On 10.09.2014 22:59, Tom Stellard wrote:
+ /* Always use the default config when all backends are enabled.
*/
+ if (rb_mask && util_bitcount(rb_mask) < max_backends) {
+ /* XXX: I can't figure out what the *_XSEL and *_YSEL
+ * fields are for, so I'm leaving them as their default
+ * values. */
+ unsigned pkr_mask = (sh_per_se | 0x1);
+ unsigned se0_pkr0 = rb_mask & pkr_mask;
+ unsigned se0_pkr1 = (rb_mask >>= sh_per_se) & pkr_mask;
+ unsigned se1_pkr0 = (rb_mask >>= sh_per_se) & pkr_mask;
+ unsigned se1_pkr1 = (rb_mask >>= sh_per_se) & pkr_mask;
+ unsigned se_map = 0;
+ unsigned se0_pkr_map = 0;
+ unsigned se1_pkr_map = 0;
+ unsigned se0_pkr0_rb_map = 0;
+ unsigned se0_pkr1_rb_map = 0;
+ unsigned se1_pkr0_rb_map = 0;
+ unsigned se1_pkr1_rb_map = 0;
+ if (!se0_pkr0 && !se0_pkr1) {
+ /* se0 disabled */
+ se_map |= 0x1;
+ }
+ if (se1_pkr0 || se1_pkr1) {
+ /* se1 enabled */
+ se_map |= 0x2;
+ }
+ if (!se0_pkr0) {
+ /* se0 pkr0 disabled */
+ se0_pkr_map |= 0x1;
+ }
+ if (se0_pkr1) {
+ /* se0 pkr1 enabled */
+ se0_pkr_map |= 0x2;
+ }
+ if (!se1_pkr0) {
+ /* se1 pkr0 disabled */
+ se1_pkr_map |= 0x1;
+ }
+ if (se1_pkr1) {
+ /* se1 pkr1 enabled */
+ se1_pkr_map |= 0x2;
+ }
+
+ se0_pkr0_rb_map = pkr_mask_to_map(se0_pkr0);
+ se0_pkr1_rb_map = pkr_mask_to_map(se0_pkr1);
+ se1_pkr0_rb_map = pkr_mask_to_map(se1_pkr0);
+ se1_pkr1_rb_map = pkr_mask_to_map(se1_pkr1);
+
+ assert(!se0_pkr0 || !se1_pkr0 || (se0_pkr0_rb_map ==
se1_pkr0_rb_map));
+ assert(!se0_pkr1 || !se1_pkr1 || (se0_pkr1_rb_map ==
se1_pkr1_rb_map));
+ raster_config &= C_028350_RB_MAP_PKR0;
+ raster_config |= S_028350_RB_MAP_PKR0(se0_pkr0_rb_map);
+ raster_config &= C_028350_RB_MAP_PKR1;
+ raster_config |= S_028350_RB_MAP_PKR1(se0_pkr1_rb_map);
+ raster_config &= C_028350_PKR_MAP;
+ raster_config |= S_028350_PKR_MAP(se0_pkr_map);
+ raster_config &= C_028350_SE_MAP;
+ raster_config |= S_028350_SE_MAP(se_map);
+ }
Taking a closer look again at the kernel code and register spec, I'm
afraid this logic is too static. I came up with the attached incremental
patch. It tries to only modify raster_config as necessary, i.e. only if
there are two SEs / packers per SE / RBs per packer but one of them is
disabled. The result may be different between SEs.
