diff --git a/training/Makefile b/training/Makefile index 226bb39..9cc9e34 100644 --- a/training/Makefile +++ b/training/Makefile @@ -11,10 +11,26 @@ train: train.m ane_runtime.h ane_mil_gen.h model.h forward.h backward.h train_large: train_large.m $(HEADERS_LARGE) $(CC) $(CFLAGS) -o $@ train_large.m $(LDFLAGS) -framework Accelerate +PROBES = test_weight_reload test_perf_stats test_qos_sweep test_ane_advanced + +test_weight_reload: test_weight_reload.m + $(CC) $(CFLAGS) -o $@ $< $(LDFLAGS) + +test_perf_stats: test_perf_stats.m + $(CC) $(CFLAGS) -o $@ $< $(LDFLAGS) + +test_qos_sweep: test_qos_sweep.m + $(CC) $(CFLAGS) -o $@ $< $(LDFLAGS) + +test_ane_advanced: test_ane_advanced.m + $(CC) $(CFLAGS) -o $@ $< $(LDFLAGS) + +probes: $(PROBES) + tokenize: python3 tokenize.py clean: - rm -f train train_large + rm -f train train_large $(PROBES) -.PHONY: clean tokenize +.PHONY: clean tokenize probes diff --git a/training/m5result.md b/training/m5result.md new file mode 100644 index 0000000..91d5eaa --- /dev/null +++ b/training/m5result.md @@ -0,0 +1,146 @@ +# M5 ANE Probe Results + +**Machine**: Apple M5, macOS 26.3 (Darwin 25.3.0) +**Date**: 2026-03-01 +**ANE Family**: H16 (same as M4) + +--- + +## test_weight_reload — FAIL + +**Question**: Can we skip recompilation by overwriting weight blobs on disk and calling unload+load? + +**Result**: **No.** Weights are baked at compile time. Overwriting `weights/weight.bin` in tmpDir and doing unload→load produces identical output — the ANE ignores the file change. + +``` +Kernel: 64x64 conv, spatial=32 +Compile+load: 33.3ms | Unload: 0.5ms | Reload: 3.8ms +Output A (identity): [0.0100, 0.0200, 0.0300, 0.0400] +Output B (3x identity, after file overwrite + reload): [0.0100, 0.0200, 0.0300, 0.0400] +Max A-B diff: 0.000000 +``` + +**Implication**: Cannot eliminate compilation bottleneck via file swap. Must use async recompile, raise ACCUM_STEPS, or find another path. + +--- + +## test_perf_stats — Partial Success + +**Question**: What hardware counters does `_ANEPerformanceStats` expose? + +**Result**: The class exists with useful properties, but `alloc/init` returns `nil`. Must be created via factory methods that require internal buffers. + +### Available Properties +| Property | Type | Description | +|----------|------|-------------| +| `hwExecutionTime` | uint64 | Hardware execution time in nanoseconds | +| `perfCounterData` | NSData | Raw performance counter data blob | +| `pStatsRawData` | NSData | Raw stats data | + +### Factory Methods +- `+statsWithHardwareExecutionNS:` — create from hw execution time +- `+statsWithRequestPerformanceBuffer:statsBufferSize:` — create from raw buffer +- `+statsWithReconstructed:hardwareExecutionNS:aneStatsRawData:` — reconstruct from components +- `+driverMaskForANEFMask:` — convert ANE feature mask to driver mask + +### Instance Methods +- `-performanceCounters` — returns counter object +- `-stringForPerfCounter:` — human-readable counter name +- `-emitPerfcounterSignpostsWithModelStringID:` — emit signposts for profiling + +**Key Finding**: `_ANEModel` has `perfStatsMask` property. Setting this on the model before eval likely enables perf stats population in the request. The `_ANEPerformanceStats` object passed to request gets populated *by the driver* — we need to set the mask first, then read stats after eval. + +--- + +## test_qos_sweep — All QoS Values Work + +**Question**: Does QoS affect ANE frequency or latency? + +**Result**: All QoS values 0-63 compile, load, and eval successfully. **No measurable latency difference** — ANE appears to run at fixed frequency regardless of QoS. + +``` +Kernel: 256x256 conv, spatial=64 (8.4 MFLOPS) + QoS Compile Load Eval(1) Eval(avg10) Status + 0 13.9ms 15.6ms 0.22ms 0.11ms OK + 1 11.6ms 1.8ms 0.17ms 0.07ms OK + 5 11.4ms 1.7ms 0.17ms 0.07ms OK + 10 12.0ms 1.8ms 0.18ms 0.06ms OK + 21 11.8ms 1.7ms 0.18ms 0.08ms OK + 33 11.5ms 1.7ms 0.17ms 0.06ms OK + 47 10.8ms 1.7ms 0.18ms 0.06ms OK + 63 11.3ms 1.7ms 0.17ms 0.07ms OK +``` + +**Notes**: +- QoS 0 has elevated load time (15.6ms vs ~1.7ms) — possibly first-use initialization +- Compile time ~11ms, load ~1.7ms, eval ~0.07ms avg for 8.4 MFLOPS kernel +- Eval throughput: 8.4M / 0.07ms = **120 GFLOPS** for a single 256×256 conv + +--- + +## test_ane_advanced — Key Findings + +### weightsBuffer IOSurface — Does NOT Override + +Passing a `weightsBuffer` IOSurface with different weights to the request **does not change output**. The compiled weights are still used. + +``` +Baseline (1x identity): Output[0..3] = [0.1000, 0.2000, 0.3000, 0.3999] +weightsBuffer (3x identity): Output[0..3] = [0.1000, 0.2000, 0.3000, 0.3999] +``` + +The `weightsBuffer` parameter likely serves a different purpose (perhaps for models that declare runtime weights vs baked constants). + +### procedureIndex — All 0-15 Succeed + +All procedure indices 0-15 return OK. Single-procedure models work with any index (they probably ignore non-zero indices). Multi-procedure models compiled from `_ANEChainingRequest` would use different indices for different subgraphs. + +### SharedEvents — Classes Exist, Need IOSurfaceSharedEvent + +- `_ANESharedEvents`, `_ANESharedSignalEvent`, `_ANESharedWaitEvent` all exist +- `alloc/init` returns nil — they need `IOSurfaceSharedEvent` objects (Metal shared events) +- `_ANESharedSignalEvent` has `symbolIndex` and `agentMask` — for GPU↔ANE sync +- Signal API: `+signalEventWithValue:symbolIndex:eventType:sharedEvent:` +- Wait API: `+waitEventWithValue:sharedEvent:eventType:` + +### ChainingRequest — Exists with Loopback Support + +`_ANEChainingRequest` supports chained execution: +- `inputBuffer`, `outputSets` — multiple output sets for pipeline +- `loopbackInputSymbolIndex`, `loopbackOutputSymbolIndex` — feed output back as input +- `fwEnqueueDelay` — firmware-level enqueue timing +- `memoryPoolId` — shared memory pool across chained ops +- `signalEvents` — sync with other agents + +### Notable _ANEClient Methods +- `evaluateRealTimeWithModel:options:request:error:` — real-time eval path +- `loadRealTimeModel:options:qos:error:` — RT model loading +- `beginRealTimeTask` / `endRealTimeTask` — RT task bracketing +- `prepareChainingWithModel:options:chainingReq:qos:error:` — set up chaining +- `enqueueSetsWithModel:outputSet:options:qos:error:` — enqueue output sets +- `buffersReadyWithModel:inputBuffers:options:qos:error:` — signal input ready + +### All ANE Classes Found (67 total) +Key unexplored classes: `_ANEDeviceController`, `_ANEQoSMapper`, `_ANEBuffer`, `_ANEIOSurfaceOutputSets`, `_ANEProgramForEvaluation`, `_ANEProgramIOSurfacesMapper`, `_ANEModelInstanceParameters`, `_ANEInputBuffersReady`, `_ANEOutputSetEnqueue` + +--- + +## Strategic Implications + +### Compilation Bottleneck (Primary) +Weight reload and weightsBuffer both fail. **Weights are irrevocably baked at compile time.** The only paths forward: +1. **Raise ACCUM_STEPS significantly** (10→100+) to amortize compile cost +2. **Async background compilation** while training continues with old weights +3. **Chaining API** (`_ANEChainingRequest`) to pipeline multiple layers in one dispatch + +### Performance Monitoring +`hwExecutionTime` from `_ANEPerformanceStats` gives wall-clock ANE time per eval. To enable: +1. Set `perfStatsMask` on the `_ANEInMemoryModel` before eval +2. Pass an `_ANEPerformanceStats` to the request +3. Read `hwExecutionTime` after eval + +### Real-Time Path +`_ANEClient` has a dedicated real-time evaluation path (`evaluateRealTimeWithModel:`) with RT load/unload. This may provide lower/more predictable latency. + +### Chaining (Most Promising for Utilization) +`_ANEChainingRequest` with loopback could allow multiple layers to execute as a single ANE program without CPU round-trips between layers. Combined with `_ANEIOSurfaceOutputSets` and `_ANEInputBuffersReady`, this could dramatically reduce idle time between kernel dispatches. diff --git a/training/test_ane_advanced.m b/training/test_ane_advanced.m new file mode 100644 index 0000000..07e9038 --- /dev/null +++ b/training/test_ane_advanced.m @@ -0,0 +1,245 @@ +// test_ane_advanced.m — Probe advanced ANE interfaces +// SharedEvents, weightsBuffer, procedureIndex, VirtualClient, ChainingRequest +#import +#import +#import +#import +#import +#import +#include + +static mach_timebase_info_data_t g_tb; +static double tb_ms(uint64_t t) { return (double)t * g_tb.numer / g_tb.denom / 1e6; } + +static void dump_class(const char *name) { + Class cls = NSClassFromString([NSString stringWithUTF8String:name]); + if (!cls) { printf(" %s: NOT FOUND\n", name); return; } + printf("\n=== %s ===\n", name); + unsigned int count; + Method *methods = class_copyMethodList(object_getClass(cls), &count); + if (count) printf(" Class methods:\n"); + for (unsigned int i = 0; i < count; i++) { + SEL s = method_getName(methods[i]); + const char *enc = method_getTypeEncoding(methods[i]); + printf(" + %s [%s]\n", sel_getName(s), enc ? enc : "?"); + } + free(methods); + methods = class_copyMethodList(cls, &count); + if (count) printf(" Instance methods:\n"); + for (unsigned int i = 0; i < count; i++) { + SEL s = method_getName(methods[i]); + const char *enc = method_getTypeEncoding(methods[i]); + printf(" - %s [%s]\n", sel_getName(s), enc ? enc : "?"); + } + free(methods); + unsigned int