summaryrefslogtreecommitdiffstats
path: root/src/mesa/drivers/dri/i965/brw_device_info.h
blob: 4e7f3135960c912683203247963d420c3e2af32c (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
 /*
  * Copyright © 2013 Intel Corporation
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
  * to deal in the Software without restriction, including without limitation
  * the rights to use, copy, modify, merge, publish, distribute, sublicense,
  * and/or sell copies of the Software, and to permit persons to whom the
  * Software is furnished to do so, subject to the following conditions:
  *
  * The above copyright notice and this permission notice (including the next
  * paragraph) shall be included in all copies or substantial portions of the
  * Software.
  *
  * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
  * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
  * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
  * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
  * IN THE SOFTWARE.
  *
  */

#pragma once
#include <stdbool.h>

/**
 * Intel hardware information and quirks
 */
struct brw_device_info
{
   int gen; /**< Generation number: 4, 5, 6, 7, ... */
   int gt;

   bool is_g4x;
   bool is_ivybridge;
   bool is_baytrail;
   bool is_haswell;
   bool is_cherryview;
   bool is_broxton;

   bool has_hiz_and_separate_stencil;
   bool must_use_separate_stencil;

   bool has_llc;

   bool has_pln;
   bool has_compr4;
   bool has_surface_tile_offset;
   bool supports_simd16_3src;
   bool has_resource_streamer;

   /**
    * \name Intel hardware quirks
    *  @{
    */
   bool has_negative_rhw_bug;

   /**
    * Some versions of Gen hardware don't do centroid interpolation correctly
    * on unlit pixels, causing incorrect values for derivatives near triangle
    * edges.  Enabling this flag causes the fragment shader to use
    * non-centroid interpolation for unlit pixels, at the expense of two extra
    * fragment shader instructions.
    */
   bool needs_unlit_centroid_workaround;
   /** @} */

   /**
    * \name GPU hardware limits
    *
    * In general, you can find shader thread maximums by looking at the "Maximum
    * Number of Threads" field in the Intel PRM description of the 3DSTATE_VS,
    * 3DSTATE_GS, 3DSTATE_HS, 3DSTATE_DS, and 3DSTATE_PS commands. URB entry
    * limits come from the "Number of URB Entries" field in the the
    * 3DSTATE_URB_VS command and friends.
    *
    * These fields are used to calculate the scratch space to allocate.  The
    * amount of scratch space can be larger without being harmful on modern
    * GPUs, however, prior to Haswell, programming the maximum number of threads
    * to greater than the hardware maximum would cause GPU performance to tank.
    *
    *  @{
    */
   /**
    * Total number of slices present on the device whether or not they've been
    * fused off.
    *
    * XXX: CS thread counts are limited by the inability to do cross subslice
    * communication. It is the effectively the number of logical threads which
    * can be executed in a subslice. Fuse configurations may cause this number
    * to change, so we program @max_cs_threads as the lower maximum.
    */
   unsigned num_slices;
   unsigned max_vs_threads;   /**< Maximum Vertex Shader threads */
   unsigned max_hs_threads;   /**< Maximum Hull Shader threads */
   unsigned max_ds_threads;   /**< Maximum Domain Shader threads */
   unsigned max_gs_threads;   /**< Maximum Geometry Shader threads. */
   /**
    * Theoretical maximum number of Pixel Shader threads.
    *
    * PSD means Pixel Shader Dispatcher. On modern Intel GPUs, hardware will
    * automatically scale pixel shader thread count, based on a single value
    * programmed into 3DSTATE_PS.
    *
    * To calculate the maximum number of threads for Gen8 beyond (which have
    * multiple Pixel Shader Dispatchers):
    *
    * - Look up 3DSTATE_PS and find "Maximum Number of Threads Per PSD"
    * - Usually there's only one PSD per subslice, so use the number of
    *   subslices for number of PSDs.
    * - For max_wm_threads, the total should be PSD threads * #PSDs.
    */
   unsigned max_wm_threads;

   /**
    * Maximum Compute Shader threads.
    *
    * Thread count * number of EUs per subslice
    */
   unsigned max_cs_threads;

   struct {
      /**
       * Hardware default URB size.
       *
       * The units this is expressed in are somewhat inconsistent: 512b units
       * on Gen4-5, KB on Gen6-7, and KB times the slice count on Gen8+.
       *
       * Look up "URB Size" in the "Device Attributes" page, and take the
       * maximum.  Look up the slice count for each GT SKU on the same page.
       * urb.size = URB Size (kbytes) / slice count
       */
      unsigned size;
      unsigned min_vs_entries;
      unsigned max_vs_entries;
      unsigned max_hs_entries;
      unsigned min_ds_entries;
      unsigned max_ds_entries;
      unsigned max_gs_entries;
   } urb;
   /** @} */
};

const struct brw_device_info *brw_get_device_info(int devid);
const char *brw_get_device_name(int devid);