
| | | | | | | | | There was two incompatible definitions of strcasecmp, which lead to a compiler warning. Let's clean this up by only leaving one of them, and using that one all the time. Signed-off-by: Erik Faye-Lund <[email protected]> Reviewed-by: Eric Anholt <[email protected]>
* nir: avoid warning when casting bogus pointerErik Faye-Lund2019-08-151-1/+1
| | | | | | | | This intentionally-bogus pointer generates a warning on some 64-bit systems, so let's cast to a properly-sized integer first. Signed-off-by: Erik Faye-Lund <[email protected]> Reviewed-by: Eric Anholt <[email protected]>
* glsl: fixup u64-warningErik Faye-Lund2019-08-151-1/+1
| | | | | | | | | Similarly to the unsigned-version, we need to first cast the result to a suiting integer before negating the number, otherwise we'll trigger a warning. Signed-off-by: Erik Faye-Lund <[email protected]> Reviewed-by: Eric Anholt <[email protected]>
* meson: add nir tests to the compiler/nir test suiteEric Engestrom2019-08-141-2/+5
| | | | | | Signed-off-by: Eric Engestrom <[email protected]> Reviewed-by: Lionel Landwerlin <[email protected]> Reviewed-by: Eric Anholt <[email protected]>
* nir/algebraic: Reassociate shift-by-constant of shift-by-constantIan Romanick2019-08-141-1/+25
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | v2: After some review discussion with Alyssa, the replacements now correct account for cases where (b+c) >= bitsize. v3: Use a temporary to simplify the Python code quite a bit. Suggested by Jason. Haswell and all Gen8+ platforms had similar results. (Ice Lake shown) total instructions in shared programs: 16251155 -> 16249576 (<.01%) instructions in affected programs: 232627 -> 231048 (-0.68%) helped: 547 HURT: 1 helped stats (abs) min: 1 max: 15 x̄: 2.89 x̃: 3 helped stats (rel) min: 0.04% max: 7.84% x̄: 1.14% x̃: 1.06% HURT stats (abs) min: 2 max: 2 x̄: 2.00 x̃: 2 HURT stats (rel) min: 0.12% max: 0.12% x̄: 0.12% x̃: 0.12% 95% mean confidence interval for instructions value: -3.12 -2.65 95% mean confidence interval for instructions %-change: -1.20% -1.06% Instructions are helped. total cycles in shared programs: 365924392 -> 365372103 (-0.15%) cycles in affected programs: 59207053 -> 58654764 (-0.93%) helped: 497 HURT: 34 helped stats (abs) min: 1 max: 29300 x̄: 1118.16 x̃: 16 helped stats (rel) min: <.01% max: 10.59% x̄: 1.82% x̃: 1.82% HURT stats (abs) min: 2 max: 424 x̄: 101.03 x̃: 63 HURT stats (rel) min: 0.07% max: 46.17% x̄: 4.72% x̃: 2.06% 95% mean confidence interval for cycles value: -1426.41 -653.77 95% mean confidence interval for cycles %-change: -1.66% -1.15% Cycles are helped. total spills in shared programs: 8870 -> 8871 (0.01%) spills in affected programs: 104 -> 105 (0.96%) helped: 0 HURT: 1 Ivy Bridge and all pre-Gen7 platforms had similar results. (Ivy Bridge shown) total instructions in shared programs: 11956236 -> 11955635 (<.01%) instructions in affected programs: 94110 -> 93509 (-0.64%) helped: 106 HURT: 0 helped stats (abs) min: 1 max: 14 x̄: 5.67 x̃: 4 helped stats (rel) min: 0.12% max: 4.71% x̄: 1.96% x̃: 0.76% 95% mean confidence interval for instructions value: -6.62 -4.72 95% mean confidence interval for instructions %-change: -2.27% -1.64% Instructions are helped. total cycles in shared programs: 179296340 -> 178788044 (-0.28%) cycles in affected programs: 51009603 -> 50501307 (-1.00%) helped: 82 HURT: 7 helped stats (abs) min: 5 max: 27820 x̄: 6199.00 x̃: 16 helped stats (rel) min: 0.30% max: 8.16% x̄: 2.58% x̃: 3.11% HURT stats (abs) min: 2 max: 8 x̄: 3.14 x̃: 2 HURT stats (rel) min: 0.02% max: 1.40% x̄: 0.34% x̃: 0.10% 95% mean confidence interval for cycles value: -7649.38 -3773.00 95% mean confidence interval for cycles %-change: -2.71% -1.99% Cycles are helped. Reviewed-by: Alyssa Rosenzweig <[email protected]> [v2] Reviewed-by: Jason Ekstrand <[email protected]>
