OpenHarmony/third_party_mesa3d
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

ac: move ac_get_num_physical_vgprs into radeon_info

Browse Source 
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
This commit is contained in:
Marek Olšák
2019-09-12 19:51:13 -04:00
parent 0692ae34e9
commit aae35fbd3a
3 changed files with 5 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
src/amd/common/ac_gpu_info.c
View File

@@ -597,6 +597,7 @@ bool ac_query_gpu_info(int fd, void *dev_p,
else else
info->num_physical_sgprs_per_simd = 512; info->num_physical_sgprs_per_simd = 512;
info->num_physical_wave64_vgprs_per_simd = info->chip_class >= GFX10 ? 512 : 256;
return true; return true;
} }

11
src/amd/common/ac_gpu_info.h
View File

@@ -143,6 +143,7 @@ struct radeon_info {
uint32_t max_sh_per_se; /* shader arrays per shader engine */ uint32_t max_sh_per_se; /* shader arrays per shader engine */
uint32_t max_wave64_per_simd; uint32_t max_wave64_per_simd;
uint32_t num_physical_sgprs_per_simd; uint32_t num_physical_sgprs_per_simd;
uint32_t num_physical_wave64_vgprs_per_simd;
/* Render backends (color + depth blocks). */ /* Render backends (color + depth blocks). */
uint32_t r300_num_gb_pipes; uint32_t r300_num_gb_pipes;
@@ -191,16 +192,6 @@ unsigned ac_get_compute_resource_limits(struct radeon_info *info,
unsigned max_waves_per_sh, unsigned max_waves_per_sh,
unsigned threadgroups_per_cu); unsigned threadgroups_per_cu);
static inline unsigned ac_get_num_physical_vgprs(enum chip_class chip_class,
unsigned wave_size)
{
/* The number is per SIMD. */
if (chip_class >= GFX10)
return wave_size == 32 ? 1024 : 512;
else
return 256;
}
#ifdef __cplusplus #ifdef __cplusplus
} }
#endif #endif

6
src/gallium/drivers/radeonsi/si_shader.c
View File

@@ -5460,7 +5460,7 @@ static void si_calculate_max_simd_waves(struct si_shader *shader)
if (conf->num_vgprs) { if (conf->num_vgprs) {
/* Always print wave limits as Wave64, so that we can compare /* Always print wave limits as Wave64, so that we can compare
* Wave32 and Wave64 with shader-db fairly. */ * Wave32 and Wave64 with shader-db fairly. */
unsigned max_vgprs = ac_get_num_physical_vgprs(sscreen->info.chip_class, 64); unsigned max_vgprs = sscreen->info.num_physical_wave64_vgprs_per_simd;
max_simd_waves = MIN2(max_simd_waves, max_vgprs / conf->num_vgprs); max_simd_waves = MIN2(max_simd_waves, max_vgprs / conf->num_vgprs);
} }
@@ -7176,8 +7176,8 @@ int si_compile_tgsi_shader(struct si_screen *sscreen,
*/ */
if (sel->type == PIPE_SHADER_COMPUTE) { if (sel->type == PIPE_SHADER_COMPUTE) {
unsigned wave_size = sscreen->compute_wave_size; unsigned wave_size = sscreen->compute_wave_size;
unsigned max_vgprs = ac_get_num_physical_vgprs(sscreen->info.chip_class, unsigned max_vgprs = sscreen->info.num_physical_wave64_vgprs_per_simd *
wave_size); (wave_size == 32 ? 2 : 1);
unsigned max_sgprs = sscreen->info.num_physical_sgprs_per_simd; unsigned max_sgprs = sscreen->info.num_physical_sgprs_per_simd;
unsigned max_sgprs_per_wave = 128; unsigned max_sgprs_per_wave = 128;
unsigned simds_per_tg = 4; /* assuming WGP mode on gfx10 */ unsigned simds_per_tg = 4; /* assuming WGP mode on gfx10 */