pcount; + objc_property_t *props = class_copyPropertyList(cls, &pcount); + if (pcount) printf(" Properties:\n"); + for (unsigned int i = 0; i < pcount; i++) { + const char *pname = property_getName(props[i]); + const char *pattr = property_getAttributes(props[i]); + printf(" @property %s [%s]\n", pname, pattr ? pattr : "?"); + } + free(props); +} + +static IOSurfaceRef make_surface(size_t bytes) { + return IOSurfaceCreate((__bridge CFDictionaryRef)@{ + (id)kIOSurfaceWidth:@(bytes), (id)kIOSurfaceHeight:@1, + (id)kIOSurfaceBytesPerElement:@1, (id)kIOSurfaceBytesPerRow:@(bytes), + (id)kIOSurfaceAllocSize:@(bytes), (id)kIOSurfacePixelFormat:@0}); +} + +int main() { + @autoreleasepool { + setbuf(stdout, NULL); + mach_timebase_info(&g_tb); + dlopen("/System/Library/PrivateFrameworks/AppleNeuralEngine.framework/AppleNeuralEngine", RTLD_NOW); + + printf("=== ANE Advanced Interface Probe ===\n"); + + // === Part 1: Event/Sync classes === + printf("\n--- Part 1: Event/Sync Classes ---\n"); + dump_class("_ANESharedEvents"); + dump_class("_ANESharedSignalEvent"); + dump_class("_ANESharedWaitEvent"); + dump_class("_ANEEvent"); + dump_class("_ANEFenceEvent"); + + const char *event_classes[] = { + "_ANESharedEvents", "_ANESharedSignalEvent", "_ANESharedWaitEvent", + "_ANEEvent", "_ANEFenceEvent", NULL + }; + for (int i = 0; event_classes[i]; i++) { + Class cls = NSClassFromString([NSString stringWithUTF8String:event_classes[i]]); + if (!cls) continue; + @try { + id obj = [[cls alloc] init]; + printf(" %s alloc/init: %s\n", event_classes[i], + obj ? [[obj description] UTF8String] : "nil"); + } @catch (NSException *ex) { + printf(" %s alloc/init: EXCEPTION: %s\n", event_classes[i], [[ex reason] UTF8String]); + } + } + + // === Part 2: VirtualClient and ChainingRequest === + printf("\n--- Part 2: VirtualClient / ChainingRequest ---\n"); + dump_class("_ANEVirtualClient"); + dump_class("_ANEChainingRequest"); + dump_class("_ANEMultiRequest"); + dump_class("_ANEBatchRequest"); + + // === Part 3: Compile working kernel for weightsBuffer + procedureIndex tests === + printf("\n--- Part 3: weightsBuffer IOSurface test ---\n"); + Class g_D = NSClassFromString(@"_ANEInMemoryModelDescriptor"); + Class g_I = NSClassFromString(@"_ANEInMemoryModel"); + Class g_AR = NSClassFromString(@"_ANERequest"); + Class g_AIO= NSClassFromString(@"_ANEIOSurfaceObject"); + + int CH = 64, SP = 32; + _Float16 *w = (_Float16*)calloc(CH*CH, sizeof(_Float16)); + for (int i = 0; i < CH; i++) w[i*CH+i] = (_Float16)1.0f; + int ws = CH*CH*2, tot = 128+ws; + uint8_t *blob = (uint8_t*)calloc(tot,1); + blob[0]=1; blob[4]=2; blob[64]=0xEF; blob[65]=0xBE; blob[66]=0xAD; blob[67]=0xDE; blob[68]=1; + *(uint32_t*)(blob+72)=ws; *(uint32_t*)(blob+80)=128; + memcpy(blob+128, w, ws); + NSData *wdata = [NSData dataWithBytesNoCopy:blob length:tot freeWhenDone:YES]; + + NSString *mil = [NSString stringWithFormat: + @"program(1.3)\n" + "[buildInfo = dict({{\"coremlc-component-MIL\", \"3510.2.1\"}, " + "{\"coremlc-version\", \"3505.4.1\"}, {\"coremltools-component-milinternal\", \"\"}, " + "{\"coremltools-version\", \"9.0\"}})]\n" + "{\n" + " func main(tensor x) {\n" + " string pt = const()[name=string(\"pt\"), val=string(\"valid\")];\n" + " tensor st = const()[name=string(\"st\"), val=tensor([1,1])];\n" + " tensor pd = const()[name=string(\"pd\"), val=tensor([0,0,0,0])];\n" + " tensor dl = const()[name=string(\"dl\"), val=tensor([1,1])];\n" + " int32 gr = const()[name=string(\"gr\"), val=int32(1)];\n" + " string to16 = const()[name=string(\"to16\"), val=string(\"fp16\")];\n" + " tensor x16 = cast(dtype=to16,x=x)[name=string(\"cin\")];\n" + " tensor W = const()[name=string(\"W\"), " + "val=tensor(BLOBFILE(path=string(\"@model_path/weights/weight.bin\"), offset=uint64(64)))];\n" + " tensor y16 = conv(dilations=dl,groups=gr,pad=pd,pad_type=pt,strides=st,weight=W,x=x16)" + "[name=string(\"conv\")];\n" + " string to32 = const()[name=string(\"to32\"), val=string(\"fp32\")];\n" + " tensor y = cast(dtype=to32,x=y16)[name=string(\"cout\")];\n" + " } -> (y);\n" + "}\n", CH, SP, CH, SP, CH, CH, CH, CH, CH, SP, CH, SP]; + + NSData *md = [mil dataUsingEncoding:NSUTF8StringEncoding]; + id desc = ((id(*)(Class,SEL,id,id,id))objc_msgSend)(g_D, @selector(modelWithMILText:weights:optionsPlist:), + md, @{@"@model_path/weights/weight.bin": @{@"offset":@0, @"data":wdata}}, nil); + id mdl = ((id(*)(Class,SEL,id))objc_msgSend)(g_I, @selector(inMemoryModelWithDescriptor:), desc); + id hx = ((id(*)(id,SEL))objc_msgSend)(mdl, @selector(hexStringIdentifier)); + NSString *td = [NSTemporaryDirectory() stringByAppendingPathComponent:hx]; + NSFileManager *fm = [NSFileManager