Juan A. Suarez Romero 1e0e521a7d broadcom/compiler: move stores to the end of shader ...

It is possible that shader comes with output stores executed before
loading inputs. As the memory to read the inputs and store the outputs
is the same, this mean it could be overwriting the inputs before reading
them.

This move avoids this situation.

This partially improves
https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/33053.

Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Signed-off-by: Juan A. Suarez Romero <jasuarez@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/33310>

2025-02-03 17:10:47 +00:00

..

meson.build

format: Generate endian-independent format aliases

2024-07-19 13:50:42 +00:00

nir_to_vir.c

nir/opt_load_store_vectorize: make hole_size signed to indicate overlapping loads

2025-01-01 00:03:55 +00:00

qpu_schedule.c

broadcom: fix pairing tmu lookup with previous ldtmu

2024-10-10 06:58:15 +00:00

qpu_validate.c

broadcom/compiler: validate rtop + thrsw hazard

2024-06-27 06:43:09 +00:00

v3d_compiler.h

broadcom: move double-buffer heuristic helpers to the compiler

2024-11-21 07:21:47 +00:00

v3d_nir_lower_algebraic.py

broadcom/compiler: generate mali opcodes for clamping on Pi5

2024-10-03 09:02:08 +00:00

v3d_nir_lower_image_load_store.c

broadcom: follow version naming convention

2024-07-08 11:19:31 +00:00

v3d_nir_lower_io.c

broadcom/compiler: implement load_kernel_input

2024-06-26 10:04:03 +00:00

v3d_nir_lower_line_smooth.c

treewide: use nir_metadata_control_flow

2024-06-17 16:28:14 -04:00

v3d_nir_lower_load_store_bitsize.c

broadcom/compiler: ensure offset source exists

2024-12-16 10:56:38 +00:00

v3d_nir_lower_logic_ops.c

treewide: use nir_metadata_control_flow

2024-06-17 16:28:14 -04:00

v3d_nir_lower_scratch.c

treewide: use nir_metadata_control_flow

2024-06-17 16:28:14 -04:00

v3d_nir_lower_txf_ms.c

…

v3d_packing.c

…

v3d_tex.c

broadcom/compiler: simplify v3d_vir_emit_tex

2024-05-09 09:29:44 +02:00

vir_dump.c

…

vir_live_variables.c

…

vir_opt_constant_alu.c

…

vir_opt_copy_propagate.c

broadcom/compiler: disallow copy propagation of FMOV exclusive modifiers

2024-07-10 08:29:50 +02:00

vir_opt_dead_code.c

broadcom/compiler: drop multop if we dce umul24

2024-06-27 06:43:09 +00:00

vir_opt_redundant_flags.c

…

vir_opt_small_immediates.c

broadcom/compiler: don't use small immediates in geometry stages

2024-09-25 14:21:46 +00:00

vir_register_allocate.c

v3d: avoid 0-size variable length array

2025-01-07 14:21:42 +00:00

vir_to_qpu.c

…

vir.c

broadcom/compiler: move stores to the end of shader

2025-02-03 17:10:47 +00:00