src/graphics/lib/compute/hotsort/platforms/vk/tests/hotsort_vk_bench/BUILD.gn

# Copyright 2019 The Fuchsia Authors. All rights reserved.
# Use of this source code is governed by a BSD-style license that can be
# found in the LICENSE file.

import("../../../../../gn/build_rules.gni")
import("../../targets/hotsort_target.gni")

#
# hotsort_vk_bench: benchmark HotSort
#

graphics_compute_vulkan_executable("hotsort_vk_bench") {
  sources = [
    "main.c",
    "sort.cpp",
  ]
  deps = [
    ":hs_amd_gcn3_u32",
    ":hs_amd_gcn3_u64",
    ":hs_intel_gen8_u32",
    ":hs_intel_gen8_u64",
    ":hs_nvidia_sm35_u32",
    ":hs_nvidia_sm35_u64",
    "${graphics_compute_dir}/common",
    "${graphics_compute_dir}/common/vk",
    "${graphics_compute_dir}/hotsort/platforms/vk",
  ]
}

#
# configuration
#
# $HS_GEN -v -a "glsl" -D HS_AMD_GCN3 -t 1 -w 64 -r 16 -s 32768 -S 32768 -b 16 -m 1 -M 1 -f 1 -F 1 -c 1 -C 1 -z
#

hotsort_target("hs_amd_gcn3_u32") {
  vendor = "amd"
  type_dwords = 1
  warp_lanes = 64
  thread_regs = 16
  smem_bs = 32768
  smem_bc = 32768
  warps_per_group = 16
  warps_min = 1
  warps_mod = 1
  merge_flip_lo = 1
  merge_flip_hi = 1
  merge_half_lo = 1
  merge_half_hi = 1
  glsl_bindings = "0,1,0,0"
  autotune = true
}

#
# configuration
#
# $HS_GEN -v -a "glsl" -D HS_AMD_GCN3 -t 2 -w 64 -r 8 -s 32768 -S 32768 -b 16 -m 1 -M 1 -f 1 -F 1 -c 1 -C 1 -z
#

hotsort_target("hs_amd_gcn3_u64") {
  vendor = "amd"
  type_dwords = 2
  warp_lanes = 64
  thread_regs = 8
  smem_bs = 32768
  smem_bc = 32768
  warps_per_group = 16
  warps_min = 1
  warps_mod = 1
  merge_flip_lo = 1
  merge_flip_hi = 1
  merge_half_lo = 1
  merge_half_hi = 1
  glsl_bindings = "0,1,0,0"
  autotune = true
}

#
# configuration
#
# $HS_GEN -v -a "glsl" -D HS_INTEL_GEN8 -t 1 -w 16 -r 8 -s 21504 -S 65536 -b 16 -B 48 -m 1 -M 1 -f 0 -F 0 -c 0 -C 0 -z
#

hotsort_target("hs_intel_gen8_u32") {
  vendor = "intel"
  type_dwords = 1
  warp_lanes = 8
  thread_regs = 8
  smem_bs = 21504
  smem_bc = 65536
  warps_per_group = 16
  warps_max = 48
  warps_min = 1
  warps_mod = 1
  merge_flip_lo = 0
  merge_flip_hi = 0
  merge_half_lo = 0
  merge_half_hi = 0
  glsl_bindings = "0,1,0,0"
  autotune = true
}

#
# configuration
#
# $HS_GEN -v -a "glsl" -D HS_INTEL_GEN8 -t 2 -w 8 -r 16 -s 21504 -S 65536 -b 16 -B 48 -m 1 -M 1 -f 1 -F 1 -c 1 -C 1 -z
#

hotsort_target("hs_intel_gen8_u64") {
  vendor = "intel"
  type_dwords = 2
  warp_lanes = 8
  thread_regs = 16
  smem_bs = 21504
  smem_bc = 65536
  warps_per_group = 16
  warps_max = 48
  warps_min = 1
  warps_mod = 1
  merge_flip_lo = 1
  merge_flip_hi = 1
  merge_half_lo = 1
  merge_half_hi = 1
  glsl_bindings = "0,1,0,0"
  autotune = true
}

#
# configuration
#
# OLD: $HS_GEN -v -a "glsl" -D HS_NVIDIA_SM35 -t 1 -w 32 -r 32 -s 49152 -S 65536 -b 32 -m 1 -M 1 -f 1 -F 1 -c 1 -C 1 -z
# NEW: $HS_GEN -v -a "glsl" -D HS_NVIDIA_SM35 -t 1 -w 32 -r 16 -s 32768 -S 32768 -b 16 -m 1 -M 1 -p 1 -P 1 -f 0 -F 0 -c 0 -C 0 -z
#

hotsort_target("hs_nvidia_sm35_u32") {
  vendor = "nvidia"
  type_dwords = 1
  warp_lanes = 32
  thread_regs = 16
  smem_bs = 32768
  smem_bc = 32768
  warps_per_group = 16
  warps_min = 1
  warps_mod = 1
  merge_flip_warps = 1
  merge_half_warps = 1
  merge_flip_lo = 0
  merge_flip_hi = 0
  merge_half_lo = 0
  merge_half_hi = 0
  glsl_bindings = "0,1,0,0"
  autotune = true
}

#
# configuration
#
# OLD: $HS_GEN -v -a "glsl" -D HS_NVIDIA_SM35 -t 2 -w 32 -r 32 -s 49152 -S 65536 -b 16 -m 1 -M 1 -f 1 -F 1 -c 1 -C 1 -z
# NEW: $HS_GEN -v -a "glsl" -D HS_NVIDIA_SM35 -t 2 -w 32 -r 8 -s 32768 -S 32768 -b 16 -m 1 -M 1 -p 1 -P 1 -f 0 -F 0 -c 0 -C 0 -z
#

hotsort_target("hs_nvidia_sm35_u64") {
  vendor = "nvidia"
  type_dwords = 2
  warp_lanes = 32
  thread_regs = 8
  smem_bs = 32768
  smem_bc = 32768
  warps_per_group = 16
  warps_min = 1
  warps_mod = 1
  merge_flip_warps = 1
  merge_half_warps = 1
  merge_flip_lo = 0
  merge_flip_hi = 0
  merge_half_lo = 0
  merge_half_hi = 0
  glsl_bindings = "0,1,0,0"
  autotune = true
}