AlexIndustrial/mesa
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
190,084 Commits 1 Branch 0 Tags
8fa46b31a89fde179d87f0b714bc882ebfa43b0d
Commit Graph

1181 Commits

Author SHA1 Message Date
Faith Ekstrand 8fa46b31a8 spirv: Handle constant cooperative matrices in OpCompositeExtract 
Fixes: b98f87612b ("spirv: Implement SPV_KHR_cooperative_matrix")
Reviewed-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29509>
 2024-06-04 16:34:48 +00:00
Faith Ekstrand c2ab522360 spirv: Update the JSON and headers 
Acked-by: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Acked-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29509>
 2024-06-04 16:34:48 +00:00
Georg Lehmann dcab408a6c nir: remove unpack_half_flush_to_zero 
It doesn't make sense to have two sets of opcodes for this when all backends
that support the flush_to_zero variant just rely on the global floating point
mode anyway.

Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29433>
 2024-05-31 09:46:35 +00:00
Caio Oliveira e3099fc839 spirv: Add MESA_SPIRV_DEBUG=values to dump all values 
Dumps the value associated with each SPIR-V ID after parsing the module.
This will show the intermediate vtn_* values that spirv_to_nir uses.
Only a subset of detailed information is printed at the moment (focus on
pointers and pointer types), but it is easy to add for other value types
later.

Example output when running crucible with the debug option enabled.

```
    crucible: start  : func.compute.num-workgroups.basic.q0
    === SPIR-V values
           1 = extension
           2 = type void glsl_type=void
           3 = type function
           4 = function
           5 = block
           6 = type scalar glsl_type=uint
           7 = type vector glsl_type=uvec3
           8 = type array glsl_type=uvec3[]
           9 = type struct glsl_type=Storage
          10 = type pointer deref=9 SpvStorageClassUniform glsl_type=uvec4
          11 = pointer ptr_type=10 (pointed-)type=9
          12 = type scalar glsl_type=int
          13 = constant type=12
          14 = type pointer deref=7 SpvStorageClassInput glsl_type=uint
          15 = pointer ptr_type=14 (pointed-)type=7
          16 = constant type=6
          17 = type pointer deref=6 SpvStorageClassInput glsl_type=uint
          18 = pointer ptr_type=17 (pointed-)type=6
               NIR: 32    %2 = deref_array &(*%0)[0] (system uint)  // &gl_LocalInvocationID[0]
          19 = ssa glsl_type=uint
          20 = pointer ptr_type=14 (pointed-)type=7
          21 = ssa glsl_type=uvec3
          22 = type pointer deref=7 SpvStorageClassUniform glsl_type=uint
          23 = pointer ptr_type=22 (pointed-)type=7
               NIR: 32x4  %12 = deref_array &(*%11)[%4] (ssbo uvec3)  // &((Storage *)%9)->uv3a[%4]
          24 = constant type=6
          25 = constant type=6
          26 = constant type=7
    ===
    crucible: pass   : func.compute.num-workgroups.basic.q0
```

When the environment variable is set, this dump will also be printed
during vtn_fail and its helpers.

Reviewed-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29295>
 2024-05-23 17:07:31 +00:00
Alyssa Rosenzweig 2912f531a7 nir: add texops for AGX border colour emulation 
AGX has limited border colour hardware. To support full
customBorderColorWithoutFormat semantics, we're forced to emulate in shaders at
a substantial performance penalty. Actually, that's needed just to pass CTS
because of other hardware issues stacking on top of each others... Hooray!

Add the texops we need to facilitate efficient custom border colour lowering.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Acked-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179>
 2024-05-14 04:57:24 +00:00
Ian Romanick f6e038fd0f spirv: Use fp16 fp_fast_math settings when lowering fp16 asin and acos 
v2: Save and restore fp_fast_math. Suggested by Georg and Ivan.

v3: Add a message to the static_assert.

