AlexIndustrial/mesa
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
171,624 Commits 1 Branch 0 Tags
c8fa8672e48d7dd9e756852cc26e7ac4fa995ec8
Commit Graph

22 Commits

Author SHA1 Message Date
David Heidelberg 7dcd02bd32 aco: drop leftover variable 
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/8652
Fixes: 44fdd2ebcb ("aco: end reduce tmp after control flow, when used within control flow")

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Signed-off-by: David Heidelberg <david.heidelberg@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22011>
 2023-03-22 03:39:56 +00:00
Rhys Perry 44fdd2ebcb aco: end reduce tmp after control flow, when used within control flow 
In the case of:

v0 = start_linear_vgpr
if (...) {

} else {
   use_linear_vgpr(v0)
}
v0 = phi

We need a p_end_linear_vgpr to ensure that the phi does not use the same
VGPR as the linear VGPR.

fossil-db (gfx1100):
Totals from 3763 (2.80% of 134574) affected shaders:
MaxWaves: 90296 -> 90164 (-0.15%)
Instrs: 6857726 -> 6856608 (-0.02%); split: -0.03%, +0.01%
CodeSize: 35382188 -> 35377688 (-0.01%); split: -0.02%, +0.01%
VGPRs: 234864 -> 235692 (+0.35%); split: -0.01%, +0.36%
Latency: 47471923 -> 47474965 (+0.01%); split: -0.03%, +0.04%
InvThroughput: 5640320 -> 5639736 (-0.01%); split: -0.04%, +0.03%
VClause: 93098 -> 93107 (+0.01%); split: -0.01%, +0.02%
SClause: 214137 -> 214130 (-0.00%); split: -0.00%, +0.00%
Copies: 369895 -> 369305 (-0.16%); split: -0.31%, +0.15%
Branches: 164996 -> 164504 (-0.30%); split: -0.30%, +0.00%
PreVGPRs: 210655 -> 211438 (+0.37%)

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20621>
 2023-02-01 15:45:22 +00:00
Timur Kristóf db5c3f170f aco: Emulate Wave64 bpermute on GFX11. 
Similar to emit_gfx10_wave64_bpermute, but uses the new
v_permlane64_b32 instruction to swap data between wave halves.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20293>
 2022-12-14 13:54:04 +00:00
Rhys Perry 6113ee650a aco/gfx11: fix FS input loads in quad-divergent control flow 
This is not ideal and it would be great to somehow make it better some
day.

fossil-db (gfx1100):
Totals from 5208 (3.86% of 135032) affected shaders:
MaxWaves: 127058 -> 126962 (-0.08%); split: +0.01%, -0.09%
Instrs: 3983440 -> 4072736 (+2.24%); split: -0.00%, +2.24%
CodeSize: 21872468 -> 22230852 (+1.64%); split: -0.00%, +1.64%
VGPRs: 206688 -> 206984 (+0.14%); split: -0.05%, +0.20%
Latency: 37447383 -> 37491197 (+0.12%); split: -0.05%, +0.17%
InvThroughput: 6421955 -> 6422348 (+0.01%); split: -0.03%, +0.03%
VClause: 71579 -> 71545 (-0.05%); split: -0.09%, +0.04%
SClause: 148289 -> 147146 (-0.77%); split: -0.84%, +0.07%
Copies: 259011 -> 258084 (-0.36%); split: -0.61%, +0.25%
Branches: 101366 -> 101314 (-0.05%); split: -0.10%, +0.05%
PreSGPRs: 223482 -> 223460 (-0.01%); split: -0.21%, +0.20%
PreVGPRs: 184448 -> 184744 (+0.16%)

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19370>
 2022-11-01 12:42:43 +00:00
Marek Olšák 39800f0fa3 amd: change chip_class naming to "enum amd_gfx_level gfx_level" 
This aligns the naming with PAL.

Acked-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Acked-by: Pierre-Eric Pellou-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16469>
 2022-05-13 14:56:22 -04:00
Daniel Schürmann 1e2639026f aco: Format. 
Manually adjusted some comments for more intuitive line breaks.

