summaryrefslogtreecommitdiffstats
path: root/src/glsl/ir_optimization.h
Commit message (Collapse)AuthorAgeFilesLines
* glsl: Vectorize multiple scalar assignmentsMatt Turner2014-01-211-0/+1
| | | | | | | | | | Reduces vertex shader instruction counts in DOTA2 by 6.42%, L4D2 by 4.61%, and CS:GO by 5.71%. total instructions in shared programs: 1500153 -> 1498191 (-0.13%) instructions in affected programs: 59919 -> 57957 (-3.27%) Reviewed-by: Ian Romanick <[email protected]>
* glsl/loops: Get rid of lower_bounded_loops and ir_loop::normative_bound.Paul Berry2013-12-091-1/+0
| | | | | | | | Now that loop_controls no longer creates normatively bound loops, there is no need for ir_loop::normative_bound or the lower_bounded_loops pass. Reviewed-by: Ian Romanick <[email protected]>
* glsl/loops: consolidate bounded loop handling into a lowering pass.Paul Berry2013-12-091-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Previously, all of the back-ends (ir_to_mesa, st_glsl_to_tgsi, and the i965 fs and vec4 visitors) had nearly identical logic for handling bounded loops. This replaces the duplicate logic with an equivalent lowering pass that is used by all the back-ends. Note: on i965, there is a slight increase in instruction count. For example, a loop like this: for (int i = 0; i < 100; i++) { total += i; } would previously compile down to this (vec4) native code: mov(8) g4<1>.xD 0D mov(8) g8<1>.xD 0D loop: cmp.ge.f0(8) null g8<4;4,1>.xD 100D (+f0) break(8) add(8) g5<1>.xD g5<4;4,1>.xD g4<4;4,1>.xD add(8) g8<1>.xD g8<4;4,1>.xD 1D add(8) g4<1>.xD g4<4;4,1>.xD 1D while(8) loop After this patch, the "(+f0) break(8)" turns into: (+f0) if(8) break(8) endif(8) because the back-end isn't smart enough to recognize that "if (condition) break;" can be done using a conditional break instruction. However, it should be relatively easy for a future peephole optimization to properly optimize this. Reviewed-by: Jordan Justen <[email protected]> Reviewed-by: Ian Romanick <[email protected]>
* glsl: Add a CSE pass.Eric Anholt2013-11-011-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | This only operates on constant/uniform values for now, because otherwise I'd have to deal with killing my available CSE entries when assignments happen, and getting even this working in the tree ir was painful enough. As is, it has the following effect in shader-db: total instructions in shared programs: 1524077 -> 1521964 (-0.14%) instructions in affected programs: 50629 -> 48516 (-4.17%) GAINED: 0 LOST: 0 And, for tropics, that accounts for most of the effect, the FPS improvement is 11.67% +/- 0.72% (n=3). v2: Use read_only field of the variable, manually check the lod_info union members, use get_num_operands(), rename cse_operands_visitor to is_cse_candidate_visitor, move all is-a-candidate logic to that function, and call it before checking for CSE on a given rvalue, more comments, use private keyword. Reviewed-by: Paul Berry <[email protected]>
* glsl: Add ldexp_to_arith lowering pass.Matt Turner2013-09-171-0/+1
| | | | Reviewed-by: Paul Berry <[email protected]>
* glsl: don't eliminate texcoords that can be set by GL_COORD_REPLACEMarek Olšák2013-08-181-1/+1
| | | | | | | | | Tested by examining generated TGSI shaders from piglit/glsl-routing. Cc: [email protected] Reviewed-by: Henri Verbeet <[email protected]> Tested-by: Henri Verbeet <[email protected]> Reviewed-by: Ian Romanick <[email protected]>
* glsl/linker: Properly pack GS input varyings.Paul Berry2013-08-011-1/+1
| | | | | | | | Since geometry shader inputs are arrays (where the array index indicates which vertex is being examined), varying packing needs to treat them differently. Reviewed-by: Ian Romanick <[email protected]>
* glsl: Remove comma at end of enumerator list.Vinson Lee2013-07-171-1/+1
| | | | | | | | | Fixes this build error on OpenBSD 5.3. In file included from ../../src/mesa/main/ff_fragment_shader.cpp:53: ./../glsl/ir_optimization.h:64: error: comma at end of enumerator list Signed-off-by: Vinson Lee <[email protected]>
