mirror of
https://github.com/valentderah/totk-pc-recomp.git
synced 2026-11-11 01:41:02 +00:00
CHEN Feng
34b4faee7c
-march=x86-64-v3 kept the port and the installer to CPUs with AVX2 and FMA. --cpu v2 compiles the generated code and the runtime for SSE4.2 instead. Without FMA3 the FP lowering calls fma/fmaf, so runtime/fma.c provides correctly rounded ones (musl, MIT) that honour MXCSR's rounding mode, FTZ and DAZ; the UCRT's software fallback rounds incorrectly by up to half an ulp. simd.h's fast paths keep their assumptions. The installer's host check asks for x86-64-v2 and selects libtotkrt.a or libtotkrt-v2.a; both release scripts build and ship the pair. The differential tests compile fma.c as well, so a --cflags=-march=x86-64-v2 run tests it. Tested on an i7-3770K (no AVX2, FMA or BMI) with an RTX 3060 Ti, game 1.4.3: the installer ran end to end, --selftest passed and play holds 40-60 fps at 1080p. fma and fmaf matched 152,288 exact vectors over two seeds, including ties, subnormals and every rounding mode, FTZ and DAZ combination. The v3 build is unchanged: fma.c is an empty translation unit there.
99 lines
4.6 KiB
C
99 lines
4.6 KiB
C
// Host check of the installer's first step, compiled with the bundled clang at install time: does the CPU run
|
|
// -march=x86-64-v3 code (or only x86-64-v2), and does a Vulkan 1.3 device exist. Prints one JSON object on stdout.
|
|
// The Vulkan loader is opened at run time, so a machine without one gets "loader": false instead of a failed start.
|
|
#include <cpuid.h>
|
|
#include <stdio.h>
|
|
#include <string.h>
|
|
#include <vulkan/vulkan.h>
|
|
#ifdef _WIN32
|
|
#include <windows.h>
|
|
#define open_lib() LoadLibraryA("vulkan-1.dll")
|
|
#define lib_sym(l, n) ((void *)GetProcAddress((l), (n)))
|
|
#else
|
|
#include <dlfcn.h>
|
|
#define open_lib() dlopen("libvulkan.so.1", RTLD_NOW)
|
|
#define lib_sym(l, n) dlsym((l), (n))
|
|
#endif
|
|
|
|
static void json_string(const char *s) {
|
|
putchar('"');
|
|
for (; *s; s++) {
|
|
if (*s == '"' || *s == '\\') printf("\\%c", *s);
|
|
else if ((unsigned char)*s < 0x20) printf("\\u%04x", *s);
|
|
else putchar(*s);
|
|
}
|
|
putchar('"');
|
|
}
|
|
|
|
// The x86-64-v2 level from CPUID: SSE3, SSSE3, SSE4.1, SSE4.2, POPCNT, CMPXCHG16B and LAHF/SAHF. Every CPU with
|
|
// SSE4.2 has the others, but the level is what the v2 build is compiled for, so check them all.
|
|
static int x86_64_v2(void) {
|
|
unsigned a, b, c, d;
|
|
if (!__get_cpuid(1, &a, &b, &c, &d)) return 0;
|
|
const unsigned sse3 = 1u << 0, ssse3 = 1u << 9, cx16 = 1u << 13, sse41 = 1u << 19, sse42 = 1u << 20,
|
|
popcnt = 1u << 23;
|
|
if ((c & (sse3 | ssse3 | cx16 | sse41 | sse42 | popcnt)) != (sse3 | ssse3 | cx16 | sse41 | sse42 | popcnt))
|
|
return 0;
|
|
if (!__get_cpuid(0x80000001, &a, &b, &c, &d)) return 0;
|
|
return (c & (1u << 0)) != 0; // LAHF/SAHF
|
|
}
|
|
|
|
// The x86-64-v3 level from CPUID: AVX, AVX2, BMI1, BMI2, F16C, FMA, LZCNT and MOVBE, with the OS saving the YMM state.
|
|
// Not __builtin_cpu_supports("x86-64-v3"): clang reads that from the C runtime's CPU model, and libgcc before GCC 12
|
|
// (the Linux release's sysroot has GCC 10) has no level bits, so it answers false on every CPU.
