summaryrefslogtreecommitdiffstats
path: root/src/compiler
Commit message (Collapse)AuthorAgeFilesLines
* nir/lower_io: Add "explicit" IO loweringJason Ekstrand2019-01-082-0/+417
| | | | | | | | | | | This new pass is for lowering explicitly laid out memory coming in from SPIR-V or a similar source. It's quite a bit more complicated than the normal lower_io because we have to be able to handle matrices. The way the stride information is stored for matrices is awkward and dealing with row-major matrices is especially painful. Reviewed-by: Alejandro Piñeiro <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* nir/validate: Allow array derefs on vectors in more modesJason Ekstrand2019-01-081-4/+6
| | | | | Reviewed-by: Alejandro Piñeiro <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* nir/intrinsics: Add access flags to load/store_derefJason Ekstrand2019-01-082-4/+5
| | | | | Reviewed-by: Alejandro Piñeiro <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* nir/intrinsics: Allow deref sources to consume anythingJason Ekstrand2019-01-082-24/+28
| | | | | | | | | | | This commit adds a new num_components value for intrinsic sources of -1 which means that it consumes everything and the number of components effectively isn't validated. This is useful for deref sources which just take the result of the deref and we leave it up to the driver to decide what that size should be. Reviewed-by: Alejandro Piñeiro <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* nir/validate: Allow derefs in phi nodesJason Ekstrand2019-01-081-1/+0
| | | | | | | | | | | We added this assert when first moving derefs over to instructions to ensure that deref chains could go all the way back to the variables. Now that we're going to start using derefs for things that we can do variable pointers on such as UBOs and SSBOs, we need to be able to run derefs through phi nodes, selects, and basically anything else. Reviewed-by: Alejandro Piñeiro <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* nir/remove_dead_variables: Properly handle deref castsJason Ekstrand2019-01-081-0/+3
| | | | | | | | | | We already detect any incomplete deref chains (where the deref is used for something other than another deref or a load/store) and flag the variable as used thanks to deref_used_for_not_store. All that's left to do is to properly skip casts when cleaning up. Reviewed-by: Alejandro Piñeiro <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* nir/deref: Skip over casts in fixup_deref_modesJason Ekstrand2019-01-081-0/+2
| | | | | | | | | | This pass is used when, for instance, we lazily change the mode of variables rather than replacing the variable with a new one. Since we only do this in cases where we know we have full deref chains, it's ok to just skip them in fixup_deref_modes. Reviewed-by: Alejandro Piñeiro <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* nir/deref: Support casts and ptr_as_array in comparisonsJason Ekstrand2019-01-081-7/+68
| | | | | | | | | | | | The code which constructs deref paths already gives you the path starting at the nearest deref_cast or deref_var. All we need to do for casts is handle the case where the start of the path isn't a deref_var. For ptr_as_array derefs, we just bail if we have any after the divergence point between the two derefs. We may be able to do better in the future but this works for now. Reviewed-by: Alejandro Piñeiro <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* nir/opt_deref: Properly optimize ptr_as_array derefsJason Ekstrand2019-01-081-6/+91
| | | | | | | | | | | | | | When handling casts, we can't blindly propagate the parent of a cast into a ptr_as_array deref because doing so might loose the stride information from the cast. Instead, before we can propagate into ptr_as_array derefs, we need to check that the cast is a cast of an array deref and that the stride matches. For other types of derefs, we can continue to propagate casts as normal because they don't need the stride. We also add an optimization which can combine a ptr_as_array deref with it parent if it is also an array deref of some form. Reviewed-by: Alejandro Piñeiro <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* nir/validate: Don't allow derefs in if conditionsJason Ekstrand2019-01-081-0/+6
| | | | Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* nir: Add a ptr_as_array deref typeJason Ekstrand2019-01-0812-13/+106
