AlexIndustrial/mesa
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
118,355 Commits 1 Branch 0 Tags
ca2dd99bf6ef0bb97ba50e817b3d32423484dc6c
Commit Graph

4381 Commits

Author SHA1 Message Date
Samuel Pitoiset e4c8491bdf radv: implement VK_KHR_separate_depth_stencil_layouts 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
 2019-12-10 13:16:17 +01:00
Samuel Pitoiset 48ee62178f radv: initialize HTILE for separate depth/stencil aspects 
It either clears the whole HTILE buffer or part of it depending
on the HTILE mask parameter.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
 2019-12-10 13:09:29 +01:00
Samuel Pitoiset 41cebfc9c1 radv: do not init HTILE as compressed state when dst layout allows it 
I don't think this makes much differences and a potential clear
following the initialization will overwrite HTILE anyways.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
 2019-12-10 13:09:26 +01:00
Samuel Pitoiset b603cc8c84 radv: synchronize after performing a separate depth/stencil fast clears 
For depth+stencil images, the driver might use an optimized path
if only one aspect is cleared. It either clears the depth or the
stencil part of HTILE. Because the two separate aspects might use
the same HTILE memory we have to synchronize.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
 2019-12-10 13:09:22 +01:00
Samuel Pitoiset 008fe909ca radv: fix possibly wrong PA_SC_AA_CONFIG value for conservative rast 
PA_SC_AA_CONFIG might be updated when conversative rasterization is
enabled. Because the driver only re-emits the multisample state if
the number of samples is different, that register value might not
be updated correctly.

Found by inspection, doesn't fix anything known.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
 2019-12-10 11:04:43 +01:00
Samuel Pitoiset 4f659224c8 radv: move emission of two PA_SC_* registers to the pipeline CS 
They don't have to be updated dynamically.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
 2019-12-10 11:04:40 +01:00
Samuel Pitoiset 86dfe92bd0 radv: do not use VK_TRUE/VK_FALSE 
For consistency.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
 2019-12-09 09:21:26 +01:00
Daniel Schürmann 8259c97b2d aco: propagate temporaries into expanded vectors 
Gives a very slight decrease in code size:
Totals from affected shaders:
Code Size: 1708488 -> 1702768 (-0.33 %) bytes
Max Waves: 2858 -> 2855 (-0.10 %)

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann df3e674fb3 aco: improve readfirstlane after uniform ssbo loads on GFX7 
pipeline-db changes for GFX7:

80310 shaders in 40472 tests
Totals:
SGPRS: 3655900 -> 3643916 (-0.33 %)
VGPRS: 2678324 -> 2686324 (0.30 %)
Spilled SGPRs: 1730 -> 1634 (-5.55 %)
Spilled VGPRs: 14 -> 21 (50.00 %)
Scratch size: 15540 -> 15536 (-0.03 %) dwords per thread
Code Size: 136106120 -> 135457616 (-0.48 %) bytes
LDS: 1259 -> 1259 (0.00 %) blocks
Max Waves: 601014 -> 600206 (-0.13 %)

Totals from affected shaders:
SGPRS: 307832 -> 295848 (-3.89 %)
VGPRS: 267864 -> 275864 (2.99 %)
Spilled SGPRs: 770 -> 674 (-12.47 %)
Spilled VGPRs: 14 -> 21 (50.00 %)
Scratch size: 16 -> 12 (-25.00 %) dwords per thread
Code Size: 22007488 -> 21358984 (-2.95 %) bytes
LDS: 65 -> 65 (0.00 %) blocks
Max Waves: 28668 -> 27860 (-2.82 %)

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann 0837471463 aco: use soffset for MUBUF instructions on SI/CI 
pipeline-db changes for GFX7:

80310 shaders in 40472 tests
Totals:
SGPRS: 3655300 -> 3655900 (0.02 %)
VGPRS: 2677732 -> 2678324 (0.02 %)
Spilled SGPRs: 1730 -> 1730 (0.00 %)
Spilled VGPRs: 14 -> 14 (0.00 %)
Scratch size: 15540 -> 15540 (0.00 %) dwords per thread
Code Size: 136488364 -> 136106120 (-0.28 %) bytes
LDS: 1259 -> 1259 (0.00 %) blocks
Max Waves: 601039 -> 601014 (-0.00 %)

Totals from affected shaders:
SGPRS: 316312 -> 316912 (0.19 %)
VGPRS: 273844 -> 274436 (0.22 %)
Spilled SGPRs: 770 -> 770 (0.00 %)
Spilled VGPRs: 14 -> 14 (0.00 %)
Scratch size: 16 -> 16 (0.00 %) dwords per thread
Code Size: 22724904 -> 22342660 (-1.68 %) bytes
LDS: 114 -> 114 (0.00 %) blocks
Max Waves: 30861 -> 30836 (-0.08 %)

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann 7b38d95b32 radv: Enable ACO on GFX7 (Sea Islands) 
This patch also disables AMD_shader_ballot on GFX7 by default if ACO is used.
Note that shader_ballot works correctly, but performance seems inferior.
To enable shader_ballot use RADV_PERFTEST=shader_ballot.