* nir/algebraic: Reassociate add-and-shift to be shift-and-addIan Romanick2019-08-141-0/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | A common thing in many shaders: uniform vs { vec4 bones[...]; }; ... x = some_calculation(bones[i + 0]); y = some_calculation(bones[i + 1]); z = some_calculation(bones[i + 2]); This turns into stuff like vec1 32 ssa_12 = iadd ssa_11, ssa_0 vec1 32 ssa_13 = ishl ssa_12, ssa_3 vec1 32 ssa_14 = intrinsic load_ssbo (ssa_7, ssa_13) (16, 4, 0) vec1 32 ssa_15 = iadd ssa_11, ssa_1 vec1 32 ssa_16 = ishl ssa_15, ssa_3 vec1 32 ssa_17 = intrinsic load_ssbo (ssa_7, ssa_16) (16, 4, 0) vec1 32 ssa_18 = iadd ssa_11, ssa_2 vec1 32 ssa_19 = ishl ssa_18, ssa_3 vec1 32 ssa_20 = intrinsic load_ssbo (ssa_7, ssa_19) (16, 4, 0) By reassociating the shift and the add, we can reduce this to vec1 32 ssa_12 = ishl ssa_11, ssa_3 vec1 32 ssa_13 = iadd ssa_12, ssa_0 vec1 32 ssa_14 = intrinsic load_ssbo (ssa_7, ssa_13) (16, 4, 0) vec1 32 ssa_16 = iadd ssa_12, ssa_1 vec1 32 ssa_17 = intrinsic load_ssbo (ssa_7, ssa_16) (16, 4, 0) vec1 32 ssa_19 = iadd ssa_12, ssa_2 vec1 32 ssa_20 = intrinsic load_ssbo (ssa_7, ssa_19) (16, 4, 0) v2: Add some commentary from Rhys Perry's nearly identical patch. All Intel platforms had similar results. (Ice Lake shown) total instructions in shared programs: 16277758 -> 16250704 (-0.17%) instructions in affected programs: 1440284 -> 1413230 (-1.88%) helped: 4920 HURT: 6 helped stats (abs) min: 1 max: 69 x̄: 5.50 x̃: 4 helped stats (rel) min: 0.10% max: 18.33% x̄: 2.21% x̃: 1.79% HURT stats (abs) min: 1 max: 12 x̄: 4.50 x̃: 3 HURT stats (rel) min: 0.18% max: 3.23% x̄: 1.91% x̃: 2.55% 95% mean confidence interval for instructions value: -5.67 -5.31 95% mean confidence interval for instructions %-change: -2.26% -2.16% Instructions are helped. total cycles in shared programs: 367118526 -> 365895358 (-0.33%) cycles in affected programs: 93504145 -> 92280977 (-1.31%) helped: 2754 HURT: 1269 helped stats (abs) min: 1 max: 47039 x̄: 460.66 x̃: 16 helped stats (rel) min: <.01% max: 34.93% x̄: 3.77% x̃: 1.12% HURT stats (abs) min: 1 max: 1500 x̄: 35.85 x̃: 9 HURT stats (rel) min: 0.01% max: 17.35% x̄: 2.18% x̃: 0.75% 95% mean confidence interval for cycles value: -387.31 -220.78 95% mean confidence interval for cycles %-change: -2.11% -1.68% Cycles are helped. LOST: 1 GAINED: 1 Reviewed-by: Alyssa Rosenzweig <[email protected]> Reviewed-by: Jason Ekstrand <[email protected]>
* nir/find_array_copies: Reject copies with mismatched lengthsAndrii Simiklit2019-08-141-4/+8
| | | | | | | | | | | | | | | | | copy_deref for wildcard dereferences requires the same arrays lengths otherwise it leads to a crash in optimizations like 'nir_opt_copy_prop_vars' because these optimizations expect 'copy_deref' just for arrays with the same lengths. v2: check was moved to 'try_match_deref' to fix aoa cases (Jason Ekstrand <[email protected]>) v3: -fixed comment -the condition merged with other one (Jason Ekstrand <[email protected]>) Reviewed-by: Jason Ekstrand <[email protected]> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111286 Signed-off-by: Andrii Simiklit <[email protected]>
* nir/range-analysis: Fail gracefully on non-SSA sourcesIan Romanick2019-08-141-0/+3
| | | | | Tested-by: Rob Clark <[email protected]> Reviewed-by: Eric Anholt <[email protected]>
* nir: add a pass to clamp gl_PointSize to a rangeIago Toral Quiroga2019-08-133-0/+127
| | | | | | | | | | | | | | | | | | | | | The OpenGL and OpenGL ES specs require that implementations clamp the value of gl_PointSize to an implementation-depedent range. This pass is useful for any GPU hardware that doesn't do this automatically for either one or both sides of the range, such as V3D. v2: - Turn into a generic NIR pass (Eric). - Make the pass work before lower I/O so we can use the deref variable to inspect if we are writing to gl_PointSize (Eric). - Make the pass take the range to clamp as parameter and allow it to clamp to both sides of the range or just one side. - Make the pass report progress. v3: - Fix copyright header (Eric) - use fmin/fmax instead of bcsel to clamp (Eric) Reviewed-by: Eric Anholt <[email protected]>
* nir: merge and extend nir_opt_move_comparisons and nir_opt_move_load_uboRhys Perry2019-08-125-149/+33
| | | | | | | | | | v2: add to series v3: update Makefile.sources v4: don't remove a comment and break statement v4: use nir_can_move_instr Signed-off-by: Rhys Perry <[email protected]> Reviewed-by: Eric Anholt <[email protected]>