* glsl/linker: eliminate unused and set-but-unused built-in varyingsMarek Olšák2013-07-021-0/+4
| | | | | | | | | | | | | This eliminates built-in varyings such as gl_Color, gl_SecondaryColor, gl_TexCoord, and gl_FogFragCoord if they are unused by the next stage or not written at all (e.g. gl_TexCoord elements). The gl_TexCoord array is broken down into separate vec4s if needed. v2: - use a switch statement in varying_info_visitor::visit(ir_variable*) - use snprintf - disable the optimization for GLES2 Reviewed-by: Ian Romanick <[email protected]>
* glsl linker: remove interface block instance namesJordan Justen2013-05-231-0/+1
| | | | | | | | Convert interface blocks with instance names into flat interface blocks without an instance name. Signed-off-by: Jordan Justen <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* glsl: Add lowering pass for ir_triop_vector_insertIan Romanick2013-05-131-0/+1
| | | | | | | | | | | | | | | | | | This will eventually replace do_vec_index_to_cond_assign. This lowering pass is called in all the places where do_vec_index_to_cond_assign or do_vec_index_to_swizzle is called. v2: Use WRITEMASK_* instead of integer literals. Use a more concise method of generating broadcast_index. Both suggested by Eric. v3: Use a series of scalar compares instead of a single vector compare. Suggested by Eric and Ken. It still uses 'if (cond) v.x = y;' instead of conditional assignments because ir_builder doesn't do conditional assignments, and I'd rather keep the code simple. Signed-off-by: Ian Romanick <[email protected]> Reviewed-by: Eric Anholt <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* glsl: Add a pass to flip matrix/vector multiplies to use dot products.Kenneth Graunke2013-05-121-0/+1
| | | | | | | | | | | | | | | | | | | | | | This pass flips (matrix * vector) operations to (vector * matrixTranspose) for certain built-in matrices (currently gl_ModelViewProjectionMatrix and gl_TextureMatrix). This is equivalent, but results in dot products rather than multiplies and adds. On some hardware, this is more efficient. This pass is conditionalized on ctx->mvp_with_dp4, the flag drivers set to indicate they prefer dot products. Improves performance in Lightsmark by 1.01131% +/- 0.162069% (n = 10) on a Haswell GT2 system. Passes Piglit on Ivybridge. v2: Use struct gl_shader_compiler_options instead of plumbing through another boolean flag for this purpose. Signed-off-by: Kenneth Graunke <[email protected]> Reviewed-by: Ian Romanick <[email protected]> Reviewed-by: Eric Anholt <[email protected]>
* glsl: Pass struct shader_compiler_options into do_common_optimization.Kenneth Graunke2013-05-121-1/+2
| | | | | | | | | | | | | do_common_optimization may need to make choices about whether to emit certain kinds of instructions. gl_context::ShaderCompilerOptions contains exactly that information, so it makes sense to pass it in. Rather than passing the whole array, pass the structure for the stage that's currently being worked on. Signed-off-by: Kenneth Graunke <[email protected]> Reviewed-by: Ian Romanick <[email protected]> Reviewed-by: Eric Anholt <[email protected]>
* glsl: Add a pass to lower bitfield-insert into bfm+bfi.Matt Turner2013-05-061-0/+1
| | | | | | | | | | i965/Gen7+ and Radeon/Evergreen+ have bfm/bfi instructions to implement bitfieldInsert() from ARB_gpu_shader5. v2: Add ir_binop_bfm and ir_triop_bfi to st_glsl_to_tgsi.cpp. Remove spurious temporary assignment and dereference. Reviewed-by: Chris Forbes <[email protected]>
* glsl: Add an optimization pass to flatten simple nested if blocks.Kenneth Graunke2013-04-041-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | GLBenchmark 2.7's shaders contain conditional blocks like: if (x) { if (y) { ... } } where the outer conditional's then clause contains exactly one statement (the nested if) and there are no else clauses. This can easily be optimized into: if (x && y) { ... } This saves a few instructions in GLBenchmark 2.7: total instructions in shared programs: 11833 -> 11649 (-1.55%) instructions in affected programs: 8234 -> 8050 (-2.23%) It also helps CS:GO slightly (-0.05%/-0.22%). More importantly, however, it simplifies the control flow graph, which could enable other optimizations. Signed-off-by: Kenneth Graunke <[email protected]> Reviewed-by: Matt Turner <[email protected]> Reviewed-by: Eric Anholt <[email protected]>
