woutermans
87365077e0
- Tag redirected surfaces as R10G10B10A2 ('R3') as well as RGBA16F ('R2'), and
let the native output kernel store the game's R10G10B10A2 texels itself.
- Import linear, exportable game textures (vkd3d-proton patch 0003) into HIP
so the output kernel writes the game's output texture with no game-side copy.
- Add ID3D12DXVKInteropDeviceD4R3 with GetVulkanLinearImageInfo.
- Gate both paths behind D4R_SHIM_OUTPUT_PACKED and D4R_SHIM_INPLACE, and use
them only for split frames of preset M whose output kernel honours the redirect.
- Convert on the host when a recorded packed frame finds the wrong kernel.
- Give the harness an R10G10B10A2 output, and add D4R_SHIM_SPIN_POLL so
frame timing is not quantised to the poll sleep.
- Document the measured removal of the output copies in performance.md.
27 lines
1.2 KiB
C++
27 lines
1.2 KiB
C++
#pragma once
|
|
#include <windows.h>
|
|
#include <cstdint>
|
|
|
|
// MinGW's Win32 std::sleep_for can truncate submillisecond durations to zero.
|
|
// NtDelayExecution retains 100 ns precision and actually sleeps under Wine.
|
|
inline void d4r_sleep_us(unsigned int microseconds)
|
|
{
|
|
using Delay = LONG(WINAPI*)(BOOLEAN, LARGE_INTEGER*);
|
|
static const auto delay = reinterpret_cast<Delay>(reinterpret_cast<void*>(
|
|
GetProcAddress(GetModuleHandleW(L"ntdll.dll"), "NtDelayExecution")));
|
|
// D4R_SHIM_SPIN_POLL=1 (measurement only): every poll yields instead of sleeping, so frame timings are
|
|
// not quantised to the ~250 us a 200 us sleep takes. Costs a CPU core per waiting thread.
|
|
static const bool spin = GetEnvironmentVariableA("D4R_SHIM_SPIN_POLL", nullptr, 0) > 1;
|
|
if (microseconds == 0 || spin)
|
|
{
|
|
SwitchToThread();
|
|
return;
|
|
}
|
|
LARGE_INTEGER interval;
|
|
interval.QuadPart = -static_cast<LONGLONG>(microseconds) * 10;
|
|
if (delay != nullptr && delay(FALSE, &interval) >= 0)
|
|
return;
|
|
// A rounded-up millisecond wait still releases the CPU if ntdll is absent.
|
|
Sleep(static_cast<DWORD>((static_cast<uint64_t>(microseconds) + 999) / 1000));
|
|
}
|