mesa/src/broadcom
Jose Maria Casanova Crespo 28e584b687 v3dv: enable lowered shaderFloat16/Int16/Int8 + VK_KHR_shader_float16_int8
V3D 7.1 now exposes shaderFloat16, shaderInt8, shaderInt16 and
VK_KHR_shader_float16_int8.

Partial native Float16 support is already available. But the rest of
sub-32-bit ALU operations are widened to 32-bit by nir_lower_bit_size
in v3d_lower_nir(); conversion and pack operations are kept at their
native bit width so the QPU's 16-bit pack/unpack paths on mul/mov can
be used.

Assisted-by: Claude Opus 4.7
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41810>
2026-06-04 13:29:39 +00:00
..
ci v3dv: enable lowered shaderFloat16/Int16/Int8 + VK_KHR_shader_float16_int8 2026-06-04 13:29:39 +00:00
cle broadcom/cle: parse once the XML spec 2026-04-06 09:17:15 +00:00
clif broadcom: use Mesa logging functions 2026-04-06 07:40:55 +00:00
common v3dv: Enable meta_copy_buffer with TFU for V3D 7.1 2026-05-26 07:50:42 +00:00
compiler v3d: emit packed-f16 ALU ops natively on V3D 7.1 2026-06-04 13:29:39 +00:00
drm-shim v3d/drm-shim: add GPU selection 2026-05-27 10:19:50 +00:00
ds mesa: replace most occurrences of getenv() with os_get_option() 2025-11-06 04:36:13 +00:00
perfcntrs broadcom: use Mesa logging functions 2026-04-06 07:40:55 +00:00
qpu broadcom/qpu: expose V3D 7.1 packed-f16 instructions 2026-06-04 13:29:39 +00:00
simulator broadcom/simulator: V3D is always 4.2 or above 2026-05-27 10:19:50 +00:00
vulkan v3dv: enable lowered shaderFloat16/Int16/Int8 + VK_KHR_shader_float16_int8 2026-06-04 13:29:39 +00:00
.editorconfig
meson.build broadcom: Add perfetto data source 2024-12-13 12:29:11 +00:00