summaryrefslogtreecommitdiffstats
path: root/src/glsl/nir
Commit message (Collapse)AuthorAgeFilesLines
* nir: Fix output swizzle in get_mul_for_srcIago Toral Quiroga2015-05-281-10/+9
| | | | | | | | When we compute the output swizzle we want to consider the number of components in the add operation. So far we were using the writemask of the multiplication for this instead, which is not correct. Reviewed-by: Jason Ekstrand <[email protected]>
* nir: Remove sRGB colorspace conversion round-trip.Matt Turner2015-05-221-0/+2
| | | | | | | | | | | | | | | | | | Some shaders in Civilization V and Beyond Earth do pow(pow(x, 2.2), 0.454545) which is converting to and from sRGB colorspace. A more general rule that replaces pow(pow(a, b), c) with pow(a, b * c) actually regresses two shaders in Sun Temple in which the result of the inner pow is used twice, once by another pow and once by another instruction. Also, since 2.2 * 0.454545 isn't exactly one, the more general pattern would have still left us with a pow, and I'm 2.2 * 0.454545 percent sure that's not what they want. instructions in affected programs: 934 -> 886 (-5.14%) helped: 16
* nir: Get rid of the array elements parameter on load/store intrinsicsJason Ekstrand2015-05-202-12/+9
| | | | | | | | | | | | | Previously, we used intrinsic->const_index[1] to represent "the number of array elements to load" for load/store intrinsics. However, this set to 1 by every pass that ever creates a load/store intrinsic. Also, while it might make some sense for registers, it makes no sense whatsoever in SSA. On top of that, the i965 backend was the only backend to ever support it; freedreno and vc4 just assert that it's always 1. Let's just delete it. Signed-off-by: Jason Ekstrand <[email protected]> Reviewed-by: Connor Abbott <[email protected]> Reviewed-by: Rob Clark <[email protected]>
* nir: Translate memory barrier intrinsics from GLSL IR.Francisco Jerez2015-05-121-0/+4
| | | | | Reviewed-by: Connor Abbott <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* nir: Translate image load, store and atomic intrinsics from GLSL IR.Francisco Jerez2015-05-121-11/+115
| | | | | | | v2: Undefine coordinate components not applicable to the target. Reviewed-by: Connor Abbott <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* nir: Fix indexing of atomic counter arrays with a constant value.Francisco Jerez2015-05-121-1/+2
| | | | | Reviewed-by: Connor Abbott <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* nir: Add memory barrier intrinsic.Francisco Jerez2015-05-121-0/+7
| | | | | Reviewed-by: Connor Abbott <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* nir: Define image load, store and atomic intrinsics.Francisco Jerez2015-05-121-0/+27
| | | | | | | v2: Undefine coordinate components not applicable to the target. Reviewed-by: Connor Abbott <[email protected]> Reviewed-by: Kenneth Graunke <[email protected]>
* nir: fix sampler lowering pass for arraysTapani Pälli2015-05-121-19/+12
| | | | | | | | | | | | | | | | | | This fixes bugs with special cases where we have arrays of structures containing samplers or arrays of samplers. I've verified that patch results in calculating same index value as returned by _mesa_get_sampler_uniform_value for IR. Patch makes following ES3 conformance test pass: ES3-CTS.shaders.struct.uniform.sampler_array_fragment v2: remove unnecessary comment (Topi) simplify changes and the overall code (Jason) Signed-off-by: Tapani Pälli <[email protected]> Reviewed-by: Jason Ekstrand <[email protected]> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=90114
* nir: Fix aggressive typos in nir_from_ssa.c.Kenneth Graunke2015-05-081-5/+5
| | | | | | s/agressive/aggressive/g Trivial.