* nir: replace nir_move_load_const() with nir_opt_sink()Rhys Perry2019-08-125-144/+236
| | | | | | | | | | | | | | | | | | | This is mostly the same as nir_move_load_const() but can also move undef instructions, comparisons and some intrinsics (being careful with loops). v2: actually delete nir_move_load_const.c v3: fix nir_opt_sink() usage in freedreno v3: update Makefile.sources v4: replace get_move_def with nir_can_move_instr and nir_instr_ssa_def v4: handle if uses v4: fix handling of nested loops v5: re-write adjust_block_for_loops v5: re-write setting of use_block for if uses Signed-off-by: Rhys Perry <[email protected]> Co-authored-by: Daniel Schürmann <[email protected]> Reviewed-by: Eric Anholt <[email protected]>
* compiler: add SYSTEM_VALUE_TESS_LEVEL_OUTER/INNER_DEFAULTMarek Olšák2019-08-123-0/+12
| | | | | | TCS system values for internal passthru TCS, needed by radeonsi NIR support Reviewed-by: Connor Abbott <[email protected]>
* compiler: add SYSTEM_VALUE_USER_DATA_AMDMarek Olšák2019-08-123-0/+8
| | | | for internal radeonsi shaders
* compiler: add shader_info.cs.user_data_components_amdMarek Olšák2019-08-121-0/+1
|
* compiler: add shader_info.vs.blit_sgprs_amdMarek Olšák2019-08-121-0/+7
| | | | for internal radeonsi shaders
* compiler: add ACCESS_STREAM_CACHE_POLICYMarek Olšák2019-08-121-0/+3
| | | | | | radeonsi will use this. Reviewed-by: Connor Abbott <[email protected]>
* glsl: Optimize the SoftFP64 shader when first creating it.Kenneth Graunke2019-08-121-0/+13
| | | | | | | | | | | | | By optimizing the shader before inlining, we avoid having to redo this work for each inlined copy of a function. It should also reduce the memory consumption a bit. This cuts the KHR-GL46.arrays_of_arrays_gl.SubroutineFunctionCalls2 runtime by 25% on my Icelake. That test compiles many shaders, which contain large types (dmat4) and division (expensive operations). Reviewed-by: Timothy Arceri <[email protected]> Reviewed-by: Matt Turner <[email protected]>
* spirv: Drop lower_workgroup_access_to_offsetsCaio Marcelo de Oliveira Filho2019-08-103-136/+14
| | | | | | | | Intel drivers are not using this anymore, and turnip still don't have Compute Shaders, so won't make a difference to stop using this option. Reviewed-by: Jason Ekstrand <[email protected]> Acked-by: Rob Clark <[email protected]>
* nir: add nir_lower_to_explicit()Rhys Perry2019-08-086-3/+208
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | v2: use glsl_type_size_align_func v2: move get_explicit_type() to glsl_types.cpp/nir_types.cpp v2: use align() instead of util_align_npot() v2: pack arrays a bit tighter v2: rename mem_* to field_* v2: don't attempt to handle when struct offsets are already set v2: use column_type() instead of recreating it v2: use a branch instead of |= in nir_lower_to_explicit_impl() v2: assign locations to variables and update shared_size and num_shared v2: allow the pass to be used with nir_var_{shader_temp,function_temp} v4: rebase v5: add TODO v5: small formatting changes v5: remove incorrect assert in get_explicit_type() v5: rename to nir_lower_vars_to_explicit_types v5: correctly update progress when only variables are updated v5: rename get_explicit_type() to get_explicit_shared_type() v5: add comment explaining how get_explicit_shared_type() is different v5: update cast strides v6: update progress when lowering nir_var_function_temp variables v6: formatting changes v6: add more detailed documentation comment for get_explicit_shared_type v6: rename get_explicit_shared_type to get_explicit_type_for_size_align v7: fix comment in nir_lower_vars_to_explicit_types_impl() Signed-off-by: Rhys Perry <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]> (v5) Reviewed-by: Jason Ekstrand <[email protected]>
* nir/lower_explicit_io: add nir_var_mem_shared supportRhys Perry2019-08-081-25/+52
| | | | | | | | | v2: require nir_address_format_32bit_offset instead v3: don't call nir_intrinsic_set_access() for shared atomics Signed-off-by: Rhys Perry <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]> Reviewed-by: Jason Ekstrand <[email protected]>
* spirv: fixup signatureErik Faye-Lund2019-08-082-3/+3
