src/panfrost/lib/pan_scratch.c

   1 /*
   2  * Copyright (C) 2019 Collabora, Ltd.
   3  *
   4  * Permission is hereby granted, free of charge, to any person obtaining a
   5  * copy of this software and associated documentation files (the "Software"),
   6  * to deal in the Software without restriction, including without limitation
   7  * the rights to use, copy, modify, merge, publish, distribute, sublicense,
   8  * and/or sell copies of the Software, and to permit persons to whom the
   9  * Software is furnished to do so, subject to the following conditions:
  10  *
  11  * The above copyright notice and this permission notice (including the next
  12  * paragraph) shall be included in all copies or substantial portions of the
  13  * Software.
  14  *
  15  * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  16  * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  17  * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
  18  * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
  19  * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
  20  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  21  * SOFTWARE.
  22  *
  23  * Authors:
  24  *   Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
  25  */
  26
  27 #include "util/u_math.h"
  28 #include "pan_encoder.h"
  29
  30 /* Midgard has a small register file, so shaders with high register pressure
  31  * need to spill from the register file onto the stack. In addition to
  32  * spilling, it is desireable to allocate temporary arrays on the stack (for
  33  * instance because the register file does not support indirect access but the
  34  * stack does).
  35  *
  36  * The stack is located in "Thread Local Storage", sometimes abbreviated TLS in
  37  * the kernel source code. Thread local storage is allocated per-thread,
  38  * per-core, so threads executing concurrently do not interfere with each
  39  * other's stacks. On modern kernels, we may query
  40  * DRM_PANFROST_PARAM_THREAD_TLS_ALLOC for the number of threads per core we
  41  * must allocate for, and DRM_PANFROST_PARAM_SHADER_PRESENT for a bitmask of
  42  * shader cores (so take a popcount of that mask for the number of shader
  43  * cores). On older kernels that do not support querying these values,
  44  * following kbase, we may use the worst-case value of 256 threads for
  45  * THREAD_TLS_ALLOC, and the worst-case value of 16 cores for Midgard per the
  46  * "shader core count" column of the implementations table in
  47  * https://en.wikipedia.org/wiki/Mali_%28GPU% [citation needed]
  48  *
  49  * Within a particular thread, there is stack allocated. If it is present, its
  50  * size is a power-of-two, and it is at least 16 bytes. Stack is allocated
  51  * with the shared memory descriptor used for all shaders within a frame (note
  52  * that they don't execute concurrently so it's fine). So, consider the maximum
  53  * stack size used by any shader within a job, and then compute (where npot
  54  * denotes the next power of two):
  55  *
  56  *      bytes/thread = npot(max(size, 16))
  57  *      allocated = (# of bytes/thread) * (# of threads/core) * (# of cores)
  58  *
  59  * The size of Thread Local Storage is signaled to the GPU in a dedicated
  60  * log_stack_size field. Since stack sizes are powers of two, it follows that
  61  * stack_size is logarithmic. Consider some sample values:
  62  *
  63  *      stack size | log_stack_size
  64  *      ---------------------------
  65  *             256 | 4
  66  *             512 | 5
  67  *            1024 | 6
  68  *
  69  *  Noting that log2(256) = 8, we have the relation:
  70  *
  71  *      stack_size <= 2^(log_stack_size + 4)
  72  *
  73  *  Given the constraints about powers-of-two and the minimum of 256, we thus
  74  *  derive a formula for log_stack_size in terms of stack size (s), where s is
  75  *  positive:
  76  *
  77  *      log_stack_size = ceil(log2(max(s, 16))) - 4
  78  *
  79  * There are other valid characterisations of this formula, of course, but this
  80  * is computationally simple, so good enough for our purposes. If s=0, since
  81  * there is no spilling used whatsoever, we may set log_stack_size to 0 to
  82  * disable the stack.
  83  */
  84
  85 /* Computes log_stack_size = ceil(log2(max(s, 16))) - 4 */
  86
  87 unsigned
  88 panfrost_get_stack_shift(unsigned stack_size)
  89 {
  90         if (stack_size)
  91                 return util_logbase2_ceil(MAX2(stack_size, 16)) - 4;
  92         else
  93                 return 0;
  94 }
  95
  96 /* Computes the aligned stack size given the shift and thread count. The blob
  97  * reserves an extra page, and since this is hardware-internal, we do too. */
  98
  99 unsigned
 100 panfrost_get_total_stack_size(
 101                 unsigned stack_shift,
 102                 unsigned threads_per_core,
 103                 unsigned core_count)
 104 {
 105         unsigned size_per_thread = MAX2(1 << (stack_shift + 4), 32);
 106         unsigned size = size_per_thread * threads_per_core * core_count;
 107
 108         return size + 4096;
 109 }