[Mesa-dev] [PATCH 1/4] radeonsi: correct maximum wave count per SIMD
Nicolai Hähnle
nhaehnle at gmail.com
Thu Aug 24 08:17:25 UTC 2017
On 23.08.2017 22:44, Marek Olšák wrote:
> From: Marek Olšák <marek.olsak at amd.com>
>
> ---
> src/gallium/drivers/radeonsi/si_shader.c | 17 ++++++++++++++++-
> 1 file changed, 16 insertions(+), 1 deletion(-)
>
> diff --git a/src/gallium/drivers/radeonsi/si_shader.c b/src/gallium/drivers/radeonsi/si_shader.c
> index f02fc9e..186a3dd 100644
> --- a/src/gallium/drivers/radeonsi/si_shader.c
> +++ b/src/gallium/drivers/radeonsi/si_shader.c
> @@ -5029,21 +5029,36 @@ static void si_shader_dump_stats(struct si_screen *sscreen,
> struct pipe_debug_callback *debug,
> unsigned processor,
> FILE *file,
> bool check_debug_option)
> {
> const struct si_shader_config *conf = &shader->config;
> unsigned num_inputs = shader->selector ? shader->selector->info.num_inputs : 0;
> unsigned code_size = si_get_shader_binary_size(shader);
> unsigned lds_increment = sscreen->b.chip_class >= CIK ? 512 : 256;
> unsigned lds_per_wave = 0;
> - unsigned max_simd_waves = 10;
> + unsigned max_simd_waves;
> +
> + switch (sscreen->b.family) {
> + /* SGPR initialization bug workaround on Tonga and Iceland reduces
> + * the wave count to 8. */
> + case CHIP_TONGA:
> + case CHIP_ICELAND:
> + /* These always have 8 waves: */
> + case CHIP_POLARIS10:
> + case CHIP_POLARIS11:
> + case CHIP_POLARIS12:
> + max_simd_waves = 8;
This should be implied by the num_sgprs set by LLVM, though.
Cheers,
Nicolai
> + break;
> + default:
> + max_simd_waves = 10;
> + }
>
> /* Compute LDS usage for PS. */
> switch (processor) {
> case PIPE_SHADER_FRAGMENT:
> /* The minimum usage per wave is (num_inputs * 48). The maximum
> * usage is (num_inputs * 48 * 16).
> * We can get anything in between and it varies between waves.
> *
> * The 48 bytes per input for a single primitive is equal to
> * 4 bytes/component * 4 components/input * 3 points.
>
--
Lerne, wie die Welt wirklich ist,
Aber vergiss niemals, wie sie sein sollte.
More information about the mesa-dev
mailing list