fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2026-05-20 13:28:09 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 4
mesa/src/intel/compiler
History
Alyssa Rosenzweig 3308626e12 jay/assign_flags: don't burn a flag for ballots 
Increases GPR pressure somehow but it's obviously the right thing to do.

SIMD16:

   Totals:
   Instrs: 2767536 -> 2767381 (-0.01%); split: -0.01%, +0.00%
   CodeSize: 44323392 -> 40075680 (-9.58%); split: -9.58%, +0.00%

   Totals from 2147 (81.11% of 2647) affected shaders:
   Instrs: 2704498 -> 2704343 (-0.01%); split: -0.01%, +0.00%
   CodeSize: 43477568 -> 39229856 (-9.77%); split: -9.77%, +0.00%

SIMD32:

   Totals:
   Instrs: 4731031 -> 4746775 (+0.33%); split: -0.33%, +0.67%
   CodeSize: 76609152 -> 70004080 (-8.62%); split: -8.68%, +0.06%
   Number of spill instructions: 50110 -> 50187 (+0.15%); split: -0.00%, +0.16%
   Number of fill instructions: 51341 -> 51804 (+0.90%); split: -0.00%, +0.91%

   Totals from 2136 (80.70% of 2647) affected shaders:
   Instrs: 4666677 -> 4682421 (+0.34%); split: -0.34%, +0.67%
   CodeSize: 75735136 -> 69130064 (-8.72%); split: -8.78%, +0.06%
   Number of spill instructions: 50108 -> 50185 (+0.15%); split: -0.00%, +0.16%
   Number of fill instructions: 51339 -> 51802 (+0.90%); split: -0.00%, +0.91%

Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41215>
2026-04-28 23:13:50 +00:00
..
brw brw: Don't lower phis involved in DPAS instructions to scalar 2026-04-27 18:09:16 +00:00
elk intel/elk: Remove dead TXL_LZ/TXF_LZ opcodes 2026-04-17 15:13:00 +00:00
jay jay/assign_flags: don't burn a flag for ballots 2026-04-28 23:13:50 +00:00
brw_device_sha1_gen_c.py Rename sha1_* and sha_* names to blake3_* 2026-03-23 07:03:28 +00:00
brw_list.h intel/compiler: Use SPDX annotations 2026-01-24 20:37:31 +00:00
intel_gfx_ver_enum.h intel/compiler: Use SPDX annotations 2026-01-24 20:37:31 +00:00
intel_nir.c intel/compiler: Use nir_split_conversions() 2025-04-07 17:45:21 -05:00
intel_nir.h intel/nir: Make intel_nir_lower_sparse work for either brw or jay 2026-04-10 18:21:21 +00:00
intel_nir_blockify_uniform_loads.c intel/compiler: Use SPDX annotations 2026-01-24 20:37:31 +00:00
intel_nir_clamp_image_1d_2d_array_sizes.c intel/compiler: Use SPDX annotations 2026-01-24 20:37:31 +00:00
intel_nir_clamp_per_vertex_loads.c intel/compiler: Use SPDX annotations 2026-01-24 20:37:31 +00:00
intel_nir_lower_non_uniform_barycentric_at_sample.c intel/compiler: Use SPDX annotations 2026-01-24 20:37:31 +00:00
intel_nir_lower_non_uniform_resource_intel.c intel/compiler: Use SPDX annotations 2026-01-24 20:37:31 +00:00
intel_nir_lower_printf.c intel/compiler: Use SPDX annotations 2026-01-24 20:37:31 +00:00
intel_nir_lower_shading_rate_output.c intel/compiler: Use SPDX annotations 2026-01-24 20:37:31 +00:00
intel_nir_lower_sparse.c intel/nir: Make intel_nir_lower_sparse work for either brw or jay 2026-04-10 18:21:21 +00:00
intel_nir_opt_peephole_ffma.c intel/nir_opt_peephole_ffma: fix fp_math_ctlr for modifiers 2026-04-28 18:26:58 +00:00
intel_nir_opt_peephole_imul32x16.c intel/compiler: Use SPDX annotations 2026-01-24 20:37:31 +00:00
intel_nir_tcs_workarounds.c nir: add and use block predecessor helpers 2026-04-08 15:06:32 +00:00
intel_prim.h intel/compiler: Use SPDX annotations 2026-01-24 20:37:31 +00:00
intel_shader_enums.h brw: Drop BRW_VARYING_SLOT_PAD and brw_varying_slot enum 2026-02-16 15:15:35 -08:00
meson.build intel: add Jay 2026-04-10 18:21:21 +00:00