* glsl: Convert mix() to use a new ir_triop_lrp opcode.Kenneth Graunke2013-02-281-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | Many GPUs have an instruction to do linear interpolation which is more efficient than simply performing the algebra necessary (two multiplies, an add, and a subtract). Pattern matching or peepholing this is more desirable, but can be tricky. By using an opcode, we can at least make shaders which use the mix() built-in get the more efficient behavior. Currently, all consumers lower ir_triop_lrp. Subsequent patches will actually generate different code. v2 [mattst88]: - Add LRP_TO_ARITH flag to ir_to_mesa.cpp. Will be removed in a subsequent patch and ir_triop_lrp translated directly. v3 [mattst88]: - Move changes from the next patch to opt_algebraic.cpp to accept 3-src operations. Reviewed-by: Matt Turner <[email protected]> Reviewed-by: Eric Anholt <[email protected]> Signed-off-by: Kenneth Graunke <[email protected]>
* glsl: Add support for lowering 4x8 pack/unpack operationsMatt Turner2013-01-251-0/+6
| | | | | | | Lower them to arithmetic and bit manipulation expressions. Reviewed-by: Chad Versace <[email protected]> Reviewed-by: Paul Berry <[email protected]>
* glsl: Add lowering pass for GLSL ES 3.00 pack/unpack operations (v4)Chad Versace2013-01-241-0/+20
| | | | | | | | | | | | | | | | Lower them to arithmetic and bit manipulation expressions. v2: Rewrite using ir_builder [for idr]. v3: Comment typos. [for mattst88] v4: Fix arithmetic error in comments. Factor out a shift instruction. Don't heap allocate factory.instructions. [for paul] Reviewed-by: Ian Romanick <[email protected]> (v2) Reviewed-by: Matt Tuner <[email protected]> (v3) Reviewed-by: Paul Berry <[email protected]> (v4) Signed-off-by: Chad Versace <[email protected]>
* glsl: Add a lowering pass for packing varyings.Paul Berry2012-12-141-0/+3
| | | | | | | | | | | | | | This lowering pass generates GLSL code that manually packs varyings into vec4 slots, for the benefit of back-ends that don't support packed varyings natively. No functional change--the lowering pass is not yet used. Reviewed-by: Eric Anholt <[email protected]> v2: Don't use ir_hierarchical_visitor--just loop over instructions directly. Also, make the names of the packed varyings include the names of the original varyings that were packed into them.
* glsl/lower_clip_distance: Update symbol table.Paul Berry2012-12-141-1/+1
| | | | | | | | | | | | | This patch modifies the clip distance lowering pass so that the new symbol it generates (glClipDistanceMESA) is added to the shader's symbol table. This will allow a later patch to modify the linker so that it finds transform feedback varyings using the symbol table rather than having to iterate through all the declarations in the shader. Reviewed-by: Eric Anholt <[email protected]> Reviewed-by: Ian Romanick <[email protected]>
* glsl: Add a lowering pass to turn complicated UBO references to vector loads.Eric Anholt2012-08-071-0/+1
| | | | | | | | | | | v2: Reduce the impenetrable code in emit_ubo_loads() by 23 lines by keeping the ir_variable as the variable part of the offset from handle_rvalue(), and track the constant offsets from that with a plain old integer value, avoiding a bunch of temporary variables in the array and struct handling. Also, fix file description doxygen. v3: Fix a row vs col typo, and fix spelling in a comment. Reviewed-by: Eric Anholt <[email protected]>
* glsl: Fix lower_discard_flow prototype mismatch.José Fonseca2012-05-151-1/+1
| | | | Should fix MSVC link failure.