* nir/search: Save/restore the variables_seen bitmask when matchingJason Ekstrand2015-05-081-0/+12
| | | | | | | | | | | | | Shader-db results on Broadwell: total instructions in shared programs: 7152330 -> 7137006 (-0.21%) instructions in affected programs: 1330548 -> 1315224 (-1.15%) helped: 5797 HURT: 76 GAINED: 0 LOST: 8 Reviewed-by: Connor Abbott <[email protected]>
* nir/search: Assert that variable id's are in rangeJason Ekstrand2015-05-081-0/+1
| | | | Reviewed-by: Connor Abbott <[email protected]>
* nir/search: handle explicitly sized sources in match_valueJason Ekstrand2015-05-081-8/+8
| | | | | | | | | | Previously, this case was being handled in match_expression prior to calling match_value. However, there is really no good reason for this given that match_value has all of the information it needs. Also, they weren't being handled properly in the commutative case and putting it in match_value gives us that for free. Reviewed-by: Connor Abbott <[email protected]>
* nir/nir: Use a linked list instead of a hash set for use/def setsJason Ekstrand2015-05-0814-306/+281
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This commit switches us from the current setup of using hash sets for use/def sets to using linked lists. Doing so should save us quite a bit of memory because we aren't carrying around 3 hash sets per register and 2 per SSA value. It should also save us CPU time because adding/removing things from use/def sets is 4 pointer manipulations instead of a hash lookup. Running shader-db 50 times with USE_NIR=0, NIR, and NIR + use/def lists: GLSL IR Only: 586.4 +/- 1.653833 NIR with hash sets: 675.4 +/- 2.502108 NIR + use/def lists: 641.2 +/- 1.557043 I also ran a memory usage experiment with Ken's patch to delete GLSL IR and keep NIR. This patch cuts an aditional 42.9 MiB of ralloc'd memory over and above what we gained by deleting the GLSL IR on the same dota trace. On the code complexity side of things, some things are now much easier and others are a bit harder. One of the operations we perform constantly in optimization passes is to replace one source with another. Due to the fact that an instruction can use the same SSA value multiple times, we had to iterate through the sources of the instruction and determine if the use we were replacing was the only one before removing it from the set of uses. With this patch, uses are per-source not per-instruction so we can just remove it safely. On the other hand, trying to iterate over all of the instructions that use a given value is more difficult. Fortunately, the two places we do that are the ffma peephole where it doesn't matter and GCM where we already gracefully handle duplicates visits to an instruction. Another aspect here is that using linked lists in this way can be tricky to get right. With sets, things were quite forgiving and the worst that happened if you didn't properly remove a use was that it would get caught in the validator. With linked lists, it can lead to linked list corruption which can be harder to track. However, we do just as much validation of the linked lists as we did of the sets so the validator should still catch these problems. While working on this series, the vast majority of the bugs I had to fix were caught by assertions. I don't think the lists are going to be that much worse than the sets. Reviewed-by: Connor Abbott <[email protected]>
* nir: Use nir_instr_rewrite_src in copy propagationJason Ekstrand2015-05-081-61/+10
| | | | | | | We were rolling our own rewrite_src variant in copy-propagation. Let's stop doing that and use the ones in core NIR. Reviewed-by: Connor Abbott <[email protected]>