| | | | | | | | | This avoids a warning on some compiler, complaining about implicitly casting the function-pointer. Signed-off-by: Erik Faye-Lund <[email protected]> Fixes: d482a8f "spirv: Update the OpenCL.std.h header" Acked-by: Eric Engestrom <[email protected]>
* nir/builder: Add nir_b2iConnor Abbott2019-08-061-0/+12
| | | | | | Same as nir_b2f but for integers. Reviewed-by: Marek Olšák <[email protected]>
* nir: add atomic_inc_wrap/atomic_dec_wrap image intrinsicsPierre-Eric Pelloux-Prayer2019-08-062-1/+11
| | | | Reviewed-by: Marek Olšák <[email protected]>
* glsl: add EXT_shader_image_load_store new image functionsPierre-Eric Pelloux-Prayer2019-08-062-0/+14
| | | | | | | | This extension has 2 functions that are missing from the ARB versions: - imageAtomicIncWrap - imageAtomicDecWrap Reviewed-by: Marek Olšák <[email protected]>
* glsl: add EXT_shader_image_load_store keywords to lexerPierre-Eric Pelloux-Prayer2019-08-061-36/+36
| | | | | | All of them already existed for ARB_shader_image_load_store. Reviewed-by: Marek Olšák <[email protected]>
* glsl: add size qualifiers from EXT_shader_image_load_storePierre-Eric Pelloux-Prayer2019-08-062-39/+93
| | | | Reviewed-by: Marek Olšák <[email protected]>
* glsl: handle differences between ARB/EXT versions of shader_image_load_storePierre-Eric Pelloux-Prayer2019-08-064-3/+21
| | | | Reviewed-by: Marek Olšák <[email protected]>
* nir/spirv: Fix gl_BaseVertex for non-indexed draws for OpenGLAntia Puentes2019-08-061-2/+5
| | | | | | | | | Lowers BaseVertex to the correct system value for OpenGL. v2: use options->environment rather than adding a new flag to spirv_to_nir_options Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* glcpp: use pre-expansion line number for __LINE__Jonathan Marek2019-08-061-4/+7
| | | | | | | | | | | Fixes the following deqp tests: dEQP-GLES2.functional.shaders.preprocessor.predefined_macros.line_2_* It don't see the spec requiring this, but it seems to be better, as the clang preprocessor for example has this behavior. Signed-off-by: Jonathan Marek <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* nir/algebraic: Use value range analysis to eliminate useless unary opsIan Romanick2019-08-051-2/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Sandy Bridge is the big winner because it lies at something of a crossroads. It supports a fairly high OpenGL version, and it still has the old style math box. The high OpenGL version means a lot more shaders can run on it. The old style math box means extra moves are necessary to resolve source modifiers on operands to complex math instructions like COS, SQRT, and RCP. v2: Remove a couple patterns that are now redundant. All Gen7+ platforms had similar results. (Ice Lake shown) total instructions in shared programs: 16282006 -> 16278207 (-0.02%) instructions in affected programs: 174555 -> 170756 (-2.18%) helped: 661 HURT: 0 helped stats (abs) min: 1 max: 36 x̄: 5.75 x̃: 3 helped stats (rel) min: 0.06% max: 23.68% x̄: 2.81% x̃: 1.94% 95% mean confidence interval for instructions value: -6.16 -5.34 95% mean confidence interval for instructions %-change: -3.02% -2.60% Instructions are helped. total cycles in shared programs: 367168597 -> 367134284 (<.01%) cycles in affected programs: 1105276 -> 1070963 (-3.10%) helped: 460 HURT: 150 helped stats (abs) min: 1 max: 568 x̄: 96.60 x̃: 82 helped stats (rel) min: 0.02% max: 32.50% x̄: 7.99% x̃: 4.27% HURT stats (abs) min: 1 max: 901 x̄: 67.49 x̃: 39 HURT stats (rel) min: 0.07% max: 20.00% x̄: 4.90% x̃: 4.22% 95% mean confidence interval for cycles value: -65.68 -46.82 95% mean confidence interval for cycles %-change: -5.59% -4.05% Cycles are helped. Sandy Bridge total instructions in shared programs: 10824272 -> 10802557 (-0.20%) instructions in affected programs: 1237988 -> 1216273 (-1.75%) helped: 8199 HURT: 0 helped stats (abs) min: 1 max: 41 x̄: 2.65 x̃: 2 helped stats (rel) min: 0.12% max: 20.00% x̄: 2.04% x̃: 1.73% 95% mean confidence interval for instructions value: -2.70 -2.59 95% mean confidence interval for instructions %-change: -2.07% -2.00% Instructions are helped. total cycles in shared programs: 154009894 -> 153843598 (-0.11%) cycles in affected