| | | | | | | | | | | | | | These correspond directly to SPIR-V's OpPtrAccessChain. As such, they treat whatever their parent gives them as if it's the first element in some array and dereferences that array. If the parent is, itself, an array deref, then the two indices can just be added together to get the final array deref. However, it can also be used in cases where what you have is a dereference to some random vec2 value somewhere. In this case, we require a cast before the ptr_as_array and use the ptr_stride field in the cast to provide a stride for the ptr_as_array derefs. Reviewed-by: Alejandro Piñeiro <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* nir: Move propagation of cast derefs to a new nir_opt_deref passJason Ekstrand2019-01-084-27/+72
| | | | | | | | | We're going to want to do more deref optimizations going forward and this gives us a central place to do them. Also, cast propagation will get a bit more complicated with the addition of ptr_as_array derefs. Reviewed-by: Alejandro Piñeiro <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* spirv: Propagate layout decorations to created glsl_typesJason Ekstrand2019-01-083-14/+78
| | | | | | | | | | | | | | | Instead of just storing the decorations in the vtn_type, propagate them all the way through to the glsl_type. For array strides, this means we need to handle them earlier so we break array stride handling into it's own function and explicitly call it for both pointer and array types. Due to type deduplication in the SPIR-V, we may have explicit layout decorations on all sorts of types that don't actually want them. In order to prevent these leaking into unfortunate places in NIR, we explicitly strip them off before creating NIR variables and when casting pointers to non-external memory. Reviewed-by: Alejandro Piñeiro <[email protected]>
* glsl_type: Add support for explicitly laid out matrices and arraysJason Ekstrand2019-01-0812-52/+254
| | | | | | | | | | | | | | | | | | | | | | SPIR-V allows for matrix and array types to be decorated with explicit byte stride decorations and matrix types to be decorated row- or column-major. This commit adds support to glsl_type to encode this information. Because this doesn't work nicely with std430 and std140 alignments, we add asserts to ensure that we don't use any of the std430 or std140 layout functions with explicitly laid out types. In SPIR-V, the layout information for matrices is applied to the parent struct member instead of to the matrix type itself. However, this is gets rather clumsy when you're walking derefs trying to compute offsets because, the moment you hit a matrix, you have to crawl back the deref chain and find the struct. Instead, we take the same path here as we've taken in spirv_to_nir and put the decorations on the matrix type itself. This also subtly adds support for strided vector types. These don't come up in SPIR-V directly but you can get one as the result of taking a column from a row-major matrix or a row from a column-major matrix. Reviewed-by: Alejandro Piñeiro <[email protected]>
* glsl_type: Simplify glsl_channel_typeJason Ekstrand2019-01-081-19/+10
| | | | | | | | | | This is C++ so we can just poke at the fields of glsl_type if we wish and calling get_instance is way easier and more reliable than handling each instance separately. While we're at it, we re-arrange the base type labels to match the enum order and add 8-bit type support. Reviewed-by: Alejandro Piñeiro <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* glsl_type: Add a C wrapper to get struct field offsetsJason Ekstrand2019-01-082-0/+10
| | | | | Reviewed-by: Alejandro Piñeiro <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* glsl_type: Drop the glsl_get_array_instance C helperJason Ekstrand2019-01-085-13/+3
| | | | | | | | It was added in bce6f9987522 even though it's completely redundant with glsl_array_type(). Reviewed-by: Alejandro Piñeiro <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* nir: Distinguish between normal uniforms and UBOsJason Ekstrand2019-01-0811-34/+40
| | | | | | | | | | | | | | | | Previously, NIR had a single nir_var_uniform mode used for atomic counters, UBOs, samplers, images, and normal uniforms. This commit splits this into nir_var_uniform and nir_var_ubo where nir_var_uniform is still a bit of a catch-all but the nir_var_ubo is specific to UBOs. While we're at it, we also rename shader_storage to ssbo to follow the convention. We need this so that we can distinguish between normal uniforms and UBO access at the deref level without going all the way back variable and seeing if it has an interface type. Reviewed-by: Alejandro Piñeiro <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* nir: Allow storing to shader_storageJason Ekstrand2019-01-081-4/+2