* nir: Add a function for rewriting the condition of an if statementJason Ekstrand2015-05-082-0/+23
| | | | Reviewed-by: Connor Abbott <[email protected]>
* nir: Add and use initializer #defines for nir_src and nir_destJason Ekstrand2015-05-086-18/+15
| | | | Reviewed-by: Connor Abbott <[email protected]>
* nir: Modernize the out-of-SSA passJason Ekstrand2015-05-081-103/+36
| | | | | | | | | The out-of-SSA pass was one of the first passes written when getting SSA up-and-going (for obvious reasons). As such, it came before a lot of the nifty SSA-based helpers were introduced. This commit modernizes it so that we're no longer doing nearly as much manual banging on use/def sets. Reviewed-by: Connor Abbott <[email protected]>
* nir/validate: Validate SSA def parent instructionsJason Ekstrand2015-05-081-0/+2
| | | | Reviewed-by: Connor Abbott <[email protected]>
* nir: Delete all traces of nir_op_flogIan Romanick2015-05-082-7/+0
| | | | | | | | Nothing produces it, and nothing can consume it. Signed-off-by: Ian Romanick <[email protected]> Reviewed-by: Matt Turner <[email protected]> Acked-by: Jason Ekstrand <[email protected]>
* nir: Don't produce nir_op_flog from GLSL IRIan Romanick2015-05-081-1/+1
| | | | | | | | | All paths that produce GLSL IR for NIR lower ir_unop_log. All paths that consume NIR will explode if they geta nir_op_flog. Signed-off-by: Ian Romanick <[email protected]> Reviewed-by: Matt Turner <[email protected]> Acked-by: Jason Ekstrand <[email protected]>
* nir: Delete all traces of nir_op_fexpIan Romanick2015-05-082-8/+0
| | | | | | | | Nothing produces it, and nothing can consume it. Signed-off-by: Ian Romanick <[email protected]> Reviewed-by: Matt Turner <[email protected]> Acked-by: Jason Ekstrand <[email protected]>
* nir: Don't produce nir_op_fexp from GLSL IRIan Romanick2015-05-081-1/+1
| | | | | | | | | All paths that produce GLSL IR for NIR lower ir_unop_exp. All paths that consume NIR will explode if they geta nir_op_fexp. Signed-off-by: Ian Romanick <[email protected]> Reviewed-by: Matt Turner <[email protected]> Acked-by: Jason Ekstrand <[email protected]>
* nir: Allow feq/fne/ieq/ine to be optimized with inot.Matt Turner2015-05-071-0/+4
| | | | | | | | instructions in affected programs: 380 -> 376 (-1.05%) helped: 2 Reviewed-by: Jordan Justen <[email protected]> Reviewed-by: Glenn Kennard <[email protected]>
* nir: Recognize (a < c || b < c) as min(a, b) < c.Matt Turner2015-05-071-0/+2
| | | | | | | | | | | | | | ... and (a >= c) || (b >= c) as max(a, b) >= c. Similar to commit 97e6c1b9. total instructions in shared programs: 6182276 -> 6182180 (-0.00%) instructions in affected programs: 6400 -> 6304 (-1.50%) helped: 68 HURT: 4 Reviewed-by: Jordan Justen <[email protected]> Reviewed-by: Glenn Kennard <[email protected]>
* nir: Recognize trivial min/max.Matt Turner2015-05-071-0/+6
| | | | | | | No changes, but does prevent some regressions in the next commit. Reviewed-by: Jordan Justen <[email protected]> Reviewed-by: Glenn Kennard <[email protected]>
* nir: Recognize i2b(b2i(x)) as x.Matt Turner2015-05-071-0/+1
| | | | | | | | | | Helps the same set of programs as the previous commit. instructions in affected programs: 4490 -> 4346 (-3.21%) helped: 8 Reviewed-by: Jordan Justen <[email protected]> Reviewed-by: Glenn Kennard <[email protected]>
* nir: Recognize imul(b2i(a), b2i(b)) as a logical AND.Matt Turner2015-05-071-0/+1
| | | | | | | | | | | | Four shaders in Unreal 4's Sun Temple are helped, and gain SIMD16 because we avoid an integer multiplication. instructions in affected programs: 2353 -> 2245 (-4.59%) helped: 4 GAINED: 4 Reviewed-by: Jordan Justen <[email protected]> Reviewed-by: Glenn Kennard <[email protected]>