programs: 10650486 -> 10484190 (-1.56%) helped: 4973 HURT: 1533 helped stats (abs) min: 1 max: 3904 x̄: 40.20 x̃: 20 helped stats (rel) min: 0.02% max: 41.72% x̄: 2.63% x̃: 1.67% HURT stats (abs) min: 1 max: 453 x̄: 21.94 x̃: 8 HURT stats (rel) min: 0.02% max: 41.91% x̄: 1.54% x̃: 0.58% 95% mean confidence interval for cycles value: -28.02 -23.10 95% mean confidence interval for cycles %-change: -1.74% -1.56% Cycles are helped. LOST: 0 GAINED: 2 GM45 and Iron Lake had similar results. (Iron Lake shown) total instructions in shared programs: 8135196 -> 8134888 (<.01%) instructions in affected programs: 31920 -> 31612 (-0.96%) helped: 169 HURT: 0 helped stats (abs) min: 1 max: 12 x̄: 1.82 x̃: 2 helped stats (rel) min: 0.43% max: 3.23% x̄: 1.23% x̃: 1.16% 95% mean confidence interval for instructions value: -2.01 -1.64 95% mean confidence interval for instructions %-change: -1.32% -1.15% Instructions are helped. total cycles in shared programs: 188575724 -> 188574092 (<.01%) cycles in affected programs: 406840 -> 405208 (-0.40%) helped: 169 HURT: 0 helped stats (abs) min: 4 max: 72 x̄: 9.66 x̃: 10 helped stats (rel) min: 0.07% max: 2.16% x̄: 0.57% x̃: 0.47% 95% mean confidence interval for cycles value: -10.72 -8.59 95% mean confidence interval for cycles %-change: -0.63% -0.50% Cycles are helped. Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* nir/algebraic: Use value range analysis to convert fmin to fsatIan Romanick2019-08-051-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | All Gen8+ platforms had similar results. (Ice Lake shown) total instructions in shared programs: 16297320 -> 16282006 (-0.09%) instructions in affected programs: 2434498 -> 2419184 (-0.63%) helped: 8091 HURT: 1 helped stats (abs) min: 1 max: 51 x̄: 1.89 x̃: 2 helped stats (rel) min: 0.04% max: 14.29% x̄: 0.98% x̃: 0.95% HURT stats (abs) min: 7 max: 7 x̄: 7.00 x̃: 7 HURT stats (rel) min: 0.28% max: 0.28% x̄: 0.28% x̃: 0.28% 95% mean confidence interval for instructions value: -1.94 -1.85 95% mean confidence interval for instructions %-change: -0.99% -0.96% Instructions are helped. total cycles in shared programs: 367221624 -> 367168597 (-0.01%) cycles in affected programs: 126409635 -> 126356608 (-0.04%) helped: 5612 HURT: 1023 helped stats (abs) min: 1 max: 2332 x̄: 31.11 x̃: 16 helped stats (rel) min: <.01% max: 30.31% x̄: 1.69% x̃: 1.42% HURT stats (abs) min: 1 max: 2372 x̄: 118.84 x̃: 16 HURT stats (rel) min: <.01% max: 46.98% x̄: 1.46% x̃: 0.35% 95% mean confidence interval for cycles value: -11.52 -4.46 95% mean confidence interval for cycles %-change: -1.26% -1.14% Cycles are helped. total spills in shared programs: 8868 -> 8870 (0.02%) spills in affected programs: 28 -> 30 (7.14%) helped: 0 HURT: 1 total fills in shared programs: 21903 -> 21904 (<.01%) fills in affected programs: 42 -> 43 (2.38%) helped: 0 HURT: 1 Haswell total instructions in shared programs: 13353925 -> 13338728 (-0.11%) instructions in affected programs: 2265850 -> 2250653 (-0.67%) helped: 8127 HURT: 5 helped stats (abs) min: 1 max: 51 x̄: 1.88 x̃: 2 helped stats (rel) min: 0.04% max: 20.00% x̄: 1.13% x̃: 1.07% HURT stats (abs) min: 5 max: 16 x̄: 9.00 x̃: 6 HURT stats (rel) min: 0.19% max: 0.52% x̄: 0.35% x̃: 0.28% 95% mean confidence interval for instructions value: -1.91 -1.83 95% mean confidence interval for instructions %-change: -1.15% -1.11% Instructions are helped. total cycles in shared programs: 375535444 -> 375536343 (<.01%) cycles in affected programs: 131206582 -> 131207481 (<.01%) helped: 5590 HURT: 1055 helped stats (abs) min: 1 max: 2844 x̄: 34.15 x̃: 16 helped stats (rel) min: <.01% max: 21.57% x̄: 2.08% x̃: 1.60% HURT stats (abs) min: 1 max: 2487 x̄: 181.78 x̃: 21 HURT stats (rel) min: <.01% max: 40.66% x̄: 1.96% x̃: 0.37% 95% mean confidence interval for cycles value: -4.74 5.01 95% mean confidence interval for cycles %-change: -1.51% -1.37% Inconclusive result (value mean confidence interval includes 0). total spills in shared programs: 23401 -> 23407 (0.03%) spills in affected programs: 248 -> 254 (2.42%) helped: 2 HURT: 5 total fills in shared programs: 34850 -> 34845 (-0.01%) fills in affected programs: 383 -> 378 (-1.31%) helped: 2 HURT: 5 Ivy Bridge total instructions in shared programs: 11975423 -> 11968117 (-0.06%) instructions in affected programs: 845703 -> 838397 (-0.86%) helped: 4071 HURT: 0 helped stats (abs) min: 1 max: 51 x̄: 1.79 x̃: 1 helped stats (rel) min: 0.08% max: 8.21% x̄: 1.04% x̃: 0.93% 95% mean confidence interval for instructions value: -1.87 -1.71 95% mean confidence interval for instructions %-change: -1.06% -1.02% Instructions are helped. total cycles in shared programs: 179674318 -> 179635552 (-0.02%) cycles in affected programs: 5100065 -> 5061299 (-0.76%) helped: 2650 HURT: 611 helped stats (abs) min: 1 max: 900 x̄: 21.85 x̃: 16 helped stats (rel) min: <.01% max: 21.55% x̄: 2.39% x̃: 1.40% HURT stats (abs) min: 1 max: 1841 x̄: 31.33 x̃: 6 HURT stats (rel) min: <.01% max: 58.71% x̄: 1.64% x̃: 0.37% 95% mean confidence interval for cycles value: -14.14 -9.64 95% mean confidence interval for cycles %-change: -1.75% -1.52% Cycles are helped. LOST: 3 GAINED: 7 Sandy Bridge total instructions in shared programs: 10828844 -> 10824272 (-0.04%) instructions in affected programs: 525678 -> 521106 (-0.87%) helped: 2386 HURT: 0 helped stats (abs) min: 1 max: 51 x̄: 1.92 x̃: 2 helped stats (rel) min: 0.11% max: 7.96% x̄: 1.05% x̃: 0.94% 95% mean confidence interval for instructions value: -2.04 -1.80 95% mean confidence interval for instructions %-change: -1.08% -1.03% Instructions are helped. total cycles in shared programs: 154024591 -> 154009894 (<.01%) cycles in affected programs: 4005766 -> 3991069 (-0.37%) helped: 1245 HURT: 506 helped stats (abs) min: 1 max: 585 x̄: 21.07 x̃: 16 helped stats (rel) min: 0.02% max: 11.57% x̄: 1.98% x̃: 0.83% HURT stats (abs) min: 1 max: 639 x̄: 22.81 x̃: 6 HURT stats (rel) min: 0.01% max: 26.21% x̄: 1.07% x̃: 0.26% 95% mean confidence interval for cycles value: -10.57 -6.21 95% mean confidence interval for cycles %-change: -1.23% -0.97% Cycles are helped. GM45 and Iron Lake had similar results. (Iron Lake shown) total instructions in shared programs: 8137248 -> 8135196 (-0.03%) instructions in affected programs: 148322 -> 146270 (-1.38%) helped: 992 HURT: 0 helped stats (abs) min: 1 max: 32 x̄: 2.07 x̃: 2 helped stats (rel) min: 0.41% max: 9.73% x̄: 1.74% x̃: 1.51% 95% mean confidence interval for instructions value: -2.16 -1.98 95% mean confidence interval for instructions %-change: -1.80% -1.67% Instructions are helped. total cycles in shared programs: 188583424 -> 188575724 (<.01%) cycles in affected programs: 4409620 -> 4401920 (-0.17%) helped: 956 HURT: 6 helped stats (abs) min: 2 max: 168 x̄: 8.09 x̃: 8 helped stats (rel) min: 0.04% max: 6.76% x̄: 0.27% x̃: 0.18% HURT stats (abs) min: 6 max: 6 x̄: 6.00 x̃: 6 HURT stats (rel) min: 0.10% max: 0.10% x̄: 0.10% x̃: 0.10% 95% mean confidence interval for cycles value: -8.41 -7.60 95% mean confidence interval for cycles %-change: -0.29% -0.25% Cycles are helped. Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* nir/algebraic: Use value range analysis to eliminate tautological comparesIan Romanick2019-08-051-21/+21
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | It's only one application on one platform (Haswell) that's affected, but spills and fills increase quite dramatically. :( All Gen8+ platforms had similar results. (Ice Lake shown) total instructions in shared programs: 16320850 -> 16297320 (-0.14%) instructions in affected programs: 448012 -> 424482 (-5.25%) helped: 1938 HURT: 0 helped stats (abs) min: 2 max: 264 x̄: 12.14 x̃: 10 helped stats (rel) min: 0.35% max: 43.75% x̄: 5.85% x̃: 5.38% 95% mean confidence interval for instructions value: -12.80 -11.48 95% mean confidence interval for instructions %-change: -5.99% -5.72% Instructions are helped. total cycles in shared programs: 367496943 -> 367221624 (-0.07%) cycles in affected programs: 8557232 -> 8281913 (-3.22%) helped: 1907 HURT: 26 helped stats (abs) min: 4 max: 12802 x̄: 147.21 x̃: 48 helped stats (rel) min: 0.03% max: 75.85% x̄: 5.55% x̃: 3.94% HURT stats (abs) min: 4 max: 1870 x̄: 208.23 x̃: 20 HURT stats (rel) min: 0.16% max: 32.11% x̄: 8.31% x̃: 0.79% 95% mean confidence interval for cycles value: -165.38 -119.48 95% mean confidence interval