* glsl: Implement the GLSL 1.30+ discard control flow rule in GLSL IR.Eric Anholt2012-05-141-0/+1
| | | | | | | Previously, I tried implementing this in the i965 driver, but did so in a way that violated the intent of the spec, and broke Tropics. Reviewed-by: Kenneth Graunke <[email protected]>
* glsl: Add an array splitting pass.Eric Anholt2012-04-111-0/+1
| | | | | | | | | | | | | | | | | I've had this code laying around almost done for a long time. The idea is like opt_structure_splitting, that we've got a bunch of transforms at the GLSL IR level that only understand scalars and vectors, which just skip complicated dereferences. While driver backends may manage some optimization after they split matrices up themselves, it would be better to bring all of our optimization to bear on the problem. While I wasn't expecting changes quite yet, a few programs end up winning: a gstreamer convolution shader, and the Humus dynamic branching demo: Total instructions: 269430 -> 269342 3/2148 programs affected (0.1%) 1498 -> 1410 instructions in affected programs (5.9% reduction)
* glsl: Add a lowering pass to remove reads of shader output variables.Vincent Lejeune2012-01-061-0/+1
| | | | | | | | | This is similar to Gallium's existing glsl_to_tgsi::remove_output_read lowering pass, but done entirely inside the GLSL compiler. Signed-off-by: Vincent Lejeune <[email protected]> Signed-off-by: Kenneth Graunke <[email protected]> Signed-off-by: Dave Airlie <[email protected]>
* glsl: Add uniform_locations_assigned parameter to do_dead_code opt passIan Romanick2011-10-251-2/+4
| | | | | | | | | | | | | | | | | Setting this flag prevents declarations of uniforms from being removed from the IR. Since the IR is directly used by several API functions that query uniforms in shaders, uniform declarations cannot be removed after the locations have been set. However, it should still be safe to reorder the declarations (this is not tested). Signed-off-by: Ian Romanick <[email protected]> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=41980 Tested-by: Brian Paul <[email protected]> Reviewed-by: Bryan Cain <[email protected]> Cc: Vinson Lee <[email protected]> Cc: José Fonseca <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]> Reviewed-by: Yuanhan Liu <[email protected]>
* glsl: Implement a lowering pass for gl_ClipDistance.Paul Berry2011-09-231-0/+1
| | | | | | | | | | | | | | | | | | | In i965 GEN6+ (and I suspect most other hardware), gl_ClipDistance needs to be laid out as a pair of vec4's (the first containing clip distances 0-3, and the second containing clip distances 4-7). However, it is declared in GLSL as an array of 8 floats. This lowering pass acts at the GLSL level, modifying the declaration of gl_ClipDistance so that it is an array of vec4's rather than an array of floats, and renaming it to gl_ClipDistanceMESA. In addition, it modifies all accesses to the array so that they access the appropiate component of one of the vec4's. Since some hardware may not internally represent gl_ClipDistance as a pair of vec4's, this lowering pass is optional. To enable it, set the LowerClipDistance flag in gl_shader_compiler_options to true. Reviewed-by: Kenneth Graunke <[email protected]>
* glsl: Use a separate div_to_mul_rcp lowering flag for integers.Bryan Cain2011-08-311-6/+7
| | | | | | | | | | | | | | Using multiply and reciprocal for integer division involves potentially lossy floating point conversions. This is okay for older GPUs that represent integers as floating point, but undesirable for GPUs with native integer division instructions. TGSI, for example, has UDIV/IDIV instructions for integer division, so it makes sense to handle this directly. Likewise for i965. Reviewed-by: Ian Romanick <[email protected]> Signed-off-by: Bryan Cain <[email protected]> Signed-off-by: Kenneth Graunke <[email protected]>
* glsl: Factor out code that generates block of index comparisonsIan Romanick2011-07-231-0/+4
| | | | Reviewed-by: Eric Anholt <[email protected]>
* glsl: Remove unused function prototypes.Paul Berry2011-07-081-2/+0
| | | | | No functional change. Remove prototypes for do_mod_to_fract() and do_sub_to_add_neg(), which haven't existed since November 2010.