| | | | | | | | | | I have no idea how shader_storage made it into the list of banned variable modes for stores but it clearly should be allowed. This only doesn't cause us a problem today because we never actually use derefs on shader_storage variables. Reviewed-by: Alejandro Piñeiro <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* nir/validate: Require array indices to match the deref bit sizeJason Ekstrand2019-01-081-2/+4
| | | | | | | | | This doesn't currently change anything because array indices are required to be 32 bits and all derefs are also 32 bits. However, we will one day have 64-bit derefs for OpenCL. Reviewed-by: Alejandro Piñeiro <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* spirv: Handle arbitrary bit sizes for deref array indicesJason Ekstrand2019-01-082-34/+42
| | | | | | | | | | | We already had code in link_as_ssa to handle bit sizes; we just need to use it. While we're at it we clean up link_as_ssa a bit and add an explicit bit_size parameter in preparation for a day when we have derefs that aren't 32 bit. Cc: [email protected] Reviewed-by: Alejandro Piñeiro <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* nir/builder: Add nir_i2i and nir_u2u helpers which take a bit sizeJason Ekstrand2019-01-081-13/+32
| | | | | | Cc: [email protected] Reviewed-by: Alejandro Piñeiro <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]
* spirv: Emit NIR deref instructions on-the-flyJason Ekstrand2019-01-083-71/+34
| | | | | | | | | | | | | | | This simplifies our deref handling by emitting the actual NIR deref instructions on-the-fly instead of of building up a deref chain and then emitting them at the last moment. In order for this to work with the parts of the compiler that assume they can chase deref chains, we have to run nir_rematerialize_derefs_in_use_blocks_impl to put the derefs back in the right places. Otherwise, in cases such as loop continues where the SPIR-V blocks are not in the same order as the NIR blocks, we may end up with a deref chain with a parent that does not dominate it's child and nir_repair_ssa_impl will insert phis in the deref chain. Reviewed-by: Alejandro Piñeiro <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* spirv: Sign-extend array indicesJason Ekstrand2019-01-081-2/+2
| | | | | | | | | The SPIR-V spec was recently updated to clarify that array indices are treated as signed integers. Cc: [email protected] Reviewed-by: Alejandro Piñeiro <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* spirv: Handle any bit size in vector_insert/extractJason Ekstrand2019-01-083-11/+15
| | | | | | | | | This crops up both in the actual SPIR-V VectorInsert/Extract opcodes as well as various places where we deal with vector derefs. Cc: [email protected] Reviewed-by: Alejandro Piñeiro <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* glsl_type: Support serializing 8 and 16-bit typesJason Ekstrand2019-01-081-2/+12
| | | | | Reviewed-by: Alejandro Piñeiro <[email protected]> Reviewed-by: Caio Marcelo de Oliveira Filho <[email protected]>
* spirv: Fix matrix parameters in function calls.Bas Nieuwenhuizen2019-01-081-0/+4
| | | | | | | | | | They can be handled exactly the same as arrays, we just need to handle the base type correctly in the switches. Fixes: a45b6fb4524 "spirv: Pass SSA values through functions" Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=109204 Reviewed-by: Jason Ekstrand <[email protected]> Reviewed-by: Samuel Pitoiset <[email protected]>
* nir: Make gl_nir_lower_samplers use gl_nir_lower_samplers_as_derefKenneth Graunke2019-01-071-47/+28
| | | | | | | | | | | | | | | | | | | | | | | | These days, we have two sampler lowering passes. The newer one, gl_nir_lower_samplers_as_deref, is used by radeonsi. It rewrites variables to drop structures out of sampler deref chains, to make life simpler. It then sets var->data.binding for non-bindless sampler and image variables based on the GL uniform storage's opaque index values. The older one converts sampler deref chains (nir_tex_src_texture_deref) to a numerical offset (nir_tex_src_texture_offset). It also stores the constant-valued portion of that number in tex->texture_index, making life really simple for drivers that don't support indirects. It too pokes at GL uniform storage's opaque index values. Logically, we can do the first pass (simplify derefs, set bindings) then the second (turn derefs to offsets, set texture_index). This patch does exactly that, eliminating some redundancy (only one pass has to poke at GL uniform storage), and gaining proper var->data.binding values for drivers using the full lowering. Reviewed-by: Ian Romanick <[email protected]> Acked-by: Jason Ekstrand <[email protected]>