defaultManager]; + [fm createDirectoryAtPath:[td stringByAppendingPathComponent:@"weights"] + withIntermediateDirectories:YES attributes:nil error:nil]; + [md writeToFile:[td stringByAppendingPathComponent:@"model.mil"] atomically:YES]; + [wdata writeToFile:[td stringByAppendingPathComponent:@"weights/weight.bin"] atomically:YES]; + + NSError *e = nil; + ((BOOL(*)(id,SEL,unsigned int,id,NSError**))objc_msgSend)(mdl, @selector(compileWithQoS:options:error:), 21, @{}, &e); + ((BOOL(*)(id,SEL,unsigned int,id,NSError**))objc_msgSend)(mdl, @selector(loadWithQoS:options:error:), 21, @{}, &e); + + int ioBytes = CH * SP * 4; + IOSurfaceRef ioIn = make_surface(ioBytes); + IOSurfaceRef ioOut = make_surface(ioBytes); + + IOSurfaceLock(ioIn, 0, NULL); + float *inp = (float*)IOSurfaceGetBaseAddress(ioIn); + for (int c = 0; c < CH; c++) for (int s = 0; s < SP; s++) inp[c*SP+s] = (float)(s+1) * 0.1f; + IOSurfaceUnlock(ioIn, 0, NULL); + + // Baseline eval + id wI = ((id(*)(Class,SEL,IOSurfaceRef))objc_msgSend)(g_AIO, @selector(objectWithIOSurface:), ioIn); + id wO = ((id(*)(Class,SEL,IOSurfaceRef))objc_msgSend)(g_AIO, @selector(objectWithIOSurface:), ioOut); + id req0 = ((id(*)(Class,SEL,id,id,id,id,id,id,id))objc_msgSend)(g_AR, + @selector(requestWithInputs:inputIndices:outputs:outputIndices:weightsBuffer:perfStats:procedureIndex:), + @[wI], @[@0], @[wO], @[@0], nil, nil, @0); + BOOL ok = ((BOOL(*)(id,SEL,unsigned int,id,id,NSError**))objc_msgSend)( + mdl, @selector(evaluateWithQoS:options:request:error:), 21, @{}, req0, &e); + printf(" Baseline eval (weightsBuffer=nil, procIdx=0): %s\n", ok ? "OK" : "FAIL"); + + IOSurfaceLock(ioOut, kIOSurfaceLockReadOnly, NULL); + float *out0 = (float*)IOSurfaceGetBaseAddress(ioOut); + float baseline_0 = out0[0], baseline_1 = out0[1]; + printf(" Output[0..3]: [%.4f, %.4f, %.4f, %.4f]\n", out0[0], out0[1], out0[2], out0[3]); + IOSurfaceUnlock(ioOut, kIOSurfaceLockReadOnly, NULL); + + // Test weightsBuffer: IOSurface with 3x identity weights + printf("\n Testing weightsBuffer IOSurface...\n"); + _Float16 *w3 = (_Float16*)calloc(CH*CH, sizeof(_Float16)); + for (int i = 0; i < CH; i++) w3[i*CH+i] = (_Float16)3.0f; + IOSurfaceRef ioW = make_surface(ws); + IOSurfaceLock(ioW, 0, NULL); + memcpy(IOSurfaceGetBaseAddress(ioW), w3, ws); + IOSurfaceUnlock(ioW, 0, NULL); + free(w3); + id wW = ((id(*)(Class,SEL,IOSurfaceRef))objc_msgSend)(g_AIO, @selector(objectWithIOSurface:), ioW); + + wI = ((id(*)(Class,SEL,IOSurfaceRef))objc_msgSend)(g_AIO, @selector(objectWithIOSurface:), ioIn); + wO = ((id(*)(Class,SEL,IOSurfaceRef))objc_msgSend)(g_AIO, @selector(objectWithIOSurface:), ioOut); + id req_wb = ((id(*)(Class,SEL,id,id,id,id,id,id,id))objc_msgSend)(g_AR, + @selector(requestWithInputs:inputIndices:outputs:outputIndices:weightsBuffer:perfStats:procedureIndex:), + @[wI], @[@0], @[wO], @[@0], wW, nil, @0); + printf(" Request with weightsBuffer: %s\n", req_wb ? "created" : "nil"); + + if (req_wb) { + ok = ((BOOL(*)(id,SEL,unsigned int,id,id,NSError**))objc_msgSend)( + mdl, @selector(evaluateWithQoS:options:request:error:), 21, @{}, req_wb, &e); + printf(" Eval with weightsBuffer: %s\n", ok ? "OK" : e ? [[e description] UTF8String] : "FAIL"); + if (ok) { + IOSurfaceLock(ioOut, kIOSurfaceLockReadOnly, NULL); + float *outW = (float*)IOSurfaceGetBaseAddress(ioOut); + printf(" Output[0..3]: [%.4f, %.4f, %.4f, %.4f]\n", outW[0], outW[1], outW[2], outW[3]); + bool changed = fabsf(outW[0] - baseline_0) > 0.001f; + bool is_3x = fabsf(outW[0] - baseline_0 * 3.0f) < 0.1f; + printf(" weightsBuffer: output %s", changed ? "CHANGED" : "unchanged"); + if (changed) printf(" (%s)", is_3x ? "matches 3x — WORKS!" : "but not 3x as expected"); + printf("\n"); + IOSurfaceUnlock(ioOut, kIOSurfaceLockReadOnly, NULL); + } + } + CFRelease(ioW); + + // === Part 4: procedureIndex sweep === + printf("\n--- Part 4: procedureIndex sweep (0-15) ---\n"); + for (int pi = 0; pi < 16; pi++) { + wI = ((id(*)(Class,SEL,IOSurfaceRef))objc_msgSend)(g_AIO, @selector(objectWithIOSurface:), ioIn); + wO = ((id(*)(Class,SEL,IOSurfaceRef))objc_msgSend)(g_AIO, @selector(objectWithIOSurface:), ioOut); + id req_p = ((id(*)(Class,SEL,id,id,id,id,id,id,id))objc_msgSend)(g_AR, + @selector(requestWithInputs:inputIndices:outputs:outputIndices:weightsBuffer:perfStats:procedureIndex:), + @[wI], @[@0], @[wO], @[@0], nil, nil, @(pi)); + if (!req_p) { printf(" procIdx %2d: request=nil\n", pi); continue; } + ok = ((BOOL(*)(id,SEL,unsigned int,id,id,NSError**))objc_msgSend)( + mdl, @selector(evaluateWithQoS:options:request:error:), 21, @{}, req_p, &e); + printf(" procIdx %2d: %s%s\n", pi, ok ? "OK" : "FAIL", + !ok && e ? [NSString stringWithFormat:@" (%@)", [e localizedDescription]].UTF8String : ""); + } + + // === Part 5: Scan all ANE classes === + printf("\n--- Part 5: All ANE-prefixed classes ---\n"); + unsigned int classCount; + Class *allClasses = objc_copyClassList(&classCount); + for (unsigned int i = 0; i < classCount; i++) { + const char *name = class_getName(allClasses[i]); + if (strstr(name, "ANE") || strstr(name, "ane")) { + printf(" %s\n", name); + } + } + free(allClasses); + free(w); + + // Cleanup + ((BOOL(*)(id,SEL,unsigned int,NSError**))objc_msgSend)(mdl, @selector(unloadWithQoS:error:), 21, &e); + [fm removeItemAtPath:td error:nil]; + CFRelease(ioIn); CFRelease(ioOut); + + printf("\nDone.