mesa/src/panfrost/compiler
Boris Brezillon c97f79ac0c pan/va: Optimize SSBO lowering on Valhall
For reads, we use the LD_PKA (AKA LD_BUFFER) so we can directly
pass the buffer index. For writes, we still convert the SSBO index
into a global address before doing a global load/store/atomic
operation, but we do that with an LEA_PKA instruction that takes
care of bounds checking.

Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31164>
2024-09-18 13:45:57 +00:00
..
bifrost panfrost: split pseudo instructions from Bifrost and Valhall 2024-08-20 12:18:19 +00:00
test bi: Rewrite dead code elimination 2024-08-20 10:03:30 +02:00
valhall pan/va: Define the LEA_BUFFER instruction 2024-09-18 13:45:57 +00:00
bi_builder.h.py panfrost: split pseudo instructions from Bifrost and Valhall 2024-08-20 12:18:19 +00:00
bi_helper_invocations.c panvk: Properly propagate helper invocations requirement 2024-08-21 18:47:02 +00:00
bi_layout.c
bi_liveness.c
bi_lower_divergent_indirects.c treewide: Use nir_shader_intrinsic_pass sometimes 2023-08-24 15:48:02 +00:00
bi_lower_swizzle.c pan/bi: Lower swizzles for 8-bit CSEL 2023-04-13 01:49:33 +00:00
bi_opcodes.c.py panfrost: split pseudo instructions from Bifrost and Valhall 2024-08-20 12:18:19 +00:00
bi_opcodes.h.py panfrost: split pseudo instructions from Bifrost and Valhall 2024-08-20 12:18:19 +00:00
bi_opt_constant_fold.c panfrost: fix shift overflow in bi_fold_constant 2024-01-26 09:40:48 +00:00
bi_opt_copy_prop.c
bi_opt_cse.c bi: Alloc replacement array once in opt_cse 2024-05-24 11:16:31 +02:00
bi_opt_dce.c bi: Rewrite dead code elimination 2024-08-20 10:03:30 +02:00
bi_opt_dual_tex.c
bi_opt_mod_props.c
bi_opt_push_ubo.c pan/bi: Lower ubo table in indices for Valhall 2024-03-11 09:23:56 +00:00
bi_packer.c.py panfrost: split pseudo instructions from Bifrost and Valhall 2024-08-20 12:18:19 +00:00
bi_pressure_schedule.c
bi_print.c panfrost: Reformat using the new style 2023-05-29 21:06:12 +00:00
bi_print_common.c
bi_print_common.h
bi_printer.c.py panfrost: split pseudo instructions from Bifrost and Valhall 2024-08-20 12:18:19 +00:00
bi_quirks.h
bi_ra.c panfrost: Reformat using the new style 2023-05-29 21:06:12 +00:00
bi_test.h panfrost: Reformat using the new style 2023-05-29 21:06:12 +00:00
bi_validate.c
bifrost.h
bifrost_compile.c pan/va: Optimize SSBO lowering on Valhall 2024-09-18 13:45:57 +00:00
bifrost_compile.h pan/bi: switch to derivative intrinsics 2024-08-14 01:34:54 +00:00
bifrost_isa.py panfrost: Update bifrost_isa.py to handle some Valhall constructs 2024-08-20 12:18:19 +00:00
bifrost_nir.h pan/bi: Export bifrost_nir_lower_load_output 2023-03-23 23:53:46 +00:00
bifrost_nir_algebraic.py pan/bi: switch to derivative intrinsics 2024-08-14 01:34:54 +00:00
bir.c
cmdline.c
compiler.h bi: Rewrite dead code elimination 2024-08-20 10:03:30 +02:00
gen_disasm.py bi: Move bi_disasm definitions to their own header 2024-06-17 07:31:50 +00:00
IR_pseudo.xml panfrost: split pseudo instructions from Bifrost and Valhall 2024-08-20 12:18:19 +00:00
meson.build panfrost: split pseudo instructions from Bifrost and Valhall 2024-08-20 12:18:19 +00:00
nodearray.h
Notes.txt
README.md

Bifrost compiler

Register file

Defined partially in software, partially in hardware.

Blend shaders

R0 - R3: input (color #0) R4 - R7: input (color #1) R8 - R15: general purpose R48: return address

Fragment

Anything live during BLEND must respect blend shader registers.

R0 - R3: preloaded (message #0) R4 - R7: preloaded (message #1) R57 - R63: preloaded (various)

R0 - R15: general purpose (full threads) R48 - R63: general purpose (full threads)

R32 - R47: general purpose (half threads, or v6)