From 7d84bb00dc4d75652e07d0a3d9f0663431f9bdc8 Mon Sep 17 00:00:00 2001 From: Alyssa Rosenzweig Date: Fri, 17 Jun 2022 12:53:49 -0400 Subject: [PATCH] panfrost: Enable more FP16 caps on Valhall MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit This brings the FP16 capabilities of Valhall to parity with Bifrost. Supporting FP16 constant buffers in particular reduces ALU in a ton of GLES shaders, so that's a nice win. FP16 derivatives get vectorized which is a big win where that applies, but they are considerably less common. The lost shaders are from enabling PIPE_SHADER_CAP_FP16_CONST_BUFFERS (these shaders compile on Midgard but not on Bifrost). The shaders in question declare the same uniform in linked vertex and fragment shaders with different precisions. This is contrary to the GLSL ES specification, which states precisions must match for default uniforms of linked shaders. All the lost shaders are in 8 Ball Pool and Hill Climb Racing. As those are proprietary games, if that becomes a problem in the future, drirc is the solution. total instructions in shared programs: 2697897 -> 2674595 (-0.86%) instructions in affected programs: 1019922 -> 996620 (-2.28%) helped: 4838 HURT: 2599 helped stats (abs) min: 1.0 max: 52.0 x̄: 7.13 x̃: 5 helped stats (rel) min: 0.16% max: 46.51% x̄: 8.04% x̃: 5.33% HURT stats (abs) min: 1.0 max: 36.0 x̄: 4.30 x̃: 3 HURT stats (rel) min: 0.17% max: 133.33% x̄: 10.53% x̃: 3.85% 95% mean confidence interval for instructions value: -3.32 -2.95 95% mean confidence interval for instructions %-change: -1.89% -1.22% Instructions are helped. total cycles in shared programs: 141764.61 -> 140602.88 (-0.82%) cycles in affected programs: 5728.22 -> 4566.48 (-20.28%) helped: 665 HURT: 89 helped stats (abs) min: 0.015625 max: 15.0 x̄: 1.75 x̃: 0 helped stats (rel) min: 0.30% max: 61.54% x̄: 11.17% x̃: 4.62% HURT stats (abs) min: 0.015625 max: 0.265625 x̄: 0.04 x̃: 0 HURT stats (rel) min: 0.30% max: 66.67% x̄: 6.77% x̃: 1.94% 95% mean confidence interval for cycles value: -1.77 -1.31 95% mean confidence interval for cycles %-change: -10.11% -7.99% Cycles are helped. total fma in shared programs: 22577.56 -> 22575.91 (<.01%) fma in affected programs: 2422.78 -> 2421.12 (-0.07%) helped: 533 HURT: 653 helped stats (abs) min: 0.015625 max: 0.0625 x̄: 0.03 x̃: 0 helped stats (rel) min: 0.30% max: 50.00% x̄: 8.25% x̃: 1.35% HURT stats (abs) min: 0.015625 max: 0.125 x̄: 0.03 x̃: 0 HURT stats (rel) min: 0.19% max: 100.00% x̄: 4.53% x̃: 2.08% 95% mean confidence interval for fma value: -0.00 0.00 95% mean confidence interval for fma %-change: -1.98% -0.44% Inconclusive result (value mean confidence interval includes 0). total cvt in shared programs: 14460.95 -> 14122.50 (-2.34%) cvt in affected programs: 6159.02 -> 5820.56 (-5.50%) helped: 4827 HURT: 2577 helped stats (abs) min: 0.015625 max: 0.796875 x̄: 0.11 x̃: 0 helped stats (rel) min: 0.20% max: 81.82% x̄: 17.78% x̃: 12.90% HURT stats (abs) min: 0.015625 max: 0.546875 x̄: 0.07 x̃: 0 HURT stats (rel) min: 0.00% max: 600.00% x̄: 43.66% x̃: 13.04% 95% mean confidence interval for cvt value: -0.05 -0.04 95% mean confidence interval for cvt %-change: 2.28% 4.93% Inconclusive result (value mean confidence interval and %-change mean confidence interval disagree). total sfu in shared programs: 7593.56 -> 7571.06 (-0.30%) sfu in affected programs: 357.19 -> 334.69 (-6.30%) helped: 149 HURT: 1 helped stats (abs) min: 0.0625 max: 0.25 x̄: 0.15 x̃: 0 helped stats (rel) min: 5.26% max: 36.36% x̄: 6.79% x̃: 5.56% HURT stats (abs) min: 0.0625 max: 0.0625 x̄: 0.06 x̃: 0 HURT stats (rel) min: 3.57% max: 3.57% x̄: 3.57% x̃: 3.57% 95% mean confidence interval for sfu value: -0.16 -0.14 95% mean confidence interval for sfu %-change: -7.51% -5.93% Sfu are helped. total v in shared programs: 8722.62 -> 8722.31 (<.01%) v in affected programs: 1.62 -> 1.31 (-19.23%) helped: 2 HURT: 0 total ls in shared programs: 129666 -> 128494 (-0.90%) ls in affected programs: 4163 -> 2991 (-28.15%) helped: 192 HURT: 0 helped stats (abs) min: 1.0 max: 15.0 x̄: 6.10 x̃: 5 helped stats (rel) min: 4.35% max: 75.00% x̄: 30.23% x̃: 26.32% 95% mean confidence interval for ls value: -6.67 -5.54 95% mean confidence interval for ls %-change: -32.67% -27.79% Ls are helped. total quadwords in shared programs: 1461496 -> 1449768 (-0.80%) quadwords in affected programs: 273592 -> 261864 (-4.29%) helped: 1992 HURT: 687 helped stats (abs) min: 8.0 max: 24.0 x̄: 8.76 x̃: 8 helped stats (rel) min: 1.43% max: 50.00% x̄: 16.30% x̃: 11.11% HURT stats (abs) min: 8.0 max: 16.0 x̄: 8.31 x̃: 8 HURT stats (rel) min: 1.92% max: 100.00% x̄: 36.39% x̃: 25.00% 95% mean confidence interval for quadwords value: -4.67 -4.08 95% mean confidence interval for quadwords %-change: -3.95% -1.62% Quadwords are helped. total threads in shared programs: 53496 -> 53551 (0.10%) threads in affected programs: 112 -> 167 (49.11%) helped: 74 HURT: 19 helped stats (abs) min: 1.0 max: 1.0 x̄: 1.00 x̃: 1 helped stats (rel) min: 100.00% max: 100.00% x̄: 100.00% x̃: 100.00% HURT stats (abs) min: 1.0 max: 1.0 x̄: 1.00 x̃: 1 HURT stats (rel) min: 50.00% max: 50.00% x̄: 50.00% x̃: 50.00% 95% mean confidence interval for threads value: 0.42 0.76 95% mean confidence interval for threads %-change: 56.83% 81.88% Threads are helped. total loops in shared programs: 128 -> 127 (-0.78%) loops in affected programs: 1 -> 0 helped: 1 HURT: 0 total fills in shared programs: 684 -> 672 (-1.75%) fills in affected programs: 160 -> 148 (-7.50%) helped: 2 HURT: 0 Signed-off-by: Alyssa Rosenzweig Part-of: --- src/gallium/drivers/panfrost/pan_screen.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/src/gallium/drivers/panfrost/pan_screen.c b/src/gallium/drivers/panfrost/pan_screen.c index b7cc255..9a365aa 100644 --- a/src/gallium/drivers/panfrost/pan_screen.c +++ b/src/gallium/drivers/panfrost/pan_screen.c @@ -431,11 +431,11 @@ panfrost_get_shader_param(struct pipe_screen *screen, return !is_nofp16; case PIPE_SHADER_CAP_FP16_DERIVATIVES: case PIPE_SHADER_CAP_FP16_CONST_BUFFERS: - return pan_is_bifrost(dev) && !is_nofp16; + return dev->arch >= 6 && !is_nofp16; case PIPE_SHADER_CAP_INT16: /* XXX: Advertise this CAP when a proper fix to lower_precision * lands. GLSL IR validation failure in glmark2 -bterrain */ - return pan_is_bifrost(dev) && !is_nofp16 && is_deqp; + return dev->arch >= 6 && !is_nofp16 && is_deqp; case PIPE_SHADER_CAP_INT64_ATOMICS: case PIPE_SHADER_CAP_DROUND_SUPPORTED: -- 2.7.4