\n"); + } + return 0; +} diff --git a/training/test_perf_stats.m b/training/test_perf_stats.m new file mode 100644 index 0000000..cf7b073 --- /dev/null +++ b/training/test_perf_stats.m @@ -0,0 +1,233 @@ +// test_perf_stats.m — What does _ANEPerformanceStats expose? +// Probe class methods, properties, instantiate, pass to request, read back. +#import +#import +#import +#import +#import +#import + +static mach_timebase_info_data_t g_tb; +static double tb_ms(uint64_t t) { return (double)t * g_tb.numer / g_tb.denom / 1e6; } + +static void dump_class(const char *name) { + Class cls = NSClassFromString([NSString stringWithUTF8String:name]); + if (!cls) { printf(" %s: NOT FOUND\n", name); return; } + printf("\n=== %s ===\n", name); + + unsigned int count; + Method *methods = class_copyMethodList(object_getClass(cls), &count); + if (count) printf(" Class methods:\n"); + for (unsigned int i = 0; i < count; i++) { + SEL s = method_getName(methods[i]); + const char *enc = method_getTypeEncoding(methods[i]); + printf(" + %s [%s]\n", sel_getName(s), enc ? enc : "?"); + } + free(methods); + + methods = class_copyMethodList(cls, &count); + if (count) printf(" Instance methods:\n"); + for (unsigned int i = 0; i < count; i++) { + SEL s = method_getName(methods[i]); + const char *enc = method_getTypeEncoding(methods[i]); + printf(" - %s [%s]\n", sel_getName(s), enc ? enc : "?"); + } + free(methods); + + unsigned int pcount; + objc_property_t *props = class_copyPropertyList(cls, &pcount); + if (pcount) printf(" Properties:\n"); + for (unsigned int i = 0; i < pcount; i++) { + const char *pname = property_getName(props[i]); + const char *pattr = property_getAttributes(props[i]); + printf(" @property %s [%s]\n", pname, pattr ? pattr : "?"); + } + free(props); +} + +static IOSurfaceRef make_surface(size_t bytes) { + return IOSurfaceCreate((__bridge CFDictionaryRef)@{ + (id)kIOSurfaceWidth:@(bytes), (id)kIOSurfaceHeight:@1, + (id)kIOSurfaceBytesPerElement:@1, (id)kIOSurfaceBytesPerRow:@(bytes), + (id)kIOSurfaceAllocSize:@(bytes), (id)kIOSurfacePixelFormat:@0}); +} + +int main() { + @autoreleasepool { + setbuf(stdout, NULL); + mach_timebase_info(&g_tb); + dlopen("/System/Library/PrivateFrameworks/AppleNeuralEngine.framework/AppleNeuralEngine", RTLD_NOW); + + printf("=== ANE Performance Stats Probe ===\n"); + + dump_class("_ANEPerformanceStats"); + dump_class("_ANEPerfRequest"); + dump_class("ANEPerfRequest"); + dump_class("_ANEPerformanceCounters"); + dump_class("_ANEDeviceInfo"); + dump_class("_ANEModel"); + dump_class("_ANEInMemoryModel"); + dump_class("_ANERequest"); + dump_class("_ANEIOSurfaceObject"); + dump_class("_ANEInMemoryModelDescriptor"); + dump_class("_ANEClient"); + dump_class("_ANEVirtualClient"); + + // Try to instantiate _ANEPerformanceStats + printf("\n=== Instantiation Tests ===\n"); + Class perfClass = NSClassFromString(@"_ANEPerformanceStats"); + if (perfClass) { + @try { + id perfStats = [[perfClass alloc] init]; + printf("_ANEPerformanceStats alloc/init: %s\n", + perfStats ? [[perfStats description] UTF8String] : "nil"); + if (perfStats) { + unsigned int pcount; + objc_property_t *props = class_copyPropertyList(perfClass, &pcount); + for (unsigned int i = 0; i < pcount; i++) { + const char *pname = property_getName(props[i]); + @try { + id val = [perfStats valueForKey:[NSString stringWithUTF8String:pname]]; + printf(" %s = %s\n", pname, val ? [[val description] UTF8String] : "nil"); + } @catch (NSException *ex) { + printf(" %s = \n", pname, [[ex reason] UTF8String]); + } + } + free(props); + } + } @catch (NSException *ex) { + printf("Exception: %s\n", [[ex reason] UTF8String]); + } + } + + // Compile a working kernel and test perfStats in request + printf("\n=== Compile kernel and test perfStats in request ===\n"); + Class g_D = NSClassFromString(@"_ANEInMemoryModelDescriptor"); + Class g_I = NSClassFromString(@"_ANEInMemoryModel"); + Class g_AR = NSClassFromString(@"_ANERequest"); + Class