AlexIndustrial/mesa
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
133,442 Commits 1 Branch 0 Tags
b603875482d78f02e50c57ff04f0bfb4f0d98669
Commit Graph

123033 Commits

Author SHA1 Message Date
Tony Wasserka b603875482 aco/ra: Use PhysRegInterval for count_zero 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7799>
 2021-01-13 18:21:06 +00:00
Tony Wasserka c30e83cc51 aco/ra: Use PhysRegInterval for collect_vars parameters 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7799>
 2021-01-13 18:21:06 +00:00
Tony Wasserka 0959b7c435 aco/ra: Use PhysReg when indexing into RegisterFile's containers 
This gets rid of a lot of implicit/explicit conversions from PhysReg to
unsigned.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7799>
 2021-01-13 18:21:06 +00:00
Tony Wasserka c3660f4781 aco/ra: Use PhysReg for member functions of PhysRegInterval 
This replaces the various PhysReg{lb} casts that had been all over the place.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7799>
 2021-01-13 18:21:06 +00:00
Tony Wasserka d2d0096c0c aco/ra: Remove unused function parameter 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7799>
 2021-01-13 18:21:06 +00:00
Tony Wasserka d9e1375e27 aco/ra: Use std::all_of to simplify a loop 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7799>
 2021-01-13 18:21:06 +00:00
Tony Wasserka f7e6b61379 aco/ra: Add helpers to test for intersection/containment of reg intervals 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7799>
 2021-01-13 18:21:06 +00:00
Tony Wasserka 88f21ad87a aco/ra: Move commonly repeated code to a helper function 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7799>
 2021-01-13 18:21:06 +00:00
Tony Wasserka 8962510e38 aco/ra: Conservatively refactor get_reg_specified to use PhysRegInterval 
All expressions have been replaced by their closest equivalent. No major
simplification efforts have been made to minimize risk of regressions.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7799>
 2021-01-13 18:21:06 +00:00
Tony Wasserka 46c9d76134 aco/ra: Use std::all_of to simplify a loop 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7799>
 2021-01-13 18:21:06 +00:00
Tony Wasserka 2b3b2f7ff5 aco/ra: Use std::find_if(_not) to clean up get_reg_simple 
This makes for a more self-describing iteration behavior, and it gets rid
of the need for the duplicated "final check" at the bottom.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7799>
 2021-01-13 18:21:06 +00:00
Tony Wasserka ebdb362937 aco/ra: Add iterator interface for PhysRegInterval 
This enables various loops to use range-based for.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7799>
 2021-01-13 18:21:06 +00:00
Tony Wasserka 689ce1f39d aco/ra: Remove always-false conditions 
All code paths that set "found" to true either break or return before the
loop header is reached again, so the checks are unnecessary.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7799>
 2021-01-13 18:21:05 +00:00
Tony Wasserka 46eee40abc aco/ra: Conservatively refactor existing code to use PhysRegInterval 
All expressions have been replaced by their closest equivalent. No major
simplification efforts have been made to minimize risk of regressions.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7799>
 2021-01-13 18:21:05 +00:00
Tony Wasserka 9bbd6162a9 aco/ra: Introduce PhysRegInterval helper class 
This mainly clarifies the semantics of register bounds (inclusive vs
exclusive), and further groups related varaibles together to clarify
sliding-window-style loops.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7799>
 2021-01-13 18:21:05 +00:00
Tony Wasserka 67c1f32228 aco/ra: Update register use bounds before recursing in get_regs_for_copies 
Delaying the call to adjust_max_used_regs until after get_regs_for_copies
returns puts the RA context into a state where registers past max_used_gpr
may be blocked. This isn't an issue on its own, but it adds a surprising
corner case to get_reg_simple that is easily avoided now.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7799>
 2021-01-13 18:21:05 +00:00
Daniel Schürmann 288032a873 aco: remove divergent branches which only jump over very few instructions 
Totals from 18436 (13.23% of 139391) affected shaders (NAVI10):
CodeSize: 138428504 -> 138172588 (-0.18%)
Instrs: 26605127 -> 26541176 (-0.24%)
Cycles: 1624994088 -> 1622461620 (-0.16%)
VMEM: 3689892 -> 3689102 (-0.02%)
SMEM: 1131767 -> 1131761 (-0.00%)
Branches: 851796 -> 787852 (-7.51%)