Fixes: 750bd9757e ("spirv: gather some float controls bits per instruction")
Reviewed-by: Ivan Briano <ivan.briano@intel.com> [v2]
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org> [v2]
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29091>
 2024-05-10 00:05:34 +00:00
Saroj Kumar 221371e903 mesa: replace shader_info::source_sha1 
Replace shader_info::source_sha1 with shader_info::source_blake3 in compiler, mesa and radeonsi.

Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Acked-by: David Heidelberg <david.heidelberg@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28156>
 2024-05-09 20:08:18 +00:00
Faith Ekstrand 69b0ee7b6c spirv: Get rid of the old caps struct 
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Iván Briano <ivan.briano@intel.com>
Acked-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28905>
 2024-05-09 01:14:23 +00:00
Faith Ekstrand 22171d16f8 mesa: Use the new spirv_capabilities struct 
Also, re-organize a bit to match the spec better.  There are now
capabilities which need to be set to constant true which we didn't have
to se in the old caps struct and this makes it all more obvious.

Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Iván Briano <ivan.briano@intel.com>
Acked-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28905>
 2024-05-09 01:14:22 +00:00
Faith Ekstrand d5f3233a06 spirv: Use spirv_capabilities in tests 
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Iván Briano <ivan.briano@intel.com>
Acked-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28905>
 2024-05-09 01:14:22 +00:00
Faith Ekstrand 3d7a465ad4 spirv: Add support for specifying caps through the new struct 
Reviewed-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Iván Briano <ivan.briano@intel.com>
Acked-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28905>
 2024-05-09 01:14:22 +00:00
Faith Ekstrand a7f8555b96 spirv: Check capabilities using the supported_capabilities table 
Reviewed-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Iván Briano <ivan.briano@intel.com>
Acked-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28905>
 2024-05-09 01:14:22 +00:00
Faith Ekstrand 5836e2430c spirv: Add a table of all implemented capabilities 
This is everything that the SPIR-V parser knows how to handle, not what
the driver supports.

Acked-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Iván Briano <ivan.briano@intel.com>
Acked-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28905>
 2024-05-09 01:14:22 +00:00
Faith Ekstrand c1eaa03904 spirv: Drop the SubgroupUniformControlFlow check 
It's just a vtn_fail_if() and there's no actual cap for it.  It's not
really gaining us much to have the check.

Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Iván Briano <ivan.briano@intel.com>
Acked-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28905>
 2024-05-09 01:14:22 +00:00
Faith Ekstrand 9ae61a152d spirv: Use supported_capabilities for various checks 
Reviewed-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Iván Briano <ivan.briano@intel.com>
Acked-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28905>
 2024-05-09 01:14:22 +00:00
Faith Ekstrand 29aa6cefcc spirv: Add supported_capabilities to vtn_builder 
Acked-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Iván Briano <ivan.briano@intel.com>
Acked-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28905>
 2024-05-09 01:14:22 +00:00
Faith Ekstrand 4b3561b14d spirv: Move the printf enable out of capabilities 
Reviewed-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Iván Briano <ivan.briano@intel.com>
Acked-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28905>
 2024-05-09 01:14:22 +00:00
Faith Ekstrand eed3b56402 spirv: Move the old AMD extensions out of capabilities 
These aren't real capabilities.  They control whether or not we turn on
the extended instruction sets for these instruction types.

