[Mesa-dev] [PATCH V2 1/2] i965: Add and initialize l3_banks field for gen7+
Anuj Phogat
anuj.phogat at gmail.com
Thu Jun 1 23:51:17 UTC 2017
This new field helps simplify l3 way size computations
in next patch.
V2: Initialize the l3_banks to 0 in macros.
Suggested-by: Francisco Jerez <currojerez at riseup.net>
Signed-off-by: Anuj Phogat <anuj.phogat at gmail.com>
Cc: Francisco Jerez <currojerez at riseup.net>
---
src/intel/common/gen_device_info.c | 33 ++++++++++++++++++++++++++++++---
src/intel/common/gen_device_info.h | 1 +
2 files changed, 31 insertions(+), 3 deletions(-)
diff --git a/src/intel/common/gen_device_info.c b/src/intel/common/gen_device_info.c
index 209b293..250ea17 100644
--- a/src/intel/common/gen_device_info.c
+++ b/src/intel/common/gen_device_info.c
@@ -125,6 +125,7 @@ static const struct gen_device_info gen_device_info_snb_gt2 = {
.has_hiz_and_separate_stencil = true, \
.must_use_separate_stencil = true, \
.has_llc = true, \
+ .l3_banks = 0, \
.has_pln = true, \
.has_surface_tile_offset = true, \
.timebase_scale = 80
@@ -132,6 +133,7 @@ static const struct gen_device_info gen_device_info_snb_gt2 = {
static const struct gen_device_info gen_device_info_ivb_gt1 = {
GEN7_FEATURES, .is_ivybridge = true, .gt = 1,
.num_slices = 1,
+ .l3_banks = 2,
.max_vs_threads = 36,
.max_tcs_threads = 36,
.max_tes_threads = 36,
@@ -156,6 +158,7 @@ static const struct gen_device_info gen_device_info_ivb_gt1 = {
static const struct gen_device_info gen_device_info_ivb_gt2 = {
GEN7_FEATURES, .is_ivybridge = true, .gt = 2,
.num_slices = 1,
+ .l3_banks = 4,
.max_vs_threads = 128,
.max_tcs_threads = 128,
.max_tes_threads = 128,
@@ -180,6 +183,7 @@ static const struct gen_device_info gen_device_info_ivb_gt2 = {
static const struct gen_device_info gen_device_info_byt = {
GEN7_FEATURES, .is_baytrail = true, .gt = 1,
.num_slices = 1,
+ .l3_banks = 1,
.has_llc = false,
.max_vs_threads = 36,
.max_tcs_threads = 36,
@@ -211,6 +215,7 @@ static const struct gen_device_info gen_device_info_byt = {
static const struct gen_device_info gen_device_info_hsw_gt1 = {
HSW_FEATURES, .gt = 1,
.num_slices = 1,
+ .l3_banks = 2,
.max_vs_threads = 70,
.max_tcs_threads = 70,
.max_tes_threads = 70,
@@ -235,6 +240,7 @@ static const struct gen_device_info gen_device_info_hsw_gt1 = {
static const struct gen_device_info gen_device_info_hsw_gt2 = {
HSW_FEATURES, .gt = 2,
.num_slices = 1,
+ .l3_banks = 4,
.max_vs_threads = 280,
.max_tcs_threads = 256,
.max_tes_threads = 280,
@@ -259,6 +265,7 @@ static const struct gen_device_info gen_device_info_hsw_gt2 = {
static const struct gen_device_info gen_device_info_hsw_gt3 = {
HSW_FEATURES, .gt = 3,
.num_slices = 2,
+ .l3_banks = 8,
.max_vs_threads = 280,
.max_tcs_threads = 256,
.max_tes_threads = 280,
@@ -286,6 +293,7 @@ static const struct gen_device_info gen_device_info_hsw_gt3 = {
.has_resource_streamer = true, \
.must_use_separate_stencil = true, \
.has_llc = true, \
+ .l3_banks = 0, \
.has_pln = true, \
.supports_simd16_3src = true, \
.has_surface_tile_offset = true, \
@@ -299,6 +307,7 @@ static const struct gen_device_info gen_device_info_hsw_gt3 = {
static const struct gen_device_info gen_device_info_bdw_gt1 = {
GEN8_FEATURES, .gt = 1,
.num_slices = 1,
+ .l3_banks = 2,
.max_cs_threads = 42,
.urb = {
.size = 192,
@@ -318,6 +327,7 @@ static const struct gen_device_info gen_device_info_bdw_gt1 = {
static const struct gen_device_info gen_device_info_bdw_gt2 = {
GEN8_FEATURES, .gt = 2,
.num_slices = 1,
+ .l3_banks = 4,
.max_cs_threads = 56,
.urb = {
.size = 384,
@@ -337,6 +347,7 @@ static const struct gen_device_info gen_device_info_bdw_gt2 = {
static const struct gen_device_info gen_device_info_bdw_gt3 = {
GEN8_FEATURES, .gt = 3,
.num_slices = 2,
+ .l3_banks = 8,
.max_cs_threads = 56,
