diff options
author | Nicolai Hähnle <[email protected]> | 2016-05-04 19:05:14 -0500 |
---|---|---|
committer | Nicolai Hähnle <[email protected]> | 2016-05-09 11:52:46 -0500 |
commit | d8f3e8e6263214caa9daf914487595e6bd5aa0df (patch) | |
tree | d77a3aa78a3cd5097b243e5461c4e813accfe47e | |
parent | ad1782cfb5eaa633582c8a7d026690878ab54064 (diff) |
radeonsi: always allocate export memory for pixel shaders
Experiments with framebuffer-no-attachments type draw calls have shown that
NULL exports stall terribly unless we ensure that export memory is allocated
by the SPI.
Reviewed-by: Marek Olšák <[email protected]>
-rw-r--r-- | src/gallium/drivers/radeonsi/si_state_shaders.c | 15 |
1 files changed, 10 insertions, 5 deletions
diff --git a/src/gallium/drivers/radeonsi/si_state_shaders.c b/src/gallium/drivers/radeonsi/si_state_shaders.c index 0bfd7e8d111..11e73098253 100644 --- a/src/gallium/drivers/radeonsi/si_state_shaders.c +++ b/src/gallium/drivers/radeonsi/si_state_shaders.c @@ -688,14 +688,19 @@ static void si_shader_ps(struct si_shader *shader) spi_shader_col_format = si_get_spi_shader_col_format(shader); cb_shader_mask = si_get_cb_shader_mask(spi_shader_col_format); - /* This must be non-zero for alpha-test/kill to work. - * The hardware ignores the EXEC mask if no export memory is allocated. + /* Ensure that some export memory is always allocated, for two reasons: + * + * 1) Correctness: The hardware ignores the EXEC mask if no export + * memory is allocated, so KILL and alpha test do not work correctly + * without this. + * 2) Performance: Every shader needs at least a NULL export, even when + * it writes no color/depth output. The NULL export instruction + * stalls without this setting. + * * Don't add this to CB_SHADER_MASK. */ if (!spi_shader_col_format && - !info->writes_z && !info->writes_stencil && !info->writes_samplemask && - (shader->selector->info.uses_kill || - shader->key.ps.epilog.alpha_func != PIPE_FUNC_ALWAYS)) + !info->writes_z && !info->writes_stencil && !info->writes_samplemask) spi_shader_col_format = V_028714_SPI_SHADER_32_R; si_pm4_set_reg(pm4, R_0286CC_SPI_PS_INPUT_ENA, input_ena); |