Improve GPU compatibility, RDNA2 kernels and startup diagnostics
- Match render/compute adapters and gate RR models by GPU capabilities - Add RDNA2 native texture kernels and fix FP16 rounding - Harden model builds, cache validation and packaging - Add startup tracing, timeouts, documentation and regression tests
This commit is contained in:
ayo committed
1 parent
ca93d0fbf7
commit
2558fcbd39
32 files changed
+1131
-81
No files matched your search
@@ -0,0 +1,149 @@
|
||||
"""GPU identity and model capability decisions without a GPU or Wine process."""
|
||||
from pathlib import Path
|
||||
import subprocess
|
||||
import tempfile
|
||||
import unittest
|
||||
|
||||
ROOT = Path(__file__).resolve().parents[1]
|
||||
|
||||
|
||||
class GpuCompatibilityTests(unittest.TestCase):
|
||||
def compile_run(self, source, cxx=False):
|
||||
with tempfile.TemporaryDirectory() as t:
|
||||
executable = Path(t) / 'check'
|
||||
result = subprocess.run(['c++' if cxx else 'cc', '-x', 'c++' if cxx else 'c',
|
||||
'-std=c++17' if cxx else '-std=gnu11', '-Wall', '-Wextra', '-Werror',
|
||||
'-pthread',
|
||||
'-I', str(ROOT / 'tools'), '-o', str(executable), '-'], input=source,
|
||||
capture_output=True, text=True)
|
||||
self.assertEqual(result.returncode, 0, result.stderr)
|
||||
subprocess.run([str(executable)], check=True, timeout=5)
|
||||
|
||||
def test_pci_identity_is_not_a_vendor_id_or_gpu_size_guess(self):
|
||||
self.compile_run(r'''
|
||||
#include "d4r_gpu_identity.h"
|
||||
#include <assert.h>
|
||||
int main(void) {
|
||||
assert(d4r_same_pci("0000:03:00.0", "00000000:03:00.0"));
|
||||
assert(!d4r_same_pci("0000:03:00.0", "0000:04:00.0"));
|
||||
assert(!d4r_same_pci("0000:03:00.0", "0001:03:00.0"));
|
||||
assert(!d4r_same_pci("0000:03:00.0garbage", "0000:03:00.0"));
|
||||
assert(d4r_pci_matches_kfd("0000:03:00.0", 0, 0x300));
|
||||
assert(!d4r_pci_matches_kfd("0000:03:00.0", 0, 0x400));
|
||||
assert(!d4r_pci_matches_kfd("0000:03:00.0", 1, 0x300));
|
||||
}
|
||||
''')
|
||||
|
||||
def test_bridge_maps_nonzero_compute_ordinal_and_only_its_luid(self):
|
||||
source = (ROOT / 'tools/wine_nvcuda_bridge.c').read_text()
|
||||
selection = source[source.index('static CUresult selected_cuda_device('):
|
||||
source.index('static void create_default_zluda_context(')]
|
||||
luid = source[source.index('CUresult WINAPI cuDeviceGetLuid('):
|
||||
source.index('CUresult WINAPI cuDeviceGetAttribute(')]
|
||||
self.compile_run(r'''
|
||||
#include "d4r_gpu_identity.h"
|
||||
#include <assert.h>
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
#define WINAPI
|
||||
typedef int CUresult;
|
||||
typedef int CUdevice;
|
||||
typedef int (*CUDEVICEGETCOUNT_FN)(int*);
|
||||
typedef int (*CUDEVICEGET_FN)(int*, int);
|
||||
typedef int (*CUDEVICEGETLUID_FN)(char*, unsigned*, int);
|
||||
enum { CUDA_SUCCESS=0, CUDA_ERROR_NOT_INITIALIZED=3, CUDA_ERROR_NOT_SUPPORTED=801 };
|
||||
static const char* render = "0000:03:00.0";
|
||||
static int devices = 2;
|
||||
static unsigned GetEnvironmentVariableA(const char* key, char* out, unsigned size) {
|
||||
(void)key; snprintf(out, size, "%s", render); return (unsigned)strlen(render);
|
||||
}
|
||||
static void tracef(const char* fmt, ...) { (void)fmt; }
|
||||
static int count(int* n) { *n=devices; return 0; }
|
||||
static int get(int* d,int n) { *d=100+n; return 0; }
|
||||
static int pci(char* out,int size,int device) {
|
||||
snprintf(out, (size_t)size, "%s", device==101 ? "00000000:03:00.0" : "0000:04:00.0"); return 0;
|
||||
}
|
||||
static int original_luid(char* out,unsigned* mask,int device) { (void)device; memset(out,0,8);*mask=0;return 0; }
|
||||
static void* find_zluda_symbol(const char* name) {
|
||||
if (!strcmp(name,"cuDeviceGetCount")) return (void*)count;
|
||||
if (!strcmp(name,"cuDeviceGet")) return (void*)get;
|
||||
if (!strcmp(name,"cuDeviceGetPCIBusId")) return (void*)pci;
|
||||
return (void*)original_luid;
|
||||
}
|
||||