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7814>
 2021-01-13 18:04:28 +00:00
Daniel Schürmann 412291ddef aco: propagate swizzles when optimizing packed clamp & fma 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6680>
 2021-01-13 17:46:56 +00:00
Daniel Schürmann 6ecbccfb23 aco: optimize v_pk_fma_f16 -> v_pk_fmac_f16 on GFX10 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6680>
 2021-01-13 17:46:56 +00:00
Daniel Schürmann b03be30e07 aco: optimize packed fneg 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6680>
 2021-01-13 17:46:56 +00:00
Daniel Schürmann e3790fc458 aco: optimize packed clamp 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6680>
 2021-01-13 17:46:56 +00:00
Daniel Schürmann a9fd9187e8 aco: optimize packed mul+add to v_pk_fma_f16 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6680>
 2021-01-13 17:46:56 +00:00
Daniel Schürmann 01134b0bfe aco: simplify multiply-add combining 
When both operands of a v_sub (same apply for v_add) are mul and one
already uses clamp/omod, pick the other operand to get a chance to
combine to a MAD.

No fossils-db changes.

Co-authored-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6680>
 2021-01-13 17:46:56 +00:00
Daniel Schürmann fcd2ef23e5 radv: vectorize 16bit instructions 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6680>
 2021-01-13 17:46:56 +00:00
Daniel Schürmann 454bbf8f23 aco: emit packed 16bit instructions 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6680>
 2021-01-13 17:46:56 +00:00
Daniel Schürmann 5ad52ac906 aco: create helpers to emit vop3p instructions 
Also make get_alu_src() capable to return
unswizzled multi-component SGPR sources.

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6680>
 2021-01-13 17:46:56 +00:00
Daniel Schürmann 036a369f46 aco: change usesModifiers() considering opsel_hi on packed instructions 
opsel_hi == 1 means that the high operand selects the
high bits of the input, which is the normal behavior.

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6680>
 2021-01-13 17:46:56 +00:00
Daniel Schürmann 178b33c870 aco: allow SGPRs on every src position for VOP3P 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6680>
 2021-01-13 17:46:56 +00:00
Daniel Schürmann 0db4263a3a aco: allow constants/literals on every src position for VOP3P 
and prevent literals on VOP3P pre-GFX10.

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6680>
 2021-01-13 17:46:56 +00:00
Daniel Schürmann 4a75a28698 aco/RA: fix subdword operands on VOP3P instructions 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6680>
 2021-01-13 17:46:55 +00:00
Daniel Schürmann 2caba08c1a aco: fix VOP3P assembly, VN and validation 
aco/opcodes: rename v_pk_fma_mix* -> v_fma_mix*
and add modifier capabilities for VOP3P.

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6680>
 2021-01-13 17:46:55 +00:00
Samuel Pitoiset 3c1275ccae radv: enable DCC for MSAA on GFX10+ 
It should work fine now.

This gives +1-2% improvements with Control MSAA (2x and 4x)
on Sienna.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8413>
 2021-01-13 17:24:31 +00:00
Boris Brezillon 0ad83e3361 pan/bi: Fix the !immediate case in bi_emit_store_vary() 
The base offset was ignored, take it into account.

Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8469>
 2021-01-13 17:07:14 +00:00
Ilia Mirkin f9237619d3 nouveau: trigger the current fence's work on destroy explicitly 
Otherwise the delete yells at us that there's still work pending. This
isn't an actual problem, but annoying to see each time.

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8462>
 2021-01-13 16:59:18 +00:00
Thong Thai 4b208cc503 frontends/va: Return an error if non-interlaced buffer is not supported 
Add a check to vaDeriveImage to see if a non-interlaced buffer was
created successfully. Otherwise, return an error, since we won't be able
to derive an image from the interlaced buffer.

Prevents a null pointer dereference from occuring on some nVidia cards,
reported by Alexander Kapshuk.

v2: Check for PIPE_VIDEO_CAP_SUPPORTS_PROGRESSIVE support (Ilia)

Fixes: fcb558321e ("frontends/va: Derive image from interlaced buffers")
Signed-off-by: Thong Thai <thong.thai@amd.com>
Tested-by: Alexander Kapshuk <alexander.kapshuk@gmail.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8320>
 2021-01-13 16:37:43 +00:00
Bas Nieuwenhuizen 4a783a3c78 radv: Use L2 coherency on GFX9+. 
Especially on GFX10 we can avoid pretty much all L2 flushes.

However, instead of that we have to do L2_METADATA invalidations. We
do that every time we could possibly be reading new DCC/HTILE info
from the L2 cache in shaders.