* nir: Fix gl_nir_lower_samplers_as_deref's structure type handling.Kenneth Graunke2019-01-071-3/+0
| | | | | | | | | | | | | | | | | | | | | | | | We recurse to remove structures, and at each step, re-modify the resulting type for our link in the deref chain. For arrays, the result of recursion is the new underlying type - so we wrap it with the array dimensionality again. For structs, we want to simply use the new underlying type, skipping the struct altogether. The correct way to do this is to do nothing at all. Previously, we had reset type to next->type, which is the /old/ field type, not the new field type we obtained by recursing. This undid our recursive work. Fixes about 338 tests with nested structs, such as: dEQP-GLES2.functional.uniform_api.value.initial.get_uniform.nested_structs_arrays.sampler2D_samplerCube_fragment Note that currently only radeonsi uses this pass, and NIR support is disabled there by default, so the breakage was likely not seen by most people. The next commit uses this pass for more drivers, so this fix prevents regressions from that change. Reviewed-by: Ian Romanick <[email protected]> Acked-by: Jason Ekstrand <[email protected]>
* glsl: correct typo in GLSL compilation error messageAndres Gomez2019-01-071-1/+1
| | | | | | | | | v2: Add the "fix" tag (Erik). Fixes: 037f68d81e1 ("glsl: apply align layout qualifier rules to block offsets") Cc: Timothy Arceri <[email protected]> Signed-off-by: Andres Gomez <[email protected]> Reviewed-by: Erik Faye-Lund <[email protected]>
* nir: avoid uninitialized variable warningTimothy Arceri2019-01-071-1/+1
| | | | | Reviewed-by: Bas Nieuwenhuizen <[email protected]> Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=109231
* nir: Add nir_lower_tex options to lower sampler return formats.Eric Anholt2019-01-042-0/+83
| | | | | | | | | | | | | I've been doing this in the nir-to-vir and nir-to-qir backends of v3d and vc4, but nir could potentially do some useful stuff for us (like avoiding unpack/repacks) if we give it the information. v2: Skip lowering for txs/query_levels v3: Fix a crash on old-style shadow v4: Rename to tex_packing, use nir_format_unpack_sint/uint helpers, pack the enum. Reviewed-by: Jason Ekstrand <[email protected]>
* nir: Allow nir_format_unpack_int/sint to unpack larger values.Eric Anholt2019-01-041-3/+8
| | | | | | | For V3D, I want to unpack 4-16-bit packed integers for 8 and 16-bit integer samplers. Reviewed-by: Jason Ekstrand <[email protected]>
* nir: remove dead code from copy_prop_varsCaio Marcelo de Oliveira Filho2019-01-041-1/+1
| | | | | | | | | | | When copy_prop_vars also took care of dead write handling, intrin was used as part of store_to_entry. Now it isn't, so this assignment isn't used really used. Add a comment clarifying what happens to intrin. Fixes: 4dfa7adc100 "nir: Remove handling of dead writes from copy_prop_vars" Reviewed-by: Jordan Justen <[email protected]> Reviewed-by: Jason Ekstrand <[email protected]>
* glsl/linker: complete documentation for assign_attribute_or_color_locationsAndres Gomez2019-01-041-9/+13
| | | | | | | | | Commit 27f1298b9d9 ("glsl/linker: validate attribute aliasing before optimizations") forgot to complete the documentation. Cc: Tapani Pälli <[email protected]> Signed-off-by: Andres Gomez <[email protected]> Reviewed-by: Tapani Pälli <[email protected]>
* nir: merge some basic consecutive ifsTimothy Arceri2019-01-031-0/+93
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | After trying multiple times to merge if-statements with phis between them I've come to the conclusion that it cannot be done without regressions. The problem is for some shaders we end up with a whole bunch of phis for the merged ifs resulting in increased register pressure. So this patch just merges ifs that have no phis between them. This seems to be consistent with what LLVM does so for radeonsi we only see a change (although its a large change) in a single shader. Shader-db results i965 (SKL): total instructions in shared programs: 13098176 -> 13098152 (<.01%) instructions in affected programs: 1326 -> 1302 (-1.81%) helped: 4 HURT: 0 total cycles in shared programs: 332032989 -> 332037583 (<.01%) cycles in affected programs: 60665 -> 65259 (7.57%) helped: 0 HURT: 4 The cycles estimates reported by shader-db for i965 seem inaccurate as the only difference in the final code is the removal of the redundent condition evaluations and jumps. Also the biggest code reduction (~7%) for radeonsi was in a tomb raider tressfx shader but for some reason this does not get merged for i965. Shader-db results radeonsi (VEGA): Totals from affected shaders: SGPRS: 232 -> 232 (0.00 %) VGPRS: 164 -> 164 (0.00 %) Spilled SGPRs: 59 -> 59 (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: 14584 -> 13520 (-7.30 %) bytes LDS: 0 -> 0 (0.00 %) blocks Max Waves: 13 -> 13 (0.00 %) Wait states: 0 -> 0 (0.00 %) Reviewed-by: Ian Romanick <[email protected]>