for cycles %-change: -5.68% -5.04% Cycles are helped. LOST: 1 GAINED: 0 Haswell total instructions in shared programs: 13374211 -> 13353925 (-0.15%) instructions in affected programs: 349868 -> 329582 (-5.80%) helped: 1669 HURT: 1 helped stats (abs) min: 1 max: 264 x̄: 12.57 x̃: 10 helped stats (rel) min: 0.12% max: 46.81% x̄: 6.86% x̃: 6.49% HURT stats (abs) min: 700 max: 700 x̄: 700.00 x̃: 700 HURT stats (rel) min: 64.34% max: 64.34% x̄: 64.34% x̃: 64.34% 95% mean confidence interval for instructions value: -13.25 -11.04 95% mean confidence interval for instructions %-change: -7.01% -6.63% Instructions are helped. total cycles in shared programs: 375763544 -> 375535444 (-0.06%) cycles in affected programs: 6932686 -> 6704586 (-3.29%) helped: 1622 HURT: 48 helped stats (abs) min: 2 max: 12229 x̄: 148.31 x̃: 68 helped stats (rel) min: 0.06% max: 74.03% x̄: 5.94% x̃: 4.12% HURT stats (abs) min: 3 max: 7451 x̄: 259.44 x̃: 41 HURT stats (rel) min: 0.05% max: 54.99% x̄: 8.52% x̃: 2.88% 95% mean confidence interval for cycles value: -159.86 -113.31 95% mean confidence interval for cycles %-change: -5.86% -5.18% Cycles are helped. total spills in shared programs: 23258 -> 23401 (0.61%) spills in affected programs: 54 -> 197 (264.81%) helped: 4 HURT: 2 total fills in shared programs: 34775 -> 34850 (0.22%) fills in affected programs: 52 -> 127 (144.23%) helped: 4 HURT: 1 LOST: 5 GAINED: 0 Ivy Bridge total instructions in shared programs: 11996051 -> 11977964 (-0.15%) instructions in affected programs: 346679 -> 328592 (-5.22%) helped: 1508 HURT: 0 helped stats (abs) min: 2 max: 198 x̄: 11.99 x̃: 10 helped stats (rel) min: 0.26% max: 19.83% x̄: 5.73% x̃: 5.43% 95% mean confidence interval for instructions value: -12.65 -11.34 95% mean confidence interval for instructions %-change: -5.86% -5.60% Instructions are helped. total cycles in shared programs: 179891389 -> 179691339 (-0.11%) cycles in affected programs: 7869479 -> 7669429 (-2.54%) helped: 1485 HURT: 23 helped stats (abs) min: 1 max: 12615 x̄: 136.16 x̃: 54 helped stats (rel) min: 0.02% max: 71.84% x̄: 4.69% x̃: 3.49% HURT stats (abs) min: 1 max: 403 x̄: 93.48 x̃: 6 HURT stats (rel) min: 0.04% max: 34.01% x̄: 8.68% x̃: 0.81% 95% mean confidence interval for cycles value: -154.59 -110.73 95% mean confidence interval for cycles %-change: -4.79% -4.19% Cycles are helped. Sandy Bridge total instructions in shared programs: 10829247 -> 10828844 (<.01%) instructions in affected programs: 21258 -> 20855 (-1.90%) helped: 88 HURT: 0 helped stats (abs) min: 2 max: 17 x̄: 4.58 x̃: 5 helped stats (rel) min: 0.52% max: 3.92% x̄: 2.05% x̃: 2.21% 95% mean confidence interval for instructions value: -5.03 -4.13 95% mean confidence interval for instructions %-change: -2.21% -1.89% Instructions are helped. total cycles in shared programs: 154035437 -> 154024591 (<.01%) cycles in affected programs: 430176 -> 419330 (-2.52%) helped: 78 HURT: 10 helped stats (abs) min: 2 max: 4649 x̄: 143.06 x̃: 32 helped stats (rel) min: 0.05% max: 6.02% x̄: 2.03% x̃: 1.07% HURT stats (abs) min: 3 max: 265 x̄: 31.30 x̃: 6 HURT stats (rel) min: 0.10% max: 8.67% x̄: 1.03% x̃: 0.21% 95% mean confidence interval for cycles value: -232.53 -13.97 95% mean confidence interval for cycles %-change: -2.13% -1.23% Cycles are helped. Iron Lake and GM45 had similar results. (Iron Lake shown) total instructions in shared programs: 8137402 -> 8137248 (<.01%) instructions in affected programs: 2280 -> 2126 (-6.75%) helped: 10 HURT: 0 helped stats (abs) min: 12 max: 19 x̄: 15.40 x̃: 15 helped stats (rel) min: 3.90% max: 11.73% x̄: 7.19% x̃: 6.95% 95% mean confidence interval for instructions value: -17.69 -13.11 95% mean confidence interval for instructions %-change: -8.99% -5.39% Instructions are helped. total cycles in shared programs: 188538716 -> 188583424 (0.02%) cycles in affected programs: 69326 -> 114034 (64.49%) helped: 0 HURT: 10 HURT stats (abs) min: 2068 max: 7686 x̄: 4470.80 x̃: 4870 HURT stats (rel) min: 27.20% max: 173.66% x̄: 69.55% x̃: 59.41% 95% mean confidence interval for cycles value: 2830.86 6110.74 95% mean confidence interval for cycles %-change: 39.18% 99.91% Cycles are HURT. Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* nir/algebraic: Use value range analysis to eliminate tautological compares ↵Ian Romanick2019-08-051-0/+28
