radeonsi/nir: disable GLSL IR loop unrolling

Delaying unrolling and allowing NIR to do it instead has been shown
to result in better code in drivers such as i965. shader-db results
appear to show the same is true for radeonsi.

The other advantage is that using NIR unrolling improves compile
times significantly.

Totals from affected shaders:
SGPRS: 9624 -> 10016 (4.07 %)
VGPRS: 6800 -> 6464 (-4.94 %)
Spilled SGPRs: 0 -> 2 (0.00 %)
Spilled VGPRs: 0 -> 0 (0.00 %)
Private memory VGPRs: 0 -> 0 (0.00 %)
Scratch size: 0 -> 0 (0.00 %) dwords per thread
Code Size: 359176 -> 332264 (-7.49 %) bytes
LDS: 0 -> 0 (0.00 %) blocks
Max Waves: 1355 -> 1432 (5.68 %)
Wait states: 0 -> 0 (0.00 %)

Reviewed-by: Marek Olšák <marek.olsak@amd.com>

diff --git a/src/gallium/drivers/radeonsi/si_get.c b/src/gallium/drivers/radeonsi/si_get.c
index ea1ac1134cfaa4a6502bf63f71abc5ab0e67b181..19426334fb6f1eacfcf36bb5bca3511ffeaee482 100644 (file)
--- a/src/gallium/drivers/radeonsi/si_get.c
+++ b/src/gallium/drivers/radeonsi/si_get.c
@@ -441,6 +441,8 @@ static int si_get_shader_param(struct pipe_screen* pscreen,
        case PIPE_SHADER_CAP_MAX_SHADER_IMAGES:
                return SI_NUM_IMAGES;
        case PIPE_SHADER_CAP_MAX_UNROLL_ITERATIONS_HINT:
+               if (sscreen->debug_flags & DBG(NIR))
+                       return 0;
                return 32;
        case PIPE_SHADER_CAP_PREFERRED_IR:
                if (sscreen->debug_flags & DBG(NIR))