* Fix a few typosZoë Blade2015-04-271-1/+1
| | | | Reviewed-by: Francisco Jerez <[email protected]>
* nir: Transform pow(x, 4) into (x*x)*(x*x).Matt Turner2015-04-241-0/+1
|
* nir/lower_source_mods: Don't propagate register sourcesJason Ekstrand2015-04-221-0/+7
| | | | | | | | | The nir_lower_source_mods pass does a weak form of copy propagation to clean up all of the mov-with-negate's that get generated. However, we weren't properly checking that the sources were SSA and so we could end up moving a register read which is not, in general, valid. Reviewed-by: Connor Abbott <[email protected]>
* nir: Rewrite instr_rewrite_srcJason Ekstrand2015-04-221-24/+28
| | | | | | | The old code wasn't correctly handling the case where the new value of the source contains an indirect. Reviewed-by: Connor Abbott <[email protected]>
* nir/locals_to_regs: Hanadle indirect accesses of length-1 arraysJason Ekstrand2015-04-221-0/+8
| | | | Reviewed-by: Connor Abbott <[email protected]>
* nir/locals_to_regs: Initialize registers with constant initializersJason Ekstrand2015-04-221-0/+103
| | | | Reviewed-by: Connor Abbott <[email protected]>
* nir/locals_to_regs: Pass around the nir_shader rather than a void * mem_ctxJason Ekstrand2015-04-221-13/+13
| | | | Reviewed-by: Connor Abbott <[email protected]>
* nir: Add a simple growing array data structureJason Ekstrand2015-04-221-0/+96
| | | | Reviewed-by: Connor Abbott <[email protected]>
* nir/types: Make glsl_get_length smarterJason Ekstrand2015-04-224-55/+8
| | | | | | | | | | | | | | | | | | Previously, this function returned the number of elements for structures and arrays and 0 for everything else. In NIR, this is almost never what you want because we also treat matricies as arrays so you have to special-case constantly. This commit glsl_get_length treat matrices as an array of columns by returning the number of columns instead of 0 This also fixes a bug in locals_to_regs caused by not checking for the matrix case in one place. v2: Only special-case for matrices and return a length of 0 for vectors as we did before. This was needed to not break the TGSI-based drivers and doesn't really affect NIR at the moment. Reviewed-by: Connor Abbott <[email protected]> Tested-by: Rob Clark <[email protected]>
* nir: Move get_const_initializer_load from vars_to_ssa to NIR coreJason Ekstrand2015-04-223-62/+65
| | | | Reviewed-by: Connor Abbott <[email protected]>
* nir/lower_vars_to_ssa: Pass around the nir_shader instead of a void mem_ctxJason Ekstrand2015-04-221-14/+14
| | | | Reviewed-by: Connor Abbott <[email protected]>
* nir/print: Print the closing paren on load_const instructionsJason Ekstrand2015-04-221-0/+2
| | | | Reviewed-by: Connor Abbott <[email protected]>
* nir/tex: Use the correct return size for query_levels and lodJason Ekstrand2015-04-221-1/+4
| | | | Reviewed-by: Connor Abbott <[email protected]>
* nir: Refactor tex_instr_dest_size to use a switch statementJason Ekstrand2015-04-221-5/+8
| | | | Reviewed-by: Connor Abbott <[email protected]>
* nir/lower_vars_to_ssa: Actually look for indirects when determining aliasingJason Ekstrand2015-04-221-0/+4
| | | | Reviewed-by: Connor Abbott <[email protected]>
* nir: Allow abs/neg in select peephole pass.Matt Turner2015-04-171-1/+3
| | | | | | | | | | | total instructions in shared programs: 4314531 -> 4308949 (-0.13%) instructions in affected programs: 429085 -> 423503 (-1.30%) helped: 1680 HURT: 0 GAINED: 0 LOST: 111 Reviewed-by: Jason Ekstrand <[email protected]>