Reviewed-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Iván Briano <ivan.briano@intel.com>
Acked-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28905>
 2024-05-09 01:14:22 +00:00
Faith Ekstrand 1d574dcf19 spirv: Record capabilities rather than ad-hoc bools 
Reviewed-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Iván Briano <ivan.briano@intel.com>
Acked-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28905>
 2024-05-09 01:14:22 +00:00
Faith Ekstrand c07cf9c395 spirv: Generate a spirv_capabilities struct 
Reviewed-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Iván Briano <ivan.briano@intel.com>
Acked-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28905>
 2024-05-09 01:14:22 +00:00
Faith Ekstrand 74b17b8d25 spirv: Better handle duplicated enums in the JSON parser 
Reviewed-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Iván Briano <ivan.briano@intel.com>
Acked-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28905>
 2024-05-09 01:14:22 +00:00
Faith Ekstrand 182877342f spirv: Update the JSON and headers 
Acked-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Iván Briano <ivan.briano@intel.com>
Acked-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28905>
 2024-05-09 01:14:22 +00:00
Faith Ekstrand a09c5d55ed spirv: Auto-generate spirv_info.h 
Reviewed-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Iván Briano <ivan.briano@intel.com>
Acked-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28905>
 2024-05-09 01:14:22 +00:00
Georg Lehmann 6ab4b2d7a0 spirv: preserve signed zero in modf 
fsign's result can be +0.0 or -0.0 for -0.0. We already calculate
the signed zero, it's even faster to replace the fmul(fsign(x), ...) with ior.

Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28938>
 2024-04-26 21:31:53 +00:00
Eric Engestrom 71fd7836f6 spirv: deduplicate default debug log level 
`level` is already set to WARNING by default, so return it normally
instead of hard-coding WARNING again in the other code path.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28799>
 2024-04-26 10:38:12 +00:00
Iván Briano 22fa29ac2f vtn: support float controls2 
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27281>
 2024-04-25 12:13:41 +00:00
Iván Briano 750bd9757e spirv: gather some float controls bits per instruction 
v2: add static_assert to ensure values fit in bitfield (Alyssa)

Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27281>
 2024-04-25 12:13:41 +00:00
Faith Ekstrand ba8860301f nir: Take a nir_def in nir_goto_if() 
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28300>
 2024-03-25 15:55:48 +00:00
Caio Oliveira e5bc5bba7c anv: Enable VK_KHR_shader_maximal_reconvergence 
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27278>
 2024-03-15 02:10:21 +00:00
Georg Lehmann 230743da2e nir: remove rotate scope 
All other subgroup operations do not have a scope in NIR, so for consistency
rotate shouldn't have one either.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27964>
 2024-03-05 14:12:21 +00:00
Samuel Pitoiset 78ea304a06 spirv: only consider IO variables when adjusting patch locations for TES 
With TES, the primitive ID is an input variable but it's considered a
sysval by SPIRV->NIR. Though, its value is greater than
VARYING_SLOT_VAR0 which means its location was adjusted by mistake.

This fixes compiling a tessellation evaluation shader in debug build
with Enshrouded.

Fixes: dfbc03fa88 ("spirv: Fix locations for per-patch varyings")
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27413>
 2024-02-21 10:36:07 +00:00
Daniel Schürmann 312d0784c5 spirv: implement SPV_KHR_quad_control 
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27277>
 2024-02-09 05:32:35 +00:00
Daniel Schürmann 6588f5a123 spirv: implement SPV_KHR_maximal_reconvergence 
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27277>
 2024-02-09 05:32:35 +00:00
Friedrich Vock 321e2cee53 vtn: Use secure_getenv for shader dumping 
Reviewed-by: Eric Engestrom <eric@igalia.com>
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27381>
 2024-01-31 17:28:12 +00:00
Daniel Schürmann faf3bb644d spirv: Update headers and grammar JSON 
1.3.276.0

Acked-by: Caio Oliveira <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27273>
 2024-01-30 22:51:52 +00:00
Daniel Schürmann 5df7be8017 spirv: Fix SpvOpExpectKHR 
This instruction behaves the same as *OpCopyObject* by making a copy of _Value_.

Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Reviewed-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27265>
 2024-01-30 19:09:42 +00:00
Faith Ekstrand 82fe981e35 nir,spirv: Add support for SPV_NV_shader_sm_builtins 
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27154>
 2024-01-18 20:20:06 +00:00
Yonggang Luo 616c0cd067 compiler/spirv: vtn_add_printf_string support for handling OpBitcast 
specifically, it's handling
         %48 = OpBitcast %_ptr_UniformConstant_uchar %_str
         %49 = OpBitcast %_ptr_UniformConstant_uchar %_str_1

; SPIR-V
; Version: 1.4
; Generator: Khronos SPIR-V Tools Linker; 0
; Bound: 53
; Schema: 0
               OpCapability Addresses
               OpCapability Kernel
               OpCapability Int64
               OpCapability Int8
          %1 = OpExtInstImport "OpenCL.std"
               OpMemoryModel Physical64 OpenCL
               OpEntryPoint Kernel %2 "main_test" %_str %_str_1
          %5 = OpString "kernel_arg_type.main_test.float*,uint*,"
          %6 = OpString "kernel_arg_type_qual.main_test.,,"
               OpSource OpenCL_C 102000
               OpName %_str ".str"
               OpName %_str_1 ".str.1"
               OpName %main_test "main_test"
               OpName %src "src"
               OpName %dest "dest"
               OpName %entry "entry"
               OpName %src_addr "src.addr"
               OpName %dest_addr "dest.addr"
               OpName %arrayidx "arrayidx"
               OpName %call "call"
               OpName %src_0 "src"
               OpName %dest_0 "dest"
               OpModuleProcessed "Linked by SPIR-V Tools Linker"
               OpDecorate %_str Constant
               OpDecorate %_str Alignment 1
               OpDecorate %_str_1 Constant
               OpDecorate %_str_1 Alignment 1
               OpDecorate %src Alignment 4
               OpDecorate %dest Alignment 4
               OpDecorate %src_addr Alignment 8
               OpDecorate %dest_addr Alignment 8
               OpDecorate %src_0 Alignment 4
               OpDecorate %dest_0 Alignment 4
      %ulong = OpTypeInt 64 0
      %uchar = OpTypeInt 8 0
       %uint = OpTypeInt 32 0
    %ulong_7 = OpConstant %ulong 7
   %uchar_37 = OpConstant %uchar 37
  %uchar_115 = OpConstant %uchar 115
   %uchar_58 = OpConstant %uchar 58
   %uchar_32 = OpConstant %uchar 32
  %uchar_102 = OpConstant %uchar 102
    %uchar_0 = OpConstant %uchar 0
    %ulong_5 = OpConstant %ulong 5
   %uchar_84 = OpConstant %uchar 84
  %uchar_101 = OpConstant %uchar 101
  %uchar_116 = OpConstant %uchar 116
    %ulong_0 = OpConstant %ulong 0
%_arr_uchar_ulong_7 = OpTypeArray %uchar %ulong_7
%_ptr_UniformConstant__arr_uchar_ulong_7 = OpTypePointer UniformConstant %_arr_uchar_ulong_7
%_arr_uchar_ulong_5 = OpTypeArray %uchar %ulong_5
%_ptr_UniformConstant__arr_uchar_ulong_5 = OpTypePointer UniformConstant %_arr_uchar_ulong_5
       %void = OpTypeVoid
      %float = OpTypeFloat 32
%_ptr_CrossWorkgroup_float = OpTypePointer CrossWorkgroup %float
%_ptr_CrossWorkgroup_uint = OpTypePointer CrossWorkgroup %uint
         %40 = OpTypeFunction %void %_ptr_CrossWorkgroup_float %_ptr_CrossWorkgroup_uint
%_ptr_Function__ptr_CrossWorkgroup_float = OpTypePointer Function %_ptr_CrossWorkgroup_float
%_ptr_Function__ptr_CrossWorkgroup_uint = OpTypePointer Function %_ptr_CrossWorkgroup_uint
%_ptr_UniformConstant_uchar = OpTypePointer UniformConstant %uchar
         %44 = OpConstantComposite %_arr_uchar_ulong_7 %uchar_37 %uchar_115 %uchar_58 %uchar_32 %uchar_37 %uchar_102 %uchar_0
       %_str = OpVariable %_ptr_UniformConstant__arr_uchar_ulong_7 UniformConstant %44
         %45 = OpConstantComposite %_arr_uchar_ulong_5 %uchar_84 %uchar_101 %uchar_115 %uchar_116 %uchar_0
     %_str_1 = OpVariable %_ptr_UniformConstant__arr_uchar_ulong_5 UniformConstant %45
  %main_test = OpFunction %void DontInline %40
        %src = OpFunctionParameter %_ptr_CrossWorkgroup_float
       %dest = OpFunctionParameter %_ptr_CrossWorkgroup_uint
      %entry = OpLabel
   %src_addr = OpVariable %_ptr_Function__ptr_CrossWorkgroup_float Function
  %dest_addr = OpVariable %_ptr_Function__ptr_CrossWorkgroup_uint Function
               OpStore %src_addr %src Aligned 8
               OpStore %dest_addr %dest Aligned 8
         %46 = OpLoad %_ptr_CrossWorkgroup_float %src_addr Aligned 8
   %arrayidx = OpInBoundsPtrAccessChain %_ptr_CrossWorkgroup_float %46 %ulong_0
         %47 = OpLoad %float %arrayidx Aligned 4
         %48 = OpBitcast %_ptr_UniformConstant_uchar %_str
         %49 = OpBitcast %_ptr_UniformConstant_uchar %_str_1
       %call = OpExtInst %uint %1 printf %48 %49 %47
         %50 = OpLoad %_ptr_CrossWorkgroup_uint %dest_addr Aligned 8
               OpStore %50 %call Aligned 4
               OpReturn
               OpFunctionEnd
          %2 = OpFunction %void DontInline %40
      %src_0 = OpFunctionParameter %_ptr_CrossWorkgroup_float
     %dest_0 = OpFunctionParameter %_ptr_CrossWorkgroup_uint
         %51 = OpLabel
         %52 = OpFunctionCall %void %main_test %src_0 %dest_0
               OpReturn
               OpFunctionEnd

