[Mesa-dev] [PATCH 5/5] radeonsi: add a workaround for a compute VGPR-usage LLVM bug

Grazvydas Ignotas notasas at gmail.com
Wed Jul 13 09:32:18 UTC 2016


On Tue, Jul 12, 2016 at 11:52 PM, Marek Olšák <maraeo at gmail.com> wrote:
> From: Marek Olšák <marek.olsak at amd.com>
>
> This patch may be dropped depending on feedback.
>
> Cc: 12.0 <mesa-stable at lists.freedesktop.org>
> ---
>  src/gallium/drivers/radeonsi/si_shader.c | 33 ++++++++++++++++++++++++++++++++
>  1 file changed, 33 insertions(+)
>
> diff --git a/src/gallium/drivers/radeonsi/si_shader.c b/src/gallium/drivers/radeonsi/si_shader.c
> index 79c3496..81d071e 100644
> --- a/src/gallium/drivers/radeonsi/si_shader.c
> +++ b/src/gallium/drivers/radeonsi/si_shader.c
> @@ -6705,6 +6705,39 @@ int si_compile_tgsi_shader(struct si_screen *sscreen,
>
>         radeon_llvm_dispose(&ctx.radeon_bld);
>
> +       /* Validate SGPR and VGPR usage for compute to detect compiler bugs. */
> +       if (sel->type == PIPE_SHADER_COMPUTE) {
> +               unsigned *props = sel->info.properties;
> +               unsigned wave_size = 64;
> +               unsigned max_vgprs = 256;
> +               unsigned max_sgprs = sscreen->b.chip_class >= VI ? 800 : 512;
> +               unsigned max_sgprs_per_wave = 128;
> +               unsigned min_waves_per_cu =
> +                       DIV_ROUND_UP(props[TGSI_PROPERTY_CS_FIXED_BLOCK_WIDTH] *
> +                                    props[TGSI_PROPERTY_CS_FIXED_BLOCK_HEIGHT] *
> +                                    props[TGSI_PROPERTY_CS_FIXED_BLOCK_DEPTH],
> +                                    wave_size);
> +               unsigned min_waves_per_simd = DIV_ROUND_UP(min_waves_per_cu, 4);
> +
> +               max_vgprs = max_vgprs / min_waves_per_simd;
> +               max_sgprs = MIN2(max_sgprs / min_waves_per_simd, max_sgprs_per_wave);
> +
> +               if (shader->config.num_sgprs > max_sgprs ||
> +                   shader->config.num_vgprs > max_vgprs) {
> +                       fprintf(stderr, "LLVM failed to compile a shader correctly: "
> +                               "SGPR:VGPR usage is %u:%u, but the hw limit is %u:%u\n",
> +                               shader->config.num_sgprs, shader->config.num_vgprs,
> +                               max_sgprs, max_vgprs);
> +
> +                       /* Just terminate the process, because dependent
> +                        * shaders can hang due to bad input data, but use
> +                        * the env var to allow shader-db to work.
> +                        */
> +                       if (!debug_get_bool_option("SI_PASS_BAD_SHADERS", false))
> +                               exit(0);

Hmm exit(0) usually means "the program finished successfully" and not
everyone might notice the error message. I think exit(1) or even
abort() would be better.

Gražvydas


More information about the mesa-dev mailing list