* nir: add rewrite_phi_predecessor_blocks() helperTimothy Arceri2019-01-031-20/+31
| | | | | | This will also be used by the if merge pass in the following commit. Reviewed-by: Ian Romanick <[email protected]>
* nir: simplify does_varying_match()Timothy Arceri2019-01-031-5/+2
| | | | Reviewed-by: Alejandro Piñeiro <[email protected]>
* nir: make use of does_varying_match() helperTimothy Arceri2019-01-031-2/+1
| | | | Reviewed-by: Alejandro Piñeiro <[email protected]>
* nir: make nir_opt_remove_phis_impl() staticTimothy Arceri2019-01-032-2/+1
| | | | Reviewed-by: Alejandro Piñeiro <[email protected]>
* nir: add a way to print the deref chainCaio Marcelo de Oliveira Filho2019-01-022-4/+14
| | | | | | | | Makes debugging easier when we care about the deref chain and not the deref instruction itself. To make it take a const pointer, constify some of the static functions in nir_print.c. Reviewed-by: Eric Anholt <[email protected]>
* compiler/spirv: use 32-bit polynomial approximation for 16-bit asin()Iago Toral Quiroga2019-01-021-0/+14
| | | | | | | | | | | | | | | | | | | | | | | | The 16-bit polynomial execution doesn't meet Khronos precision requirements. Also, the half-float denorm range starts at 2^(-14) and with asin taking input values in the range [0, 1], polynomial approximations can lead to flushing relatively easy. An alternative is to use the atan2 formula to compute asin, which is the reference taken by Khronos to determine precision requirements, but that ends up generating too many additional instructions when compared to the polynomial approximation. Specifically, for the Intel case, doing this adds +41 instructions to the program for each asin/acos call, which looks like an undesirable trade off. So for now we take the easy way out and fallback to using the 32-bit polynomial approximation, which is better (faster) than the 16-bit atan2 implementation and gives us better precision that matches Khronos requirements. v2: - Fallback to 32-bit using recursion (Jason). Reviewed-by: Jason Ekstrand <[email protected]>
* compiler/spirv: implement 16-bit frexpIago Toral Quiroga2019-01-021-2/+46
| | | | Reviewed-by: Jason Ekstrand <[email protected]>
* compiler/spirv: implement 16-bit hyperbolic trigonometric functionsIago Toral Quiroga2019-01-021-18/+26
| | | | | | | | | | v2: - use nir_fadd_imm and nir_fmul_imm helpers (Jason) v3: - since we need to define one for fsub use it for fdiv too (Jason) Reviewed-by: Jason Ekstrand <[email protected]>
* compiler/spirv: implement 16-bit exp and logIago Toral Quiroga2019-01-021-2/+2
| | | | | | | v2 - use nir_fmul_imm helper (Jason) Reviewed-by: Jason Ekstrand <[email protected]>
* compiler/spirv: implement 16-bit atan2Iago Toral Quiroga2019-01-021-7/+11
| | | | | | | | | | | | v2: - fix huge_val for 16-bit, it was mean't to be 2^14 not 10^14. v3: - rebase on top of new bool sized opcodes - use nir_b2f helper - use nir_fmul_imm helper Reviewed-by: Jason Ekstrand <[email protected]>
* compiler/spirv: implement 16-bit atanIago Toral Quiroga2019-01-021-12/+11
| | | | | | | | | v2: - use nir_fadd_imm and nir_fmul_imm helpers (Jason) - rebased on top of new sized boolean opcodes - use nir_b2f helper Reviewed-by: Jason Ekstrand <[email protected]>
* compiler/spirv: implement 16-bit acosIago Toral Quiroga2019-01-021-2/+3
| | | | Reviewed-by: Jason Ekstrand <[email protected]>
* compiler/spirv: implement 16-bit asinIago Toral Quiroga2019-01-021-9/+14
| | | | | | | | | | | v2: - use nir_fmul_imm and nir_fadd_imm helpers (Jason) v3: - missed one case where we need to replace nir_imm_float with nir_imm_floatN_t (Jason) Reviewed-by: Jason Ekstrand <[email protected]>
* compiler/spirv: handle 16-bit float in radians() and degrees()Iago Toral Quiroga2019-01-021-2/+2
| | | | | | | v2: - use nir_imm_fmul helper (Jason) Reviewed-by: Jason Ekstrand <[email protected]>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-26 03:37:20 +0000