From: Dave Airlie Date: Mon, 23 Apr 2018 00:42:21 +0000 (+1000) Subject: ac/radv/radeonsi: refactor harvest config register getters. X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=a90c9f33cf5c8f7674de989b2c9146466e871459;p=mesa.git ac/radv/radeonsi: refactor harvest config register getters. This refactors the code out to share it between radv and radeonsi. Reviewed-by: Bas Nieuwenhuizen Acked-by: Nicolai Hähnle Reviewed-by: Samuel Pitoiset --- diff --git a/src/amd/common/ac_gpu_info.c b/src/amd/common/ac_gpu_info.c index 47a87650a6d..031fd183b6f 100644 --- a/src/amd/common/ac_gpu_info.c +++ b/src/amd/common/ac_gpu_info.c @@ -647,3 +647,116 @@ ac_get_raster_config(struct radeon_info *info, *raster_config_p = raster_config; *raster_config_1_p = raster_config_1; } + +void +ac_get_harvested_configs(struct radeon_info *info, + unsigned raster_config, + unsigned *cik_raster_config_1_p, + unsigned *raster_config_se) +{ + unsigned sh_per_se = MAX2(info->max_sh_per_se, 1); + unsigned num_se = MAX2(info->max_se, 1); + unsigned rb_mask = info->enabled_rb_mask; + unsigned num_rb = MIN2(info->num_render_backends, 16); + unsigned rb_per_pkr = MIN2(num_rb / num_se / sh_per_se, 2); + unsigned rb_per_se = num_rb / num_se; + unsigned se_mask[4]; + unsigned se; + + se_mask[0] = ((1 << rb_per_se) - 1) & rb_mask; + se_mask[1] = (se_mask[0] << rb_per_se) & rb_mask; + se_mask[2] = (se_mask[1] << rb_per_se) & rb_mask; + se_mask[3] = (se_mask[2] << rb_per_se) & rb_mask; + + assert(num_se == 1 || num_se == 2 || num_se == 4); + assert(sh_per_se == 1 || sh_per_se == 2); + assert(rb_per_pkr == 1 || rb_per_pkr == 2); + + + if (info->chip_class >= CIK) { + unsigned raster_config_1 = *cik_raster_config_1_p; + if ((num_se > 2) && ((!se_mask[0] && !se_mask[1]) || + (!se_mask[2] && !se_mask[3]))) { + raster_config_1 &= C_028354_SE_PAIR_MAP; + + if (!se_mask[0] && !se_mask[1]) { + raster_config_1 |= + S_028354_SE_PAIR_MAP(V_028354_RASTER_CONFIG_SE_PAIR_MAP_3); + } else { + raster_config_1 |= + S_028354_SE_PAIR_MAP(V_028354_RASTER_CONFIG_SE_PAIR_MAP_0); + } + *cik_raster_config_1_p = raster_config_1; + } + } + + for (se = 0; se < num_se; se++) { + unsigned pkr0_mask = ((1 << rb_per_pkr) - 1) << (se * rb_per_se); + unsigned pkr1_mask = pkr0_mask << rb_per_pkr; + int idx = (se / 2) * 2; + + raster_config_se[se] = raster_config; + if ((num_se > 1) && (!se_mask[idx] || !se_mask[idx + 1])) { + raster_config_se[se] &= C_028350_SE_MAP; + + if (!se_mask[idx]) { + raster_config_se[se] |= + S_028350_SE_MAP(V_028350_RASTER_CONFIG_SE_MAP_3); + } else { + raster_config_se[se] |= + S_028350_SE_MAP(V_028350_RASTER_CONFIG_SE_MAP_0); + } + } + + pkr0_mask &= rb_mask; + pkr1_mask &= rb_mask; + if (rb_per_se > 2 && (!pkr0_mask || !pkr1_mask)) { + raster_config_se[se] &= C_028350_PKR_MAP; + + if (!pkr0_mask) { + raster_config_se[se] |= + S_028350_PKR_MAP(V_028350_RASTER_CONFIG_PKR_MAP_3); + } else { + raster_config_se[se] |= + S_028350_PKR_MAP(V_028350_RASTER_CONFIG_PKR_MAP_0); + } + } + + if (rb_per_se >= 2) { + unsigned rb0_mask = 1 << (se * rb_per_se); + unsigned rb1_mask = rb0_mask << 1; + + rb0_mask &= rb_mask; + rb1_mask &= rb_mask; + if (!rb0_mask || !rb1_mask) { + raster_config_se[se] &= C_028350_RB_MAP_PKR0; + + if (!rb0_mask) { + raster_config_se[se] |= + S_028350_RB_MAP_PKR0(V_028350_RASTER_CONFIG_RB_MAP_3); + } else { + raster_config_se[se] |= + S_028350_RB_MAP_PKR0(V_028350_RASTER_CONFIG_RB_MAP_0); + } + } + + if (rb_per_se > 2) { + rb0_mask = 1 << (se * rb_per_se + rb_per_pkr); + rb1_mask = rb0_mask << 1; + rb0_mask &= rb_mask; + rb1_mask &= rb_mask; + if (!rb0_mask || !rb1_mask) { + raster_config_se[se] &= C_028350_RB_MAP_PKR1; + + if (!rb0_mask) { + raster_config_se[se] |= + S_028350_RB_MAP_PKR1(V_028350_RASTER_CONFIG_RB_MAP_3); + } else { + raster_config_se[se] |= + S_028350_RB_MAP_PKR1(V_028350_RASTER_CONFIG_RB_MAP_0); + } + } + } + } + } +} diff --git a/src/amd/common/ac_gpu_info.h b/src/amd/common/ac_gpu_info.h index de566c62fa9..7af6fbfca97 100644 --- a/src/amd/common/ac_gpu_info.h +++ b/src/amd/common/ac_gpu_info.h @@ -134,6 +134,10 @@ int ac_get_gs_table_depth(enum chip_class chip_class, enum radeon_family family) void ac_get_raster_config(struct radeon_info *info, uint32_t *raster_config_p, uint32_t *raster_config_1_p); +void ac_get_harvested_configs(struct radeon_info *info, + unsigned raster_config, + unsigned *cik_raster_config_1_p, + unsigned *raster_config_se); static inline unsigned ac_get_max_simd_waves(enum radeon_family family) { diff --git a/src/amd/vulkan/si_cmd_buffer.c b/src/amd/vulkan/si_cmd_buffer.c index 2140368c80d..4c3a888f3cf 100644 --- a/src/amd/vulkan/si_cmd_buffer.c +++ b/src/amd/vulkan/si_cmd_buffer.c @@ -41,97 +41,16 @@ si_write_harvested_raster_configs(struct radv_physical_device *physical_device, unsigned raster_config, unsigned raster_config_1) { - unsigned sh_per_se = MAX2(physical_device->rad_info.max_sh_per_se, 1); unsigned num_se = MAX2(physical_device->rad_info.max_se, 1); - unsigned rb_mask = physical_device->rad_info.enabled_rb_mask; - unsigned num_rb = MIN2(physical_device->rad_info.num_render_backends, 16); - unsigned rb_per_pkr = MIN2(num_rb / num_se / sh_per_se, 2); - unsigned rb_per_se = num_rb / num_se; - unsigned se_mask[4]; + unsigned raster_config_se[4]; unsigned se; - se_mask[0] = ((1 << rb_per_se) - 1) & rb_mask; - se_mask[1] = (se_mask[0] << rb_per_se) & rb_mask; - se_mask[2] = (se_mask[1] << rb_per_se) & rb_mask; - se_mask[3] = (se_mask[2] << rb_per_se) & rb_mask; - - assert(num_se == 1 || num_se == 2 || num_se == 4); - assert(sh_per_se == 1 || sh_per_se == 2); - assert(rb_per_pkr == 1 || rb_per_pkr == 2); - - /* XXX: I can't figure out what the *_XSEL and *_YSEL - * fields are for, so I'm leaving them as their default - * values. */ + ac_get_harvested_configs(&physical_device->rad_info, + raster_config, + &raster_config_1, + raster_config_se); for (se = 0; se < num_se; se++) { - unsigned raster_config_se = raster_config; - unsigned pkr0_mask = ((1 << rb_per_pkr) - 1) << (se * rb_per_se); - unsigned pkr1_mask = pkr0_mask << rb_per_pkr; - int idx = (se / 2) * 2; - - if ((num_se > 1) && (!se_mask[idx] || !se_mask[idx + 1])) { - raster_config_se &= C_028350_SE_MAP; - - if (!se_mask[idx]) { - raster_config_se |= - S_028350_SE_MAP(V_028350_RASTER_CONFIG_SE_MAP_3); - } else { - raster_config_se |= - S_028350_SE_MAP(V_028350_RASTER_CONFIG_SE_MAP_0); - } - } - - pkr0_mask &= rb_mask; - pkr1_mask &= rb_mask; - if (rb_per_se > 2 && (!pkr0_mask || !pkr1_mask)) { - raster_config_se &= C_028350_PKR_MAP; - - if (!pkr0_mask) { - raster_config_se |= - S_028350_PKR_MAP(V_028350_RASTER_CONFIG_PKR_MAP_3); - } else { - raster_config_se |= - S_028350_PKR_MAP(V_028350_RASTER_CONFIG_PKR_MAP_0); - } - } - - if (rb_per_se >= 2) { - unsigned rb0_mask = 1 << (se * rb_per_se); - unsigned rb1_mask = rb0_mask << 1; - - rb0_mask &= rb_mask; - rb1_mask &= rb_mask; - if (!rb0_mask || !rb1_mask) { - raster_config_se &= C_028350_RB_MAP_PKR0; - - if (!rb0_mask) { - raster_config_se |= - S_028350_RB_MAP_PKR0(V_028350_RASTER_CONFIG_RB_MAP_3); - } else { - raster_config_se |= - S_028350_RB_MAP_PKR0(V_028350_RASTER_CONFIG_RB_MAP_0); - } - } - - if (rb_per_se > 2) { - rb0_mask = 1 << (se * rb_per_se + rb_per_pkr); - rb1_mask = rb0_mask << 1; - rb0_mask &= rb_mask; - rb1_mask &= rb_mask; - if (!rb0_mask || !rb1_mask) { - raster_config_se &= C_028350_RB_MAP_PKR1; - - if (!rb0_mask) { - raster_config_se |= - S_028350_RB_MAP_PKR1(V_028350_RASTER_CONFIG_RB_MAP_3); - } else { - raster_config_se |= - S_028350_RB_MAP_PKR1(V_028350_RASTER_CONFIG_RB_MAP_0); - } - } - } - } - /* GRBM_GFX_INDEX has a different offset on SI and CI+ */ if (physical_device->rad_info.chip_class < CIK) radeon_set_config_reg(cs, R_00802C_GRBM_GFX_INDEX, @@ -142,7 +61,7 @@ si_write_harvested_raster_configs(struct radv_physical_device *physical_device, radeon_set_uconfig_reg(cs, R_030800_GRBM_GFX_INDEX, S_030800_SE_INDEX(se) | S_030800_SH_BROADCAST_WRITES(1) | S_030800_INSTANCE_BROADCAST_WRITES(1)); - radeon_set_context_reg(cs, R_028350_PA_SC_RASTER_CONFIG, raster_config_se); + radeon_set_context_reg(cs, R_028350_PA_SC_RASTER_CONFIG, raster_config_se[se]); } /* GRBM_GFX_INDEX has a different offset on SI and CI+ */ @@ -156,21 +75,8 @@ si_write_harvested_raster_configs(struct radv_physical_device *physical_device, S_030800_SE_BROADCAST_WRITES(1) | S_030800_SH_BROADCAST_WRITES(1) | S_030800_INSTANCE_BROADCAST_WRITES(1)); - if (physical_device->rad_info.chip_class >= CIK) { - if ((num_se > 2) && ((!se_mask[0] && !se_mask[1]) || - (!se_mask[2] && !se_mask[3]))) { - raster_config_1 &= C_028354_SE_PAIR_MAP; - - if (!se_mask[0] && !se_mask[1]) { - raster_config_1 |= - S_028354_SE_PAIR_MAP(V_028354_RASTER_CONFIG_SE_PAIR_MAP_3); - } else { - raster_config_1 |= - S_028354_SE_PAIR_MAP(V_028354_RASTER_CONFIG_SE_PAIR_MAP_0); - } - } + if (physical_device->rad_info.chip_class >= CIK) radeon_set_context_reg(cs, R_028354_PA_SC_RASTER_CONFIG_1, raster_config_1); - } } static void diff --git a/src/gallium/drivers/radeonsi/si_state.c b/src/gallium/drivers/radeonsi/si_state.c index 83f4f857d3c..a7c99427e17 100644 --- a/src/gallium/drivers/radeonsi/si_state.c +++ b/src/gallium/drivers/radeonsi/si_state.c @@ -4621,121 +4621,22 @@ si_write_harvested_raster_configs(struct si_context *sctx, unsigned raster_config, unsigned raster_config_1) { - unsigned sh_per_se = MAX2(sctx->screen->info.max_sh_per_se, 1); unsigned num_se = MAX2(sctx->screen->info.max_se, 1); - unsigned rb_mask = sctx->screen->info.enabled_rb_mask; - unsigned num_rb = MIN2(sctx->screen->info.num_render_backends, 16); - unsigned rb_per_pkr = MIN2(num_rb / num_se / sh_per_se, 2); - unsigned rb_per_se = num_rb / num_se; - unsigned se_mask[4]; + unsigned raster_config_se[4]; unsigned se; - se_mask[0] = ((1 << rb_per_se) - 1); - se_mask[1] = (se_mask[0] << rb_per_se); - se_mask[2] = (se_mask[1] << rb_per_se); - se_mask[3] = (se_mask[2] << rb_per_se); - - se_mask[0] &= rb_mask; - se_mask[1] &= rb_mask; - se_mask[2] &= rb_mask; - se_mask[3] &= rb_mask; - - assert(num_se == 1 || num_se == 2 || num_se == 4); - assert(sh_per_se == 1 || sh_per_se == 2); - assert(rb_per_pkr == 1 || rb_per_pkr == 2); - - /* XXX: I can't figure out what the *_XSEL and *_YSEL - * fields are for, so I'm leaving them as their default - * values. */ + ac_get_harvested_configs(&sctx->screen->info, + raster_config, + &raster_config_1, + raster_config_se); for (se = 0; se < num_se; se++) { - unsigned raster_config_se = raster_config; - unsigned pkr0_mask = ((1 << rb_per_pkr) - 1) << (se * rb_per_se); - unsigned pkr1_mask = pkr0_mask << rb_per_pkr; - int idx = (se / 2) * 2; - - if ((num_se > 1) && (!se_mask[idx] || !se_mask[idx + 1])) { - raster_config_se &= C_028350_SE_MAP; - - if (!se_mask[idx]) { - raster_config_se |= - S_028350_SE_MAP(V_028350_RASTER_CONFIG_SE_MAP_3); - } else { - raster_config_se |= - S_028350_SE_MAP(V_028350_RASTER_CONFIG_SE_MAP_0); - } - } - - pkr0_mask &= rb_mask; - pkr1_mask &= rb_mask; - if (rb_per_se > 2 && (!pkr0_mask || !pkr1_mask)) { - raster_config_se &= C_028350_PKR_MAP; - - if (!pkr0_mask) { - raster_config_se |= - S_028350_PKR_MAP(V_028350_RASTER_CONFIG_PKR_MAP_3); - } else { - raster_config_se |= - S_028350_PKR_MAP(V_028350_RASTER_CONFIG_PKR_MAP_0); - } - } - - if (rb_per_se >= 2) { - unsigned rb0_mask = 1 << (se * rb_per_se); - unsigned rb1_mask = rb0_mask << 1; - - rb0_mask &= rb_mask; - rb1_mask &= rb_mask; - if (!rb0_mask || !rb1_mask) { - raster_config_se &= C_028350_RB_MAP_PKR0; - - if (!rb0_mask) { - raster_config_se |= - S_028350_RB_MAP_PKR0(V_028350_RASTER_CONFIG_RB_MAP_3); - } else { - raster_config_se |= - S_028350_RB_MAP_PKR0(V_028350_RASTER_CONFIG_RB_MAP_0); - } - } - - if (rb_per_se > 2) { - rb0_mask = 1 << (se * rb_per_se + rb_per_pkr); - rb1_mask = rb0_mask << 1; - rb0_mask &= rb_mask; - rb1_mask &= rb_mask; - if (!rb0_mask || !rb1_mask) { - raster_config_se &= C_028350_RB_MAP_PKR1; - - if (!rb0_mask) { - raster_config_se |= - S_028350_RB_MAP_PKR1(V_028350_RASTER_CONFIG_RB_MAP_3); - } else { - raster_config_se |= - S_028350_RB_MAP_PKR1(V_028350_RASTER_CONFIG_RB_MAP_0); - } - } - } - } - si_set_grbm_gfx_index_se(sctx, pm4, se); - si_pm4_set_reg(pm4, R_028350_PA_SC_RASTER_CONFIG, raster_config_se); + si_pm4_set_reg(pm4, R_028350_PA_SC_RASTER_CONFIG, raster_config_se[se]); } si_set_grbm_gfx_index(sctx, pm4, ~0); if (sctx->chip_class >= CIK) { - if ((num_se > 2) && ((!se_mask[0] && !se_mask[1]) || - (!se_mask[2] && !se_mask[3]))) { - raster_config_1 &= C_028354_SE_PAIR_MAP; - - if (!se_mask[0] && !se_mask[1]) { - raster_config_1 |= - S_028354_SE_PAIR_MAP(V_028354_RASTER_CONFIG_SE_PAIR_MAP_3); - } else { - raster_config_1 |= - S_028354_SE_PAIR_MAP(V_028354_RASTER_CONFIG_SE_PAIR_MAP_0); - } - } - si_pm4_set_reg(pm4, R_028354_PA_SC_RASTER_CONFIG_1, raster_config_1); } }