* nir/builder: add nir_builder_insert_after_instr()Rob Clark2015-04-171-2/+18
| | | | | | | For lowering if/else, I need a way to insert at the end of the previous block. Signed-off-by: Rob Clark <[email protected]>
* nir: Convert the if-test for num_inputs == 2 to an assertionIan Romanick2015-04-161-2/+2
| | | | | | | | | Suggested by Jason on a different patch after some comments / questions by Ilia. Signed-off-by: Ian Romanick <[email protected]> Reviewed-by: Jason Ekstrand <[email protected]> Reviewed-by: Connor Abbott <[email protected]>
* nir: Try commutative sources in CSEIan Romanick2015-04-151-9/+18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Shader-db results: GM45 NIR: total instructions in shared programs: 4082044 -> 4081919 (-0.00%) instructions in affected programs: 27609 -> 27484 (-0.45%) helped: 44 Iron Lake NIR: total instructions in shared programs: 5678776 -> 5678646 (-0.00%) instructions in affected programs: 27406 -> 27276 (-0.47%) helped: 45 Sandy Bridge NIR: total instructions in shared programs: 7329995 -> 7329096 (-0.01%) instructions in affected programs: 142035 -> 141136 (-0.63%) helped: 406 HURT: 19 Ivy Bridge NIR: total instructions in shared programs: 6769314 -> 6768359 (-0.01%) instructions in affected programs: 140820 -> 139865 (-0.68%) helped: 423 HURT: 2 Haswell NIR: total instructions in shared programs: 6183693 -> 6183298 (-0.01%) instructions in affected programs: 96538 -> 96143 (-0.41%) helped: 303 HURT: 4 Broadwell NIR: total instructions in shared programs: 7501711 -> 7498170 (-0.05%) instructions in affected programs: 266403 -> 262862 (-1.33%) helped: 705 HURT: 5 GAINED: 4 v2: Rebase on top of Connor's fix. v3: Convert the if-test for num_inputs == 2 to an assertion. Suggested by Jason after some comments / questions by Ilia. Signed-off-by: Ian Romanick <[email protected]> Reviewed-by: Jordan Justen <[email protected]> [v1] Reviewed-by: Jason Ekstrand <[email protected]> Cc: Connor Abbott <[email protected]>
* nir: Fix typo in "ushr by 0" algebraic replacementIan Romanick2015-04-141-1/+1
| | | | | | | | Signed-off-by: Ian Romanick <[email protected]> Reviewed-by: Jordan Justen <[email protected]> Reviewed-by: Jason Ekstrand <[email protected]> Reviewed-by: Connor Abbott <[email protected]> Cc: "10.5" <[email protected]>
* nir: Silence unused parameter warningsIan Romanick2015-04-142-1/+3
| | | | | | | | | | | | | | | | | | | nir/nir.h: In function 'nir_validate_shader': nir/nir.h:1567:56: warning: unused parameter 'shader' [-Wunused-parameter] static inline void nir_validate_shader(nir_shader *shader) { } ^ nir/nir_opt_cse.c: In function 'src_is_ssa': nir/nir_opt_cse.c:165:32: warning: unused parameter 'data' [-Wunused-parameter] src_is_ssa(nir_src *src, void *data) ^ nir/nir_opt_cse.c: In function 'dest_is_ssa': nir/nir_opt_cse.c:171:35: warning: unused parameter 'data' [-Wunused-parameter] dest_is_ssa(nir_dest *dest, void *data) ^ Signed-off-by: Ian Romanick <[email protected]> Reviewed-by: Jordan Justen <[email protected]> Reviewed-by: Connor Abbott <[email protected]>
* nir/cse: fix bug with comparing non-per-component sourcesConnor Abbott2015-04-141-10/+7
| | | | | | | | | | | | We weren't comparing the right number of components when checking swizzles. Use nir_ssa_alu_instr_num_src_components() to do the right thing. No piglit regressions, and no fixes either. Reviewed-by: Ian Romanick <[email protected]> Reviewed-by: Jason Ekstrand <[email protected]> Signed-off-by: Connor Abbott <[email protected]>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-28 02:44:45 +0000