.max_ds_threads = 80,
.max_gs_threads = 80,
.max_wm_threads = 128,
- .max_cs_threads = 28,
+ .max_cs_threads = 6 * 7,
.urb = {
.size = 192,
.min_vs_entries = 34,
.gt = 1,
.has_llc = false,
- /* XXX: These are preliminary thread counts and URB sizes. */
.num_slices = 1,
- .max_vs_threads = 56,
- .max_hs_threads = 56,
+ .max_vs_threads = 112,
+ .max_hs_threads = 112,
+ .max_ds_threads = 112,
+ .max_gs_threads = 112,
+ .max_wm_threads = 64 * 3,
+ .max_cs_threads = 6 * 6,
+ .urb = {
+ .size = 192,
+ .min_vs_entries = 34,
+ .max_vs_entries = 704,
+ .max_hs_entries = 256,
+ .max_ds_entries = 416,
+ .max_gs_entries = 256,
+ }
+};
+
+static const struct brw_device_info brw_device_info_bxt_2x6 = {
+ GEN9_FEATURES,
+ .is_broxton = 1,
+ .gt = 1,
+ .has_llc = false,
+
+ .num_slices = 1,
+ .max_vs_threads = 56, /* XXX: guess */
+ .max_hs_threads = 56, /* XXX: guess */
.max_ds_threads = 56,
.max_gs_threads = 56,
- .max_wm_threads = 32,
- .max_cs_threads = 28,
+ .max_wm_threads = 64 * 2,
+ .max_cs_threads = 6 * 6,
.urb = {
- .size = 64,
+ .size = 128,
.min_vs_entries = 34,
- .max_vs_entries = 640,
- .max_hs_entries = 80,
- .max_ds_entries = 80,
- .max_gs_entries = 256,
+ .max_vs_entries = 352,
+ .max_hs_entries = 128,
+ .max_ds_entries = 208,
+ .max_gs_entries = 128,
}
};
+/*
+ * Note: for all KBL SKUs, the PRM says SKL for GS entries, not SKL+.
+ * There's no KBL entry. Using the default SKL (GEN9) GS entries value.
+ */
+
+/*
+ * Both SKL and KBL support a maximum of 64 threads per
+ * Pixel Shader Dispatch (PSD) unit.
+ */
+#define KBL_MAX_THREADS_PER_PSD 64
+
+static const struct brw_device_info brw_device_info_kbl_gt1 = {
+ GEN9_FEATURES,
+ .gt = 1,
+
+ .max_cs_threads = 7 * 6,
+ .max_wm_threads = KBL_MAX_THREADS_PER_PSD * 2,
+ .urb.size = 192,
+ .num_slices = 1,
+};
+
+static const struct brw_device_info brw_device_info_kbl_gt1_5 = {
+ GEN9_FEATURES,
+ .gt = 1,
+
+ .max_cs_threads = 7 * 6,
+ .max_wm_threads = KBL_MAX_THREADS_PER_PSD * 3,
+ .num_slices = 1,
+};
+
+static const struct brw_device_info brw_device_info_kbl_gt2 = {
+ GEN9_FEATURES,
+ .gt = 2,
+
+ .max_wm_threads = KBL_MAX_THREADS_PER_PSD * 3,
+ .num_slices = 1,
+};
+
+static const struct brw_device_info brw_device_info_kbl_gt3 = {
+ GEN9_FEATURES,
+ .gt = 3,
+
+ .max_wm_threads = KBL_MAX_THREADS_PER_PSD * 6,
+ .num_slices = 2,
+};
+
+static const struct brw_device_info brw_device_info_kbl_gt4 = {
+ GEN9_FEATURES,
+ .gt = 4,
+
+ .max_wm_threads = KBL_MAX_THREADS_PER_PSD * 9,
+ /*
+ * From the "L3 Allocation and Programming" documentation:
+ *
+ * "URB is limited to 1008KB due to programming restrictions. This
+ * is not a restriction of the L3 implementation, but of the FF and
+ * other clients. Therefore, in a GT4 implementation it is
+ * possible for the programmed allocation of the L3 data array to
+ * provide 3*384KB=1152KB for URB, but only 1008KB of this
+ * will be used."
+ */
+ .urb.size = 1008 / 3,
+ .num_slices = 3,
+};
const struct brw_device_info *
brw_get_device_info(int devid)