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann 28c95cc402 aco: return to loop_active mask at continue_or_break blocks 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann 0f9447ccb0 radv: disable Youngblood app profile if ACO is used 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann 746165e540 aco: implement exclusive scan for SI/CI 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann 7ae227effd aco: implement inclusive_scan for SI/CI 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann f895a8b1df aco: implement (clustered) reductions for SI/CI 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann 9254fb4fc7 aco: don't use a scalar temporary for reductions on GFX10 
This patch also adds the scalar temporary for scans on SI/CI

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann 8ad43d8838 aco: flush denorms after fmin/fmax on pre-GFX9 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann 21f67a3bdc radv: only flush scalar cache for SSBO writes with ACO on GFX8+ 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann 79ce6c1b33 aco: disable disassembly for SI/CI due to lack of support by LLVM 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann 1c4afe38f2 aco: implement 64bit ine/ieq for SI/CI 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann 1e1356b2ad aco: implement 64bit i2b for SI /CI 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann da7ff58835 aco: make 1/2*PI a literal constant on SI/CI 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann 90fad7360d aco: implement 64bit VGPR shifts for SI/CI 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann 6a586a6006 aco: split read/writelane opcode into VOP2/VOP3 version for SI/CI 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann 23319add93 aco: fix disassembly of writelane instructions. 
ACO writes an unused 3rd operand for internal usage
which makes LLVM recoginize it as illegal instruction.

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann 6fc9ddfef8 aco: recognize SI/CI SMRD hazards 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann 3eed4d2be5 aco: implement quad swizzles for SI/CI 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann bde9c1e3a1 aco: move buffer_store data to VGPR if needed 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann a8195bdf2e aco: implement nir_op_isign on SI/CI 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann b8783973cd aco: only use scalar loads for readonly buffers on SI/CI 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann f27783a667 aco: implement nir_op_fquantize2f16 for SI/CI 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann caea4bbfdc aco: fix SMEM offsets for SI/CI 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann 8aab92b393 aco: SI/CI - fix sampler aniso 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Dave Airlie 9b533a2ca3 aco: handle gfx7 int8/10 clamping on exports 
Co-authored-by: Daniel Schürmann <daniel@schuermann.dev>

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann 0d42e4d7a0 aco: Initial GFX7 Support 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Daniel Schürmann 3177346bfc aco: refactor visit_store_fs_output() to use the Builder 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
 2019-12-07 11:23:11 +01:00
Timur Kristóf 637c5a1dd9 aco/wave32: Fix reductions. 
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
 2019-12-04 10:36:01 +00:00
Timur Kristóf 21db083504 aco/wave32: Allow setting the subgroup ballot size to 64-bit. 
Previously, it would only work when the ballot size was set to the
lane mask. This patch makes is possible to set the ballot size
to either 32-bit or 64-bit for wave32 mode.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
 2019-12-04 10:36:01 +00:00
Timur Kristóf ed815d503e aco/wave32: Use wave_size for barrier intrinsic. 
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
 2019-12-04 10:36:01 +00:00
Timur Kristóf b8f2edb452 aco/wave32: Fix load_local_invocation_index to support wave32. 
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
 2019-12-04 10:36:01 +00:00
Timur Kristóf e0bcefc3a0 aco/wave32: Use lane mask regclass for exec/vcc. 
Currently all usages of exec and vcc are hardcoded to use s2 regclass.
This commit makes it possible to use s1 in wave32 mode and
s2 in wave64 mode.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
 2019-12-04 10:36:01 +00:00
Timur Kristóf b4efe179ed aco/wave32: Add wave size specific opcodes to aco_builder. 
Several places in ACO we use SOP1 or SOP2 instructions to operate over the
exec mask or VCC, and these need to be adapted to the new size in wave32
mode.

This commit adds a way to deal with this problem in aco_builder: the caller
can specify a wave size specific opcode and the builder will translate that
to the correct opcode based on the current wave size.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
 2019-12-04 10:36:01 +00:00
Timur Kristóf c44af6cbc7 aco/wave32: Introduce emit_mbcnt which takes wave size into account. 
This is relevant because in wave32 mode the v_mbcnt_hi_u32_b32
instruction is superfluous.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
 2019-12-04 10:36:01 +00:00
Timur Kristóf 07754a9c9e aco/wave32: Replace hardcoded numbers in spiller with wave size. 
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
 2019-12-04 10:36:01 +00:00
Timur Kristóf c0dbf42a03 aco/wave32: Change uniform bool optimization to work with wave32. 
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
 2019-12-04 10:36:01 +00:00
Timur Kristóf dd9dad731b aco: Optimize load_subgroup_id to one bit field extract instruction. 
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
 2019-12-04 10:36:01 +00:00
Timur Kristóf 753670e902 aco: Remove lower_linear_bool_phi, it is not needed anymore. 
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
 2019-12-04 10:36:01 +00:00
Timur Kristóf 0d2d672020 aco: Remove superfluous argument from emit_boolean_logic. 
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
 2019-12-04 10:36:01 +00:00
Timur Kristóf 9a43d26b74 aco: Fix operand of s_bcnt1_i32_b64 in emit_boolean_reduce. 
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
 2019-12-04 10:36:01 +00:00