Signed-off-by: Yonggang Luo <luoyonggang@gmail.com>
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26775>
 2024-01-17 02:59:57 +00:00
Yonggang Luo 88c4de7e7b compiler/spirv: There is not need unqualify const in function vtn_string_literal 
Signed-off-by: Yonggang Luo <luoyonggang@gmail.com>
Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26775>
 2024-01-17 02:59:57 +00:00
Yonggang Luo fd11818828 compiler/spirv: The spirv shader is binary, should write in binary mode 
Fixes: 53265c8798 ("spirv: Add a mechanism for dumping failing shaders")

Signed-off-by: Yonggang Luo <luoyonggang@gmail.com>
Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26775>
 2024-01-17 02:59:57 +00:00
Konstantin Seurer 4c363acf94 vtn: Allow for OpCopyLogical with different but compatible types 
> Result Type must not equal the type of Operand (see OpCopyObject),
> but Result Type must logically match the Operand type.

Allow for this by setting the expected type and making sure, that both
types match.

cc: mesa-stable

Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/10163
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26252>
 2024-01-09 21:53:21 +00:00
Alyssa Rosenzweig 3da2773316 vtn: fuse OpenCL mad if we can can 
clpeak "float" case from 1112 -> 1978 GFLOPS on rusticl on m1.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26932>
 2024-01-09 18:04:19 +00:00
Konstantin Seurer 8050b89819 vtn: Handle DepthReplacing correctly 
The meaning of DepthReplacing was clarified in
https://gitlab.khronos.org/spirv/SPIR-V/-/issues/342 .
TLDR: It just means that the shader can write to FragDepth.

We should therefore only overwrite depth_layout if it is equal to NONE,
since NONE means "not written" and all other modes mean "written" plus
some additional information.

Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/10344
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26876>
 2024-01-08 18:52:50 +00:00
Konstantin Seurer 4d02543853 vtn: Remove transpose(m0)*m1 fast path 
This is broken for games that rely on invariant geometry since the usage
of matrices can affect how gl_Position is computed. The fdot fastpath
relied on if and how fdot is lowered for correctness.