* glsl: Add a new opt_copy_propagation variant that does it channel-wise.Eric Anholt2011-02-041-0/+1
| | | | | | | | | | This patch cleans up many of the extra copies in GLSL IR introduced by i965's scalarizing passes. It doesn't result in a statistically significant performance difference on nexuiz high settings (n=3) or my demo (n=10), due to brw_fs.cpp's register coalescing covering most of those extra moves anyway. However, it does make the debug of wine's GLSL shaders much more tractable, and reduces instruction count of glsl-fs-convolution-2 from 376 to 288.
* glsl: Support if-flattening beyond a given maximum nesting depth.Kenneth Graunke2010-12-271-1/+1
| | | | | | | | | | | This adds a new optional max_depth parameter (defaulting to 0) to lower_if_to_cond_assign, and makes the pass only flatten if-statements nested deeper than that. By default, all if-statements will be flattened, just like before. This patch also renames do_if_to_cond_assign to lower_if_to_cond_assign, to match the new naming conventions.
* glsl: Lower ir_binop_pow to a sequence of EXP2 and LOG2Ian Romanick2010-12-011-2/+3
|
* glsl: Add a lowering pass to move discards out of if-statements.Kenneth Graunke2010-12-011-0/+1
| | | | | | | This should allow lower_if_to_cond_assign to work in the presence of discards, fixing bug #31690 and likely #31983. NOTE: This is a candidate for the 7.9 branch.
* glsl: Add an optimization pass to simplify discards.Kenneth Graunke2010-12-011-0/+1
| | | | NOTE: This is a candidate for the 7.9 branch.
* glsl: Combine many instruction lowering passes into one.Kenneth Graunke2010-11-191-2/+8
| | | | | | | This should save on the overhead of tree-walking and provide a convenient place to add more instruction lowering in the future. Signed-off-by: Ian Romanick <[email protected]>
* glsl: Add ir_quadop_vector expressionIan Romanick2010-11-191-0/+1
| | | | | | | | | | The vector operator collects 2, 3, or 4 scalar components into a vector. Doing this has several advantages. First, it will make ud-chain tracking for components of vectors much easier. Second, a later optimization pass could collect scalars into vectors to allow generation of SWZ instructions (or similar as operands to other instructions on R200 and i915). It also enables an easy way to generate IR for SWZ instructions in the ARB_vertex_program assembler.