g_AIO= NSClassFromString(@"_ANEIOSurfaceObject"); + + int CH = 64, SP = 32; + _Float16 *w = (_Float16*)calloc(CH*CH, sizeof(_Float16)); + for (int i = 0; i < CH; i++) w[i*CH+i] = (_Float16)1.0f; + int ws = CH*CH*2, tot = 128+ws; + uint8_t *blob = (uint8_t*)calloc(tot,1); + blob[0]=1; blob[4]=2; blob[64]=0xEF; blob[65]=0xBE; blob[66]=0xAD; blob[67]=0xDE; blob[68]=1; + *(uint32_t*)(blob+72)=ws; *(uint32_t*)(blob+80)=128; + memcpy(blob+128, w, ws); + NSData *wdata = [NSData dataWithBytesNoCopy:blob length:tot freeWhenDone:YES]; + free(w); + + NSString *mil = [NSString stringWithFormat: + @"program(1.3)\n" + "[buildInfo = dict({{\"coremlc-component-MIL\", \"3510.2.1\"}, " + "{\"coremlc-version\", \"3505.4.1\"}, {\"coremltools-component-milinternal\", \"\"}, " + "{\"coremltools-version\", \"9.0\"}})]\n" + "{\n" + " func main(tensor x) {\n" + " string pt = const()[name=string(\"pt\"), val=string(\"valid\")];\n" + " tensor st = const()[name=string(\"st\"), val=tensor([1,1])];\n" + " tensor pd = const()[name=string(\"pd\"), val=tensor([0,0,0,0])];\n" + " tensor dl = const()[name=string(\"dl\"), val=tensor([1,1])];\n" + " int32 gr = const()[name=string(\"gr\"), val=int32(1)];\n" + " string to16 = const()[name=string(\"to16\"), val=string(\"fp16\")];\n" + " tensor x16 = cast(dtype=to16,x=x)[name=string(\"cin\")];\n" + " tensor W = const()[name=string(\"W\"), " + "val=tensor(BLOBFILE(path=string(\"@model_path/weights/weight.bin\"), offset=uint64(64)))];\n" + " tensor y16 = conv(dilations=dl,groups=gr,pad=pd,pad_type=pt,strides=st,weight=W,x=x16)" + "[name=string(\"conv\")];\n" + " string to32 = const()[name=string(\"to32\"), val=string(\"fp32\")];\n" + " tensor y = cast(dtype=to32,x=y16)[name=string(\"cout\")];\n" + " } -> (y);\n" + "}\n", CH, SP, CH, SP, CH, CH, CH, CH, CH, SP, CH, SP]; + + NSData *md = [mil dataUsingEncoding:NSUTF8StringEncoding]; + id desc = ((id(*)(Class,SEL,id,id,id))objc_msgSend)(g_D, @selector(modelWithMILText:weights:optionsPlist:), + md, @{@"@model_path/weights/weight.bin": @{@"offset":@0, @"data":wdata}}, nil); + id mdl = ((id(*)(Class,SEL,id))objc_msgSend)(g_I, @selector(inMemoryModelWithDescriptor:), desc); + id hx = ((id(*)(id,SEL))objc_msgSend)(mdl, @selector(hexStringIdentifier)); + NSString *td = [NSTemporaryDirectory() stringByAppendingPathComponent:hx]; + [[NSFileManager defaultManager] createDirectoryAtPath:[td stringByAppendingPathComponent:@"weights"] + withIntermediateDirectories:YES attributes:nil error:nil]; + [md writeToFile:[td stringByAppendingPathComponent:@"model.mil"] atomically:YES]; + [wdata writeToFile:[td stringByAppendingPathComponent:@"weights/weight.bin"] atomically:YES]; + + NSError *e = nil; + ((BOOL(*)(id,SEL,unsigned int,id,NSError**))objc_msgSend)(mdl, @selector(compileWithQoS:options:error:), 21, @{}, &e); + ((BOOL(*)(id,SEL,unsigned int,id,NSError**))objc_msgSend)(mdl, @selector(loadWithQoS:options:error:), 21, @{}, &e); + + int ioBytes = CH * SP * 4; // fp32 + IOSurfaceRef ioIn = make_surface(ioBytes); + IOSurfaceRef ioOut = make_surface(ioBytes); + id wI = ((id(*)(Class,SEL,IOSurfaceRef))objc_msgSend)(g_AIO, @selector(objectWithIOSurface:), ioIn); + id wO = ((id(*)(Class,SEL,IOSurfaceRef))objc_msgSend)(g_AIO, @selector(objectWithIOSurface:), ioOut); + + // Try creating request WITH perfStats + if (perfClass) { + id perfStats = [[perfClass alloc] init]; + printf(" Creating request with perfStats=%s\n", perfStats ? "non-nil" : "nil"); + + id req = ((id(*)(Class,SEL,id,id,id,id,id,id,id))objc_msgSend)(g_AR, + @selector(requestWithInputs:inputIndices:outputs:outputIndices:weightsBuffer:perfStats:procedureIndex:), + @[wI], @[@0], @[wO], @[@0], nil, perfStats, @0); + printf(" Request: %s\n", req ? "created" : "nil"); + + if (req) { + IOSurfaceLock(ioIn, 0, NULL); + float *inp = (float*)IOSurfaceGetBaseAddress(ioIn); + for (int i = 0; i < CH*SP; i++) inp[i] = 1.0f; + IOSurfaceUnlock(ioIn, 0, NULL); + + BOOL ok = ((BOOL(*)(id,SEL,unsigned int,id,id,NSError**))objc_msgSend)( + mdl, @selector(evaluateWithQoS:options:request:error:), 21, @{}, req, &e); + printf(" Eval: %s\n", ok ? "OK" : [[e description] UTF8String]); + + if (ok && perfStats) { + printf("\n PerfStats after 1 eval:\n"); + unsigned int pcount; + objc_property_t *props = class_copyPropertyList(perfClass, &pcount); + for (unsigned int i = 0; i < pcount; i++) { + const char *pname = property_getName(props[i]); + @try { + id val = [perfStats valueForKey:[NSString stringWithUTF8String:pname]]; + printf(" %s = %s\n", pname, val ? [[val description] UTF8String] : "nil"); + } @catch (NSException *ex) { + printf(" %s = \n", pname); + } + } + free(props); + + printf("\n Running 100 evals...