Totals from 6578 (7.73% of 85071) affected shaders:
MaxWaves: 147190 -> 147170 (-0.01%)
Instrs: 4451406 -> 4438140 (-0.30%); split: -0.31%, +0.01%
CodeSize: 23553020 -> 23541772 (-0.05%); split: -0.07%, +0.03%
VGPRs: 302304 -> 302328 (+0.01%)
SpillSGPRs: 1309 -> 1329 (+1.53%)
Latency: 22509985 -> 22177164 (-1.48%); split: -1.48%, +0.00%
InvThroughput: 4862795 -> 4842951 (-0.41%); split: -0.41%, +0.01%
VClause: 85035 -> 84998 (-0.04%); split: -0.06%, +0.02%
SClause: 131008 -> 131055 (+0.04%); split: -0.02%, +0.05%
Copies: 298935 -> 298060 (-0.29%); split: -0.71%, +0.41%
PreSGPRs: 266833 -> 267292 (+0.17%); split: -0.85%, +1.03%
PreVGPRs: 249511 -> 249601 (+0.04%)

Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/9562
cc: mesa-stable

Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26821>
 2024-01-07 22:14:36 +00:00
Caio Oliveira 0b5abf2512 spirv: Use value_id_bound to set initial memory allocated 
Don't rely on the current default (which is 2048 bytes) buffer size for
blocks -- which ends up being too small for most shaders.  Since we
already rely on value_id_bound to allocate an array of vtn_value, use
that to estimate a better value.

In addition to space for the array, we approximate the extra size of
extra data structures with the size of vtn_ssa_value, and skip it to the
next size (double it) to cover the CFG related allocations.  This
results in only single system allocation necessary to back the temporary
data for the majority of the shaders.

Parsing code was slightly reordered so we can validate and read the
value_id_bound before the temporary allocator is created.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25279>
 2024-01-02 16:07:06 +00:00
Caio Oliveira d5b4b7356e spirv: Use linear_alloc for parsing-only data 
All the vtn_* structures and arrays are used only during the lifetime of
spirv_to_nir(); we don't need to free them individually nor steal
them out; and some of them are smaller than the 5-pointer header
required for ralloc allocations.

These properties make them a good candidate for using an
arena-style allocation.

Change the code to create a linear_parent and use that for all the vtn_*
allocation.  Note that NIR data structures still go through ralloc,
since we steal them (through the nir_shader) at the end, i.e. they
outlive the parsing.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25279>
 2024-01-02 16:07:06 +00:00
Yonggang Luo 0210b554d6 treewide: Replace the include of nir_types.h with glsl_types.h 
Signed-off-by: Yonggang Luo <luoyonggang@gmail.com>
Acked-by: Caio Oliveira <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26753>
 2023-12-30 15:08:11 +00:00
Friedrich Vock f1817ab7e0 radv,vtn,driconf: Add and use radv_rt_ssbo_non_uniform workaround for Crysis 2/3 Remastered 
Crysis 2 and 3 Remastered's RT shaders non-uniformly index into SSBO
descriptor arrays without specifying the NonUniformEXT qualifier on the
relevant access chains/load ops. This leads to artifacts around objects.

To add insult to injury, the game fails to provide a meaningful
applicationName/engineName in the Vulkan part of the DX11-Vulkan interop
solution used for RT. Both of these fields are set to "nvpro-sample"
(perhaps the code has been copied from NVIDIA's sample applications).
Therefore, fall back to executable name matching.

Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/9883
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26391>
 2023-12-12 21:16:39 +00:00
Lionel Landwerlin dc3e69af1a nir/serialize: untangle printf serialization from a particular stage 
This allows any stage to carry printf instructions.

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26505>
 2023-12-12 11:11:10 +00:00
Eric Engestrom c51e40dd8b spirv: add missing build dependency 
Fixes: 59a72570b6 ("compiler: Move spirv into a module of its own")
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/10277
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26624>
 2023-12-11 21:47:37 +00:00