static int missing(const char* name) { (void)name; return 999; }
|
||||
static unsigned get_process_u32(const char* name,unsigned fallback) {
|
||||
(void)fallback;
|
||||
return strstr(name,"LOW") ? 0x3f2 : strstr(name,"HIGH") ? 0 : 1;
|
||||
}
|
||||
''' + selection + luid + r'''
|
||||
int main(void) {
|
||||
assert(d4r_pci_matches_kfd("0000:03:00.0",0,0x300));
|
||||
int selected=-1; assert(selected_cuda_device(&selected)==0 && selected==101);
|
||||
char id[8]; unsigned mask=9;
|
||||
assert(cuDeviceGetLuid(id,&mask,100)==0 && mask==0);
|
||||
assert(cuDeviceGetLuid(id,&mask,101)==0 && mask==1);
|
||||
unsigned low=0;memcpy(&low,id,4);assert(low==0x3f2);
|
||||
render="0000:05:00.0";assert(selected_cuda_device(&selected)==801);
|
||||
render="";assert(selected_cuda_device(&selected)==801);
|
||||
devices=1;assert(selected_cuda_device(&selected)==0 && selected==100);
|
||||
}
|
||||
''')
|
||||
|
||||
def test_rr_model_cannot_reach_unsupported_fp8_pipelines(self):
|
||||
self.compile_run(r'''
|
||||
#include "d4r_engine_compat.h"
|
||||
#include <cassert>
|
||||
int main() {
|
||||
const char* fp8 = "D4RR0001\npreset 4\nstage enc0 x.spv\n";
|
||||
const char* wide = "D4RR0001\npreset 4\narithmetic gfx11\nstage enc0 x.spv\n";
|
||||
assert(!d4r_rr_model_compatible(fp8, true, false));
|
||||
assert(!d4r_rr_model_compatible(wide, false, false));
|
||||
assert(d4r_rr_model_compatible(wide, true, false));
|
||||
assert(d4r_rr_model_compatible(fp8, true, true));
|
||||
assert(!d4r_rr_model_compatible("D4RR0002\npreset 6\n", true, false));
|
||||
assert(!d4r_rr_model_compatible("D4RR0001\narithmetic unknown\n", true, true));
|
||||
VkCooperativeMatrixPropertiesKHR p{};
|
||||
p.MSize=p.NSize=p.KSize=16; p.scope=VK_SCOPE_SUBGROUP_KHR;
|
||||
p.AType=p.BType=VK_COMPONENT_TYPE_FLOAT16_KHR;
|
||||
p.CType=p.ResultType=VK_COMPONENT_TYPE_FLOAT32_KHR;
|
||||
assert(d4r_matrix_tuple(p, VK_COMPONENT_TYPE_FLOAT16_KHR));
|
||||
p.KSize=32; assert(!d4r_matrix_tuple(p, VK_COMPONENT_TYPE_FLOAT16_KHR));
|
||||
}
|
||||
''', cxx=True)
|
||||
|
||||
def test_existing_context_is_preserved_and_bootstrap_binds_each_thread(self):
|
||||
text = (ROOT / 'tools/wine_nvcuda_bridge.c').read_text()
|
||||
ensure = text[text.index('static void ensure_context(void)'):text.index('/* D4R_NGX_STREAM_PRIORITY')]
|
||||
self.compile_run(r'''
|
||||
#include <assert.h>
|
||||
#include <pthread.h>
|
||||
#include <stdint.h>
|
||||
#include <string.h>
|
||||
typedef int CUresult;
|
||||
typedef void* CUcontext;
|
||||
typedef CUresult (*CUCTX_CURRENT_FN)(CUcontext);
|
||||
enum { CUDA_SUCCESS=0 };
|
||||
static pthread_once_t context_once=PTHREAD_ONCE_INIT;
|
||||
static int context_bootstrap_result=3, bootstrap_calls=0;
|
||||
static _Thread_local int context_setup_result=3;
|
||||
static _Thread_local void* active;
|
||||
static void* cuda_context;
|
||||
static int current(void** out) { *out=active;return 0; }
|
||||
static int set(void* context) { active=context;return 0; }
|
||||
static void* find_zluda_symbol(const char* key) {
|
||||
return !strcmp(key,"cuCtxGetCurrent") ? (void*)current : (void*)set;
|
||||
}
|
||||
static void create_default_zluda_context(void) {
|
||||
++bootstrap_calls;cuda_context=(void*)(uintptr_t)0x456;context_bootstrap_result=0;
|
||||
}
|
||||
''' + ensure + r'''
|
||||
static void* worker(void* ignored) {
|
||||
(void)ignored;ensure_context();assert(active==cuda_context && context_setup_result==0);return NULL;
|
||||
}
|
||||
int main(void) {
|
||||
active=(void*)(uintptr_t)0x123;ensure_context();assert(active==(void*)(uintptr_t)0x123 && bootstrap_calls==0);
|
||||
pthread_t a;assert(!pthread_create(&a,NULL,worker,NULL));pthread_join(a,NULL);
|
||||
assert(bootstrap_calls==1);ensure_context();assert(active==(void*)(uintptr_t)0x123);
|
||||
assert(!pthread_create(&a,NULL,worker,NULL));pthread_join(a,NULL);assert(bootstrap_calls==1);
|
||||
}
|
||||
''')
|
||||
Reference in new issue
Block a user