\n"); + uint64_t t0 = mach_absolute_time(); + for (int i = 0; i < 100; i++) { + ((BOOL(*)(id,SEL,unsigned int,id,id,NSError**))objc_msgSend)( + mdl, @selector(evaluateWithQoS:options:request:error:), 21, @{}, req, &e); + } + printf(" 100 evals in %.1fms (%.2fms/eval)\n", + tb_ms(mach_absolute_time()-t0), tb_ms(mach_absolute_time()-t0)/100.0); + + printf("\n PerfStats after 101 evals:\n"); + props = class_copyPropertyList(perfClass, &pcount); + for (unsigned int i = 0; i < pcount; i++) { + const char *pname = property_getName(props[i]); + @try { + id val = [perfStats valueForKey:[NSString stringWithUTF8String:pname]]; + printf(" %s = %s\n", pname, val ? [[val description] UTF8String] : "nil"); + } @catch (NSException *ex) { + printf(" %s = \n", pname); + } + } + free(props); + } + } + } else { + printf(" _ANEPerformanceStats class NOT FOUND\n"); + } + + // Cleanup + ((BOOL(*)(id,SEL,unsigned int,NSError**))objc_msgSend)(mdl, @selector(unloadWithQoS:error:), 21, &e); + [[NSFileManager defaultManager] removeItemAtPath:td error:nil]; + CFRelease(ioIn); CFRelease(ioOut); + } + return 0; +} diff --git a/training/test_qos_sweep.m b/training/test_qos_sweep.m new file mode 100644 index 0000000..2802c6b --- /dev/null +++ b/training/test_qos_sweep.m @@ -0,0 +1,157 @@ +// test_qos_sweep.m — Does QoS affect frequency/latency? +// Sweep QoS 0-63 on compile, load, eval of a working kernel. +#import +#import +#import +#import +#import +#import + +static mach_timebase_info_data_t g_tb; +static double tb_ms(uint64_t t) { return (double)t * g_tb.numer / g_tb.denom / 1e6; } + +static IOSurfaceRef make_surface(size_t bytes) { + return IOSurfaceCreate((__bridge CFDictionaryRef)@{ + (id)kIOSurfaceWidth:@(bytes), (id)kIOSurfaceHeight:@1, + (id)kIOSurfaceBytesPerElement:@1, (id)kIOSurfaceBytesPerRow:@(bytes), + (id)kIOSurfaceAllocSize:@(bytes), (id)kIOSurfacePixelFormat:@0}); +} + +int main() { + @autoreleasepool { + setbuf(stdout, NULL); + mach_timebase_info(&g_tb); + dlopen("/System/Library/PrivateFrameworks/AppleNeuralEngine.framework/AppleNeuralEngine", RTLD_NOW); + + Class g_D = NSClassFromString(@"_ANEInMemoryModelDescriptor"); + Class g_I = NSClassFromString(@"_ANEInMemoryModel"); + Class g_AR = NSClassFromString(@"_ANERequest"); + Class g_AIO= NSClassFromString(@"_ANEIOSurfaceObject"); + + // 256x256 conv, spatial=64 for measurable latency + int CH = 256, SP = 64; + int ws = CH*CH*2, tot = 128+ws; + uint8_t *blob = (uint8_t*)calloc(tot, 1); + blob[0]=1; blob[4]=2; blob[64]=0xEF; blob[65]=0xBE; blob[66]=0xAD; blob[67]=0xDE; blob[68]=1; + *(uint32_t*)(blob+72)=ws; *(uint32_t*)(blob+80)=128; + _Float16 *wp = (_Float16*)(blob+128); + for (int i = 0; i < CH*CH; i++) wp[i] = (_Float16)(0.01f * (i % 100 - 50)); + NSData *wdata = [NSData dataWithBytesNoCopy:blob length:tot freeWhenDone:YES]; + + NSString *mil = [NSString stringWithFormat: + @"program(1.3)\n" + "[buildInfo = dict({{\"coremlc-component-MIL\", \"3510.2.1\"}, " + "{\"coremlc-version\", \"3505.4.1\"}, {\"coremltools-component-milinternal\", \"\"}, " + "{\"coremltools-version\", \"9.0\"}})]\n" + "{\n" + " func main(tensor x) {\n" + " string pt = const()[name=string(\"pt\"), val=string(\"valid\")];\n" + " tensor st = const()[name=string(\"st\"), val=tensor([1,1])];\n" + " tensor pd = const()[name=string(\"pd\"), val=tensor([0,0,0,0])];\n" + " tensor dl = const()[name=string(\"dl\"), val=tensor([1,1])];\n" + " int32 gr = const()[name=string(\"gr\"), val=int32(1)];\n" + " string to16 = const()[name=string(\"to16\"), val=string(\"fp16\")];\n" + " tensor x16 = cast(dtype=to16,x=x)[name=string(\"cin\")];\n" + " tensor W = const()[name=string(\"W\"), " + "val=tensor(BLOBFILE(path=string(\"@model_path/weights/weight.bin\"), offset=uint64(64)))];\n" + " tensor y16 = conv(dilations=dl,groups=gr,pad=pd,pad_type=pt,strides=st,weight=W,x=x16)" + "[name=string(\"conv\")];\n" + " string to32 = const()[name=string(\"to32\"), val=string(\"fp32\")];\n" + " tensor y = cast(dtype=to32,x=y16)[name=string(\"cout\")];\n" + " } -> (y);\n" + "}\n", CH, SP, CH, SP, CH, CH, CH, CH, CH, SP, CH, SP]; + + NSDictionary *weights = @{@"@model_path/weights/weight.bin": @{@"offset":@0, @"data":wdata}}; + NSData *milData = [mil dataUsingEncoding:NSUTF8StringEncoding]; + NSFileManager *fm = [NSFileManager defaultManager]; + + printf("=== QoS Sweep: compile/load/eval with varying QoS ===\n"); + printf("Kernel: %dx%d conv, spatial=%d (%.1f MFLOPS)\n", CH, CH, SP, 2.0*CH*CH*SP/1e6); + printf("%4s %10s %10s %10s %10s %s\n", "QoS", "Compile", "Load", "Eval(1)", "Eval(avg10)", "Status"); + + unsigned int qos_values[] = {0, 1, 5, 10, 15, 17, 19, 21, 25, 31, 33, 40, 47, 50, 55, 60, 63}; + int