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | not used by if-statements This just eliminates tautological / contradictory compares that are used for bcsel and other non-if-statement cases. If-statements are not affected because removing flow control can cause the i965 instrution scheduler to create some very long live ranges resulting in unncessary spilling. This causes some shaders to fall of a performance cliff. Since many small if-statements are already flattened to bcsel, this optimization covers more than 68% of the possible cases (2417 shaders helped for instructions on Skylake vs. 3554). v2: Reorder and add whitespace to make the relationship between the patterns more obvious. Suggested by Caio. All Gen7+ platforms had similar results. (Ice Lake shown) total instructions in shared programs: 16333474 -> 16322028 (-0.07%) instructions in affected programs: 438559 -> 427113 (-2.61%) helped: 1765 HURT: 0 helped stats (abs) min: 1 max: 275 x̄: 6.48 x̃: 4 helped stats (rel) min: 0.20% max: 36.36% x̄: 4.07% x̃: 1.82% 95% mean confidence interval for instructions value: -6.87 -6.10 95% mean confidence interval for instructions %-change: -4.30% -3.84% Instructions are helped. total cycles in shared programs: 367608554 -> 367511103 (-0.03%) cycles in affected programs: 8368829 -> 8271378 (-1.16%) helped: 1541 HURT: 129 helped stats (abs) min: 1 max: 4468 x̄: 66.78 x̃: 39 helped stats (rel) min: 0.01% max: 45.69% x̄: 4.10% x̃: 2.17% HURT stats (abs) min: 1 max: 973 x̄: 42.25 x̃: 10 HURT stats (rel) min: 0.02% max: 64.39% x̄: 2.15% x̃: 0.60% 95% mean confidence interval for cycles value: -64.90 -51.81 95% mean confidence interval for cycles %-change: -3.89% -3.36% Cycles are helped. total spills in shared programs: 8867 -> 8868 (0.01%) spills in affected programs: 18 -> 19 (5.56%) helped: 0 HURT: 1 total fills in shared programs: 21900 -> 21903 (0.01%) fills in affected programs: 78 -> 81 (3.85%) helped: 0 HURT: 1 All Gen6 and earlier platforms had similar results. (Sandy Bridge shown) total instructions in shared programs: 10829877 -> 10829247 (<.01%) instructions in affected programs: 30240 -> 29610 (-2.08%) helped: 177 HURT: 0 helped stats (abs) min: 1 max: 15 x̄: 3.56 x̃: 3 helped stats (rel) min: 0.37% max: 17.39% x̄: 2.68% x̃: 1.94% 95% mean confidence interval for instructions value: -3.93 -3.18 95% mean confidence interval for instructions %-change: -3.04% -2.32% Instructions are helped. total cycles in shared programs: 154036580 -> 154035437 (<.01%) cycles in affected programs: 352402 -> 351259 (-0.32%) helped: 96 HURT: 28 helped stats (abs) min: 1 max: 128 x̄: 14.73 x̃: 6 helped stats (rel) min: 0.03% max: 24.00% x̄: 1.51% x̃: 0.46% HURT stats (abs) min: 1 max: 117 x̄: 9.68 x̃: 4 HURT stats (rel) min: 0.03% max: 2.24% x̄: 0.43% x̃: 0.23% 95% mean confidence interval for cycles value: -13.40 -5.03 95% mean confidence interval for cycles %-change: -1.62% -0.53% Cycles are helped. Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* nir/range-analysis: Range tracking for ffma and flrpIan Romanick2019-08-051-114/+138
| | | | | | | | | A similar technique could be used for fmin3, fmax3, and fmid3. This could be squashed with the previous commit. I kept it separate to ease review. Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* nir/range-analysis: Range tracking for bcselIan Romanick2019-08-051-0/+77
| | | | | | | | | | | This could be squashed with the previous commit. I kept it separate to ease review. v2: Add some missing cases. Use nir_src_is_const helper. Both suggested by Caio. Use a table for mapping source ranges to a result range. Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* nir/range-analysis: Tighten the range of fsat based on the range of its sourceIan Romanick2019-08-051-1/+22
| | | | | | | | | | This could be squashed with the previous commit. I kept it separate to ease review. v2: Use a switch statement and add more comments. Both suggested by Caio. Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-28 07:52:52 +0000