* glsl: Add a lowering pass for texture projection.Eric Anholt2010-09-301-0/+1
|
* glsl2: Add flags to enable variable index loweringIan Romanick2010-09-171-1/+2
|
* glsl: add pass to lower variable array indexing to conditional assignmentsLuca Barbieri2010-09-171-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | Currenly GLSL happily generates indirect addressing of any kind of arrays. Unfortunately DirectX 9 GPUs are not guaranteed to support any of them in general. This pass fixes that by lowering such constructs to a binary search on the values, followed at the end by vectorized generation of equality masks, and 4 conditional assignments for each mask generation. Note that this requires the ir_binop_equal change so that we can emit SEQ to generate the boolean masks. Unfortunately, ir_structure_splitting is too dumb to turn the resulting constant array references to individual variables, so this will need to be added too before this pass can actually be effective for temps. Several patches in the glsl2-lower-variable-indexing were squashed into this commit. These patches fix bugs in Luca's original implementation, and the individual patches can be seen in that branch. This was done to aid bisecting in the future. Signed-off-by: Ian Romanick <[email protected]>
* glsl2: Add pass to remove redundant jumpsIan Romanick2010-09-131-0/+1
|
* glsl: add continue/break/return unification/elimination pass (v2)Luca Barbieri2010-09-131-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Changes in v2: - Base class renamed to ir_control_flow_visitor - Tried to comply with coding style This is a new pass that supersedes ir_if_return and "lowers" jumps to if/else structures. Currently it causes no regressions on softpipe and nv40, but I'm not sure whether the piglit glsl tests are thorough enough, so consider this experimental. It can be asked to: 1. Pull jumps out of ifs where possible 2. Remove all "continue"s, replacing them with an "execute flag" 3. Replace all "break" with a single conditional one at the end of the loop 4. Replace all "return"s with a single return at the end of the function, for the main function and/or other functions This gives several great benefits: 1. All functions can be inlined after this pass 2. nv40 and other pre-DX10 chips without "continue" can be supported 3. nv30 and other pre-DX10 chips with no control flow at all are better supported Note that for full effect we should also teach the unroller to unroll loops with a fixed maximum number of iterations but with the canonical conditional "break" that this pass will insert if asked to. Continues are lowered by adding a per-loop "execute flag", initialized to TRUE, that when cleared inhibits all execution until the end of the loop. Breaks are lowered to continues, plus setting a "break flag" that is checked at the end of the loop, and trigger the unique "break". Returns are lowered to breaks/continues, plus adding a "return flag" that causes loops to break again out of their enclosing loops until all the loops are exited: then the "execute flag" logic will ignore everything until the end of the function. Note that "continue" and "return" can also be implemented by adding a dummy loop and using break. However, this is bad for hardware with limited nesting depth, and prevents further optimization, and thus is not currently performed.
* glsl2: Add lowering pass to remove noise opcodesIan Romanick2010-09-091-0/+1
|
* glsl: add several EmitNo* options, and MaxUnrollIterationsLuca Barbieri2010-09-081-1/+1
| | | | | | | | | This increases the chance that GLSL programs will actually work. Note that continues and returns are not yet lowered, so linking will just fail if not supported. Signed-off-by: Ian Romanick <[email protected]>
* glsl2: Add a pass to strip out noop swizzles.Eric Anholt2010-08-131-0/+1
| | | | | | With the glsl2-965 branch, the optimization of glsl-algebraic-rcp-rcp regressed due to noop swizzles hiding information from ir_algebraic. This cleans up those noop swizzles for us.
* glsl2: Move the common optimization passes to a helper function.Eric Anholt2010-08-131-0/+2
| | | | | These are passes that we expect all codegen to be happy with. The other lowering passes for Mesa IR are moved to the Mesa IR generator.
* glsl2: Add a pass to transform ir_binop_sub to add(op0, neg(op1))Eric Anholt2010-08-091-0/+1
| | | | | | All the current HW backends transform subtract to adding the negation, so I haven't bothered peepholing it back out in Mesa IR. This allows some subtract of subtract to get removed in ir_algebraic.
* glsl2: Add constant propagation.Eric Anholt2010-08-091-0/+1
| | | | | | | | Whereas constant folding evaluates constant expressions at rvalue nodes, constant propagation tracks constant components of vectors across execution to replace (possibly swizzled) variable dereferences with constant values, triggering possible constant folding or reduced variable liveness.
* glsl2: Add a pass to convert exp and log to exp2 and log2.Eric Anholt2010-08-051-0/+1
| | | | | | | | | Fixes ir_to_mesa handling of unop_log, which used the weird ARB_vp LOG opcode that doesn't do what we want. This also lets the multiplication coefficients in there get constant-folded, possibly. Fixes: glsl-fs-log
* ir_structure_splitting: New pass to chop structures into their components.Eric Anholt2010-08-051-0/+1
| | | | | | | This doesn't do anything if your structure goes through an uninlined function call or if whole-structure assignment occurs. As such, the impact is limited, at least until we do some global copy propagation to reduce whole-structure assignment.
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-15 04:45:33 +0000