--
Earthling Michel Dänzer | http://www.amd.com
Libre software enthusiast | Mesa and X developer
commit 7103b9ccbc5b7ab9acc6eda2046b3db58bb6645d
Author: Michel Dänzer <[email protected]>
Date: Thu Sep 11 17:12:54 2014 +0900
radeonsi: Improve RASTER_CONFIG calculation for harvested cards
diff --git a/src/gallium/drivers/radeonsi/si_state.c b/src/gallium/drivers/radeonsi/si_state.c
index 21b9c34..91ada67 100644
--- a/src/gallium/drivers/radeonsi/si_state.c
+++ b/src/gallium/drivers/radeonsi/si_state.c
@@ -2989,15 +2989,114 @@ void si_init_state_functions(struct si_context *sctx)
sctx->b.b.draw_vbo = si_draw_vbo;
}
-static unsigned pkr_mask_to_map(unsigned mask)
-{
- switch(mask & 0x3) {
- case 0x0:
- case 0x1: return 0x0;
- case 0x2: return 0x3;
- case 0x3: return 0x2;
+static void
+si_write_harvested_raster_configs(struct si_context *sctx,
+ struct si_pm4_state *pm4,
+ unsigned raster_config)
+{
+ unsigned sh_per_se = MAX2(sctx->screen->b.info.max_sh_per_se, 1);
+ unsigned num_se = MAX2(sctx->screen->b.info.max_se, 1);
+ unsigned rb_mask = sctx->screen->b.info.si_backend_enabled_mask;
+ unsigned num_rb = sctx->screen->b.info.r600_num_backends;
+ unsigned rb_per_pkr = num_rb / num_se / sh_per_se;
+ unsigned rb_per_se = num_rb / num_se;
+ unsigned se0_mask = (1 << rb_per_se) - 1;
+ unsigned se1_mask = se0_mask << rb_per_se;
+ unsigned se;
+
+ assert(num_se == 1 || num_se == 2);
+ assert(sh_per_se == 1 || sh_per_se == 2);
+ assert(rb_per_pkr == 1 || rb_per_pkr == 2);
+
+ fprintf(stderr, "Original raster_config = 0x%x, rb_mask = 0x%x\n",
+ raster_config, rb_mask);
+
+ /* XXX: I can't figure out what the *_XSEL and *_YSEL
+ * fields are for, so I'm leaving them as their default
+ * values. */
+
+ se0_mask &= rb_mask;
+ se1_mask &= rb_mask;
+ if (num_se == 2 && (!se0_mask || !se1_mask)) {
+ raster_config &= C_028350_SE_MAP;
+
+ if (!se0_mask) {
+ raster_config |=
+ S_028350_SE_MAP(V_028350_RASTER_CONFIG_SE_MAP_3);
+ } else {
+ raster_config |=
+ S_028350_SE_MAP(V_028350_RASTER_CONFIG_SE_MAP_0);
+ }
}
- return 0;
+
+ 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;
+
+ pkr0_mask &= rb_mask;
+ pkr1_mask &= rb_mask;
+ if (sh_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_pkr == 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 (sh_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);
+ }
+ }
+ }
+ }
+
+ fprintf(stderr, "SE%d: raster_config = 0x%x\n",
+ se, raster_config_se);
+
+ si_pm4_set_reg(pm4, GRBM_GFX_INDEX,
+ SE_INDEX(se) | SH_BROADCAST_WRITES |
+ INSTANCE_BROADCAST_WRITES);
+ si_pm4_set_reg(pm4, R_028350_PA_SC_RASTER_CONFIG, raster_config_se);
+ }
+
+ si_pm4_set_reg(pm4, GRBM_GFX_INDEX,
+ SE_BROADCAST_WRITES | SH_BROADCAST_WRITES |
+ INSTANCE_BROADCAST_WRITES);
}
void si_init_config(struct si_context *sctx)
@@ -3071,11 +3170,10 @@ void si_init_config(struct si_context *sctx)
break;
}
} else {
- unsigned raster_config = 0;