|
|
static int x86_64_v3(void) {
|
|
if (!x86_64_v2()) return 0;
|
|
unsigned a, b, c, d;
|
|
if (!__get_cpuid(1, &a, &b, &c, &d)) return 0;
|
|
const unsigned fma = 1u << 12, movbe = 1u << 22, osxsave = 1u << 27, avx = 1u << 28, f16c = 1u << 29;
|
|
if ((c & (fma | movbe | osxsave | avx | f16c)) != (fma | movbe | osxsave | avx | f16c)) return 0;
|
|
unsigned lo, hi;
|
|
__asm__("xgetbv" : "=a"(lo), "=d"(hi) : "c"(0));
|
|
if ((lo & 6) != 6) return 0; // XMM and YMM state enabled by the OS
|
|
if (!__get_cpuid_count(7, 0, &a, &b, &c, &d)) return 0;
|
|
const unsigned bmi1 = 1u << 3, avx2 = 1u << 5, bmi2 = 1u << 8;
|
|
if ((b & (bmi1 | avx2 | bmi2)) != (bmi1 | avx2 | bmi2)) return 0;
|
|
if (!__get_cpuid(0x80000001, &a, &b, &c, &d)) return 0;
|
|
return (c & (1u << 5)) != 0; // LZCNT (ABM)
|
|
}
|
|
|
|
int main(void) {
|
|
printf("{\"x86_64_v2\": %s, \"x86_64_v3\": %s, ", x86_64_v2() ? "true" : "false",
|
|
x86_64_v3() ? "true" : "false");
|
|
void *lib = open_lib();
|
|
PFN_vkGetInstanceProcAddr gipa = lib ? (PFN_vkGetInstanceProcAddr)lib_sym(lib, "vkGetInstanceProcAddr") : NULL;
|
|
if (!gipa) {
|
|
printf("\"loader\": false, \"devices\": []}\n");
|
|
return 0;
|
|
}
|
|
printf("\"loader\": true, ");
|
|
PFN_vkCreateInstance create = (PFN_vkCreateInstance)gipa(NULL, "vkCreateInstance");
|
|
VkApplicationInfo app = {.sType = VK_STRUCTURE_TYPE_APPLICATION_INFO, .pApplicationName = "totk-install",
|
|
.apiVersion = VK_API_VERSION_1_3};
|
|
VkInstanceCreateInfo ci = {.sType = VK_STRUCTURE_TYPE_INSTANCE_CREATE_INFO, .pApplicationInfo = &app};
|
|
VkInstance inst = VK_NULL_HANDLE;
|
|
VkResult r = create ? create(&ci, NULL, &inst) : VK_ERROR_INITIALIZATION_FAILED;
|
|
if (r != VK_SUCCESS) {
|
|
printf("\"instance\": %d, \"devices\": []}\n", (int)r);
|
|
return 0;
|
|
}
|
|
PFN_vkEnumeratePhysicalDevices enumerate = (PFN_vkEnumeratePhysicalDevices)gipa(inst, "vkEnumeratePhysicalDevices");
|
|
PFN_vkGetPhysicalDeviceProperties props = (PFN_vkGetPhysicalDeviceProperties)gipa(inst, "vkGetPhysicalDeviceProperties");
|
|
PFN_vkDestroyInstance destroy = (PFN_vkDestroyInstance)gipa(inst, "vkDestroyInstance");
|
|
VkPhysicalDevice devs[16];
|
|
uint32_t n = 16;
|
|
if (enumerate(inst, &n, devs) < 0) n = 0;
|
|
printf("\"instance\": 0, \"devices\": [");
|
|
for (uint32_t i = 0; i < n; i++) {
|
|
VkPhysicalDeviceProperties p;
|
|
props(devs[i], &p);
|
|
printf("%s{\"name\": ", i ? ", " : "");
|
|
json_string(p.deviceName);
|
|
printf(", \"api\": [%u, %u, %u], \"type\": %d}", VK_API_VERSION_MAJOR(p.apiVersion),
|
|
VK_API_VERSION_MINOR(p.apiVersion), VK_API_VERSION_PATCH(p.apiVersion), (int)p.deviceType);
|
|
}
|
|
printf("]}\n");
|
|
destroy(inst, NULL);
|
|
return 0;
|
|
}
|