.urb = {
.size = 384,
@@ -357,6 +368,7 @@ static const struct gen_device_info gen_device_info_chv = {
GEN8_FEATURES, .is_cherryview = 1, .gt = 1,
.has_llc = false,
.num_slices = 1,
+ .l3_banks = 2,
.max_vs_threads = 80,
.max_tcs_threads = 80,
.max_tes_threads = 80,
@@ -384,6 +396,7 @@ static const struct gen_device_info gen_device_info_chv = {
.has_resource_streamer = true, \
.must_use_separate_stencil = true, \
.has_llc = true, \
+ .l3_banks = 0, \
.has_pln = true, \
.supports_simd16_3src = true, \
.has_surface_tile_offset = true, \
@@ -413,6 +426,7 @@ static const struct gen_device_info gen_device_info_chv = {
.gt = 1, \
.has_llc = false, \
.num_slices = 1, \
+ .l3_banks = 0, \
.max_vs_threads = 112, \
.max_tcs_threads = 112, \
.max_tes_threads = 112, \
@@ -457,22 +471,26 @@ static const struct gen_device_info gen_device_info_chv = {
static const struct gen_device_info gen_device_info_skl_gt1 = {
GEN9_FEATURES, .gt = 1,
.num_slices = 1,
+ .l3_banks = 2,
.urb.size = 192,
};
static const struct gen_device_info gen_device_info_skl_gt2 = {
GEN9_FEATURES, .gt = 2,
.num_slices = 1,
+ .l3_banks = 4,
};
static const struct gen_device_info gen_device_info_skl_gt3 = {
GEN9_FEATURES, .gt = 3,
.num_slices = 2,
+ .l3_banks = 8,
};
static const struct gen_device_info gen_device_info_skl_gt4 = {
GEN9_FEATURES, .gt = 4,
.num_slices = 3,
+ .l3_banks = 12,
/* From the "L3 Allocation and Programming" documentation:
*
* "URB is limited to 1008KB due to programming restrictions. This is not a
@@ -485,11 +503,13 @@ static const struct gen_device_info gen_device_info_skl_gt4 = {
};
static const struct gen_device_info gen_device_info_bxt = {
- GEN9_LP_FEATURES
+ GEN9_LP_FEATURES,
+ .l3_banks = 2,
};
static const struct gen_device_info gen_device_info_bxt_2x6 = {
- GEN9_LP_FEATURES_2X6
+ GEN9_LP_FEATURES_2X6,
+ .l3_banks = 1,
};
/*
* Note: for all KBL SKUs, the PRM says SKL for GS entries, not SKL+.
@@ -504,6 +524,7 @@ static const struct gen_device_info gen_device_info_kbl_gt1 = {
.max_cs_threads = 7 * 6,
.urb.size = 192,
.num_slices = 1,
+ .l3_banks = 2,
};
static const struct gen_device_info gen_device_info_kbl_gt1_5 = {
@@ -513,6 +534,7 @@ static const struct gen_device_info gen_device_info_kbl_gt1_5 = {
.max_cs_threads = 7 * 6,
.num_slices = 1,
+ .l3_banks = 4,
};
static const struct gen_device_info gen_device_info_kbl_gt2 = {
@@ -521,6 +543,7 @@ static const struct gen_device_info gen_device_info_kbl_gt2 = {
.gt = 2,
.num_slices = 1,
+ .l3_banks = 4,
};
static const struct gen_device_info gen_device_info_kbl_gt3 = {
@@ -529,6 +552,7 @@ static const struct gen_device_info gen_device_info_kbl_gt3 = {
.gt = 3,
.num_slices = 2,
+ .l3_banks = 8,
};
static const struct gen_device_info gen_device_info_kbl_gt4 = {
@@ -548,12 +572,15 @@ static const struct gen_device_info gen_device_info_kbl_gt4 = {
*/
.urb.size = 1008 / 3,
.num_slices = 3,
+ .l3_banks = 12,
};
static const struct gen_device_info gen_device_info_glk = {
- GEN9_LP_FEATURES
+ GEN9_LP_FEATURES,
+ .l3_banks = 2,
};
+/*TODO: Initialize l3_banks when we know the number. */
static const struct gen_device_info gen_device_info_glk_2x6 = {
GEN9_LP_FEATURES_2X6
};
diff --git a/src/intel/common/gen_device_info.h b/src/intel/common/gen_device_info.h
index 80676d0..6207630 100644
--- a/src/intel/common/gen_device_info.h
+++ b/src/intel/common/gen_device_info.h
@@ -96,6 +96,7 @@ struct gen_device_info
* to change, so we program @max_cs_threads as the lower maximum.
*/
unsigned num_slices;
+ unsigned l3_banks;
unsigned max_vs_threads; /**< Maximum Vertex Shader threads */
unsigned max_tcs_threads; /**< Maximum Hull Shader threads */
unsigned max_tes_threads; /**< Maximum Domain Shader threads */
--
2.9.3
More information about the mesa-dev
mailing list