- unsigned sh_per_se = MAX2(sctx->screen->b.info.max_sh_per_se, 1);
- unsigned num_se = MAX2(sctx->screen->b.info.max_se, 1);
unsigned rb_mask = sctx->screen->b.info.si_backend_enabled_mask;
- unsigned max_backends = 2 * sh_per_se * num_se;
+ unsigned num_rb = sctx->screen->b.info.r600_num_backends;
+ unsigned raster_config;
+
switch (sctx->screen->b.family) {
case CHIP_TAHITI:
case CHIP_PITCAIRN:
@@ -3091,69 +3189,19 @@ void si_init_config(struct si_context *sctx)
raster_config = 0x00000000;
break;
default:
+ fprintf(stderr,
+ "radeonsi: Unknown GPU, using 0 for raster_config\n");
raster_config = 0x00000000;
break;
}
/* Always use the default config when all backends are enabled. */
- if (rb_mask && util_bitcount(rb_mask) < max_backends) {
- /* XXX: I can't figure out what the *_XSEL and *_YSEL
- * fields are for, so I'm leaving them as their default
- * values. */
- unsigned pkr_mask = (sh_per_se | 0x1);
- unsigned se0_pkr0 = rb_mask & pkr_mask;
- unsigned se0_pkr1 = (rb_mask >>= sh_per_se) & pkr_mask;
- unsigned se1_pkr0 = (rb_mask >>= sh_per_se) & pkr_mask;
- unsigned se1_pkr1 = (rb_mask >>= sh_per_se) & pkr_mask;
- unsigned se_map = 0;
- unsigned se0_pkr_map = 0;
- unsigned se1_pkr_map = 0;
- unsigned se0_pkr0_rb_map = 0;
- unsigned se0_pkr1_rb_map = 0;
- unsigned se1_pkr0_rb_map = 0;
- unsigned se1_pkr1_rb_map = 0;
- if (!se0_pkr0 && !se0_pkr1) {
- /* se0 disabled */
- se_map |= 0x1;
- }
- if (se1_pkr0 || se1_pkr1) {
- /* se1 enabled */
- se_map |= 0x2;
- }
- if (!se0_pkr0) {
- /* se0 pkr0 disabled */
- se0_pkr_map |= 0x1;
- }
- if (se0_pkr1) {
- /* se0 pkr1 enabled */
- se0_pkr_map |= 0x2;
- }
- if (!se1_pkr0) {
- /* se1 pkr0 disabled */
- se1_pkr_map |= 0x1;
- }
- if (se1_pkr1) {
- /* se1 pkr1 enabled */
- se1_pkr_map |= 0x2;
- }
-
- se0_pkr0_rb_map = pkr_mask_to_map(se0_pkr0);
- se0_pkr1_rb_map = pkr_mask_to_map(se0_pkr1);
- se1_pkr0_rb_map = pkr_mask_to_map(se1_pkr0);
- se1_pkr1_rb_map = pkr_mask_to_map(se1_pkr1);
-
- assert(!se0_pkr0 || !se1_pkr0 || (se0_pkr0_rb_map == se1_pkr0_rb_map));
- assert(!se0_pkr1 || !se1_pkr1 || (se0_pkr1_rb_map == se1_pkr1_rb_map));
- raster_config &= C_028350_RB_MAP_PKR0;
- raster_config |= S_028350_RB_MAP_PKR0(se0_pkr0_rb_map);
- raster_config &= C_028350_RB_MAP_PKR1;
- raster_config |= S_028350_RB_MAP_PKR1(se0_pkr1_rb_map);
- raster_config &= C_028350_PKR_MAP;
- raster_config |= S_028350_PKR_MAP(se0_pkr_map);
- raster_config &= C_028350_SE_MAP;
- raster_config |= S_028350_SE_MAP(se_map);
+ if (rb_mask && util_bitcount(rb_mask) >= num_rb) {
+ si_pm4_set_reg(pm4, R_028350_PA_SC_RASTER_CONFIG,
+ raster_config);
+ } else {
+ si_write_harvested_raster_configs(sctx, pm4, raster_config);
}
- si_pm4_set_reg(pm4, R_028350_PA_SC_RASTER_CONFIG, raster_config);
}
si_pm4_set_reg(pm4, R_028204_PA_SC_WINDOW_SCISSOR_TL, S_028204_WINDOW_OFFSET_DISABLE(1));
_______________________________________________
mesa-dev mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/mesa-dev