Benchmark results, basemark on high preset with a navi10 on profile_standard
(which is slower than a navi10 on default settings, please don't compare
 to random navi10 results you find)

before:
  5932
  5928
  5937

after:
  6011
  6013
  6009

So this looks like a >1% increase.

Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7202>
 2021-01-13 16:27:19 +00:00
Bas Nieuwenhuizen 0af86341a2 radv: Use L2 for CP DMA on GFX9+. 
This enables assuming that the L2 is always up to date for barriers.

Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7202>
 2021-01-13 16:27:19 +00:00
Bas Nieuwenhuizen 8f8d72af55 radv: Use access helpers for flushing with meta operations. 
This way we're properly using the vulkan barrier paradigm instead
of adhoc guessing what caches need to be flushed. This is more robust
for cache policy changes as we now don't have to revisit all the meta
operations all the time.

Note that a barrier has both a src and dst part though. So

barrier:
   flush src
   meta op
   flush dst

becomes

barrier:
  flush barrier src
  flush meta op dst
  meta op
  flush meta op src
  flush barrier dst

And there are some places where we've been able to replace a CB flush
with a shader flush because that is what we'd need according to vulkan rules
(and it turns out that in the cases the CB flush mattered the app will set the
bit in one of the relevant flushes or it was needed as a result of an optimization
that we counter-acted in the previous patch.)

Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7202>
 2021-01-13 16:27:19 +00:00
Bas Nieuwenhuizen dba0a523a0 radv: Do dst invalidations for write accesses. 
For write-after-write hazards.

Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7202>
 2021-01-13 16:27:19 +00:00
Bas Nieuwenhuizen 9026f10cda radv: Invalidate CB on SHADER_WRITE for meta operations. 
To cancel the optimization in radv_dst_access_flush if these helpers
get used by meta operations.

We could also remove that optimization but I think this triggers less
often as all SHADER_WRITE flushes on images not supporting STORAGE should
be meta

Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7202>
 2021-01-13 16:27:19 +00:00
Bas Nieuwenhuizen 3d7713b5a2 radv: Remove redundant WB_L2 flush. 
INV_L2 already does that.

Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7202>
 2021-01-13 16:27:19 +00:00
Alyssa Rosenzweig 275277a2b4 panfrost: Implement alpha testing natively 
On Midgard, we still have to lower on v6+. Passes Piglit
./fbo-mrt-alphatest (saving a cycle in the fragment shader to
compare/discard).

Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8447>
 2021-01-13 15:17:32 +00:00
Alyssa Rosenzweig ff44f813fb panfrost: Add alpha reference to XML 
Midgard only, v6 dropped support.

Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8447>
 2021-01-13 15:17:32 +00:00
Alyssa Rosenzweig 7a6a5f3fe1 panfrost: Handle explicit primitive restart 
Don't fall back. Passes piglit ./bin/primitive-restart on Bifrost.

Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8447>
 2021-01-13 15:17:32 +00:00
Samuel Pitoiset afad13700a radv: disable VK_EXT_sample_locations again on GFX10+ 
I attempted to enable it for 21.0, only 2x and 4x were supported
but there is new failures if DCC+MSAA is enabled.

Disable it again because DCC is more important than this feature and
no Mesa releases have it on GFX10+.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8472>
 2021-01-13 15:04:56 +00:00
Boris Brezillon 09bf6910b0 panfrost: Fix panfrost_afbc_format_needs_fixup() 
This function returns true for PIPE_FORMAT_R8G8B8X8_UNORM, which is
wrong.

Fixes: 44217be921 ("panfrost: Adjust the format for AFBC textures on Bifrost v7")
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8466>
 2021-01-13 14:01:42 +00:00
Samuel Pitoiset 001c1105f1 radv: enable DCC for mipmaps on GFX10+ 
Seems to work fine.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8468>
 2021-01-13 13:42:04 +00:00
Samuel Pitoiset 825e2386dc radv: do not enable DCC for 3D images with mipmaps on GFX10+ 
This is broken for some reasons, and probably rare enough to
care for now.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8468>
 2021-01-13 13:42:04 +00:00
Samuel Pitoiset 755a8313fc radv: add support for fast-clearing DCC levels on GFX10+ 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8468>
 2021-01-13 13:42:04 +00:00
Samuel Pitoiset 5537c9de73 radv: prevent fast-clearing uncompressed DCC levels 
When size is 0, this means the level can't be compressed.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8468>
 2021-01-13 13:42:04 +00:00