Reviewed-by: Tony Wasserka <tony.wasserka@gmx.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11258>
 2021-07-12 21:27:31 +00:00
Daniel Schürmann 59fdaa1985 aco: reorder and cleanup #includes 
Reviewed-by: Tony Wasserka <tony.wasserka@gmx.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11271>
 2021-07-12 12:09:31 +00:00
Rhys Perry e115b01948 aco: return references in instruction cast methods 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8595>
 2021-01-22 14:12:33 +00:00
Rhys Perry 70dbcfa1c9 aco: use instruction cast methods 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8595>
 2021-01-22 14:12:32 +00:00
Rhys Perry ec2185c598 aco: keep track of temporaries' regclasses in the Program 
A future change will switch the liveness sets to bit vectors, which don't
contain regclass information.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6733>
 2020-09-21 13:47:28 +00:00
Rhys Perry 834b449a46 aco: fix value numbering of reductions 
Non-ssa definitions caused an assertion in value numbering.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6662>
 2020-09-09 15:00:45 +00:00
Timur Kristóf 14a5021aff aco/gfx10: Refactor of GFX10 wave64 bpermute. 
The emulated GFX10 wave64 bpermute no longer needs a linear_vgpr,
so we don't consider it a reduction anymore. Additionally, the
code is slightly reorganized in preparation for the GFX6 emulated
bpermute.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5223>
 2020-06-02 21:12:12 +00:00
Samuel Pitoiset 8ece71507d aco: allocate a temp VGPR for some 8-bit/16-bit reduction ops on GFX10 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5148>
 2020-05-29 11:20:58 +00:00
Samuel Pitoiset c76595aec2 aco: use a temporary SGPR for 8-bit/16-bit literal reduction identities 
Otherwise, the compiler overwrites s0 which contains the exec mask.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4494>
 2020-05-21 15:06:48 +00:00
Rhys Perry 20eb1acb6f aco: fix gfx10_wave64_bpermute 
Since 9254fb4fc7, the pass replaced the SCC clobber with the scalar
identity temporary. Just skip most of the temporary setup, since we don't
need it for gfx10_wave64_bpermute.

Although shuffles are disabled on GFX10, Detroit: Become Human seems to
use them anyway.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Fixes: 9254fb4fc7 ('aco: don't use a scalar
       temporary for reductions on GFX10')

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3683>
 2020-02-06 16:43:03 +00:00
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
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
Rhys Perry 56c06c79fc aco: implement 64-bit integer reductions 
The multiplication reduction is larger than it could be, but it should be
easier to implement this way.

No failures with dEQP-VK.subgroups.*int64* except those caused by LLVM
being used for other stages.

v2: don't call setFixed() for v_add carry-out, since setHint sets physReg
v3: add and use emit_vadd32() helper
v4: use num_opcodes instead of last_opcode

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev> (v3)
 2019-11-19 18:58:04 +00:00
Timur Kristóf d59f702e26 aco: Implement subgroup shuffle in GFX10 wave64 mode. 
Previously subgroup shuffle was implemented using the bpermute
instruction, which only works accross half-waves, so by itself it's
not suitable for implementing subgroup shuffle when the shader is
running in wave64 mode.

This commit adds a trick using shared VGPRs that allows to implement
subgroup shuffle still relatively effectively in this mode.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
 2019-10-28 23:52:50 +00:00
Rhys Perry 3865448012 aco: Fix reductions on GFX10. 
Fixes p_reduce (all cluster sizes), p_inclusive_scan and p_exclusive_scan
with all reduction operations.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
 2019-10-28 23:52:50 +00:00
Daniel Schürmann 93c8ebfa78 aco: Initial commit of independent AMD compiler 
ACO (short for AMD Compiler) is a new compiler backend with the goal to replace
LLVM for Radeon hardware for the RADV driver.

ACO currently supports only VS, PS and CS on VI and Vega.
There are some optimizations missing because of unmerged NIR changes
which may decrease performance.

Full commit history can be found at
https://github.com/daniel-schuermann/mesa/commits/backend

Co-authored-by: Daniel Schürmann <daniel@schuermann.dev>
Co-authored-by: Rhys Perry <pendingchaos02@gmail.com>
Co-authored-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Co-authored-by: Connor Abbott <cwabbott0@gmail.com>
Co-authored-by: Michael Schellenberger Costa <mschellenbergercosta@googlemail.com>
Co-authored-by: Timur Kristóf <timur.kristof@gmail.com>

Acked-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Acked-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
 2019-09-19 12:10:00 +02:00