n_qos = sizeof(qos_values)/sizeof(qos_values[0]); + + for (int qi = 0; qi < n_qos; qi++) { + unsigned int qos = qos_values[qi]; + NSError *e = nil; + + // Make unique weights per iteration so hex differs + _Float16 *wq = (_Float16*)(blob+128); + wq[0] = (_Float16)(0.001f * qi); + NSData *wdata_q = [NSData dataWithBytes:blob length:tot]; + NSDictionary *weights_q = @{@"@model_path/weights/weight.bin": @{@"offset":@0, @"data":wdata_q}}; + + id desc = ((id(*)(Class,SEL,id,id,id))objc_msgSend)(g_D, @selector(modelWithMILText:weights:optionsPlist:), + milData, weights_q, nil); + id mdl = ((id(*)(Class,SEL,id))objc_msgSend)(g_I, @selector(inMemoryModelWithDescriptor:), desc); + id hx = ((id(*)(id,SEL))objc_msgSend)(mdl, @selector(hexStringIdentifier)); + NSString *td = [NSTemporaryDirectory() stringByAppendingPathComponent:hx]; + [fm createDirectoryAtPath:[td stringByAppendingPathComponent:@"weights"] + withIntermediateDirectories:YES attributes:nil error:nil]; + [milData writeToFile:[td stringByAppendingPathComponent:@"model.mil"] atomically:YES]; + [wdata_q writeToFile:[td stringByAppendingPathComponent:@"weights/weight.bin"] atomically:YES]; + + uint64_t t0 = mach_absolute_time(); + BOOL cok = ((BOOL(*)(id,SEL,unsigned int,id,NSError**))objc_msgSend)( + mdl, @selector(compileWithQoS:options:error:), qos, @{}, &e); + double cms = tb_ms(mach_absolute_time() - t0); + + if (!cok) { + printf("%4u %10s %10s %10s %10s COMPILE_FAIL\n", qos, "-", "-", "-", "-"); + [fm removeItemAtPath:td error:nil]; + continue; + } + + t0 = mach_absolute_time(); + BOOL lok = ((BOOL(*)(id,SEL,unsigned int,id,NSError**))objc_msgSend)( + mdl, @selector(loadWithQoS:options:error:), qos, @{}, &e); + double lms = tb_ms(mach_absolute_time() - t0); + + if (!lok) { + printf("%4u %8.1fms %10s %10s %10s LOAD_FAIL\n", qos, cms, "-", "-", "-"); + ((BOOL(*)(id,SEL,unsigned int,NSError**))objc_msgSend)(mdl, @selector(unloadWithQoS:error:), 21, &e); + [fm removeItemAtPath:td error:nil]; + continue; + } + + int ioBytes = CH * SP * 4; + IOSurfaceRef ioIn = make_surface(ioBytes); + IOSurfaceRef ioOut = make_surface(ioBytes); + id wI = ((id(*)(Class,SEL,IOSurfaceRef))objc_msgSend)(g_AIO, @selector(objectWithIOSurface:), ioIn); + id wO = ((id(*)(Class,SEL,IOSurfaceRef))objc_msgSend)(g_AIO, @selector(objectWithIOSurface:), ioOut); + id req = ((id(*)(Class,SEL,id,id,id,id,id,id,id))objc_msgSend)(g_AR, + @selector(requestWithInputs:inputIndices:outputs:outputIndices:weightsBuffer:perfStats:procedureIndex:), + @[wI], @[@0], @[wO], @[@0], nil, nil, @0); + + IOSurfaceLock(ioIn, 0, NULL); + float *inp = (float*)IOSurfaceGetBaseAddress(ioIn); + for (int i = 0; i < CH*SP; i++) inp[i] = 0.5f; + IOSurfaceUnlock(ioIn, 0, NULL); + + t0 = mach_absolute_time(); + BOOL eok = ((BOOL(*)(id,SEL,unsigned int,id,id,NSError**))objc_msgSend)( + mdl, @selector(evaluateWithQoS:options:request:error:), qos, @{}, req, &e); + double ems1 = tb_ms(mach_absolute_time() - t0); + + if (!eok) { + printf("%4u %8.1fms %8.1fms %10s %10s EVAL_FAIL\n", qos, cms, lms, "-", "-"); + } else { + t0 = mach_absolute_time(); + for (int i = 0; i < 10; i++) { + ((BOOL(*)(id,SEL,unsigned int,id,id,NSError**))objc_msgSend)( + mdl, @selector(evaluateWithQoS:options:request:error:), qos, @{}, req, &e); + } + double ems_avg = tb_ms(mach_absolute_time() - t0) / 10.0; + printf("%4u %8.1fms %8.1fms %8.2fms %8.2fms OK\n", qos, cms, lms, ems1, ems_avg); + } + + ((BOOL(*)(id,SEL,unsigned int,NSError**))objc_msgSend)(mdl, @selector(unloadWithQoS:error:), 21, &e); + CFRelease(ioIn); CFRelease(ioOut); + [fm removeItemAtPath:td error:nil]; + } + + printf("\nDone.\n"); + } + return 0; +} diff --git a/training/test_weight_reload.m b/training/test_weight_reload.m new file mode 100644 index 0000000..a248005 --- /dev/null +++ b/training/test_weight_reload.m @@ -0,0 +1,253 @@ +// test_weight_reload.m — Can we skip recompilation by rewriting weight blobs on disk? +// Compile a conv kernel with weights A, eval, verify output. +// Overwrite weights/weight.bin in tmpDir with weights B. +// unloadWithQoS: then loadWithQoS: (no recompile). +// Eval again — if output matches B @ x, compilation bottleneck is eliminated. +#import +#import +#import +#import +#import +#import +#include + +static mach_timebase_info_data_t g_tb; +static double tb_ms(uint64_t t) { return (double)t * g_tb.numer / g_tb.denom / 1e6; } + +static IOSurfaceRef make_surface(size_t bytes) { + return IOSurfaceCreate((__bridge CFDictionaryRef)@{ + (id)kIOSurfaceWidth:@(bytes), (id)kIOSurfaceHeight:@1, + (id)kIOSurfaceBytesPerElement:@1, (id)kIOSurfaceBytesPerRow:@(bytes), + (id)kIOSurfaceAllocSize:@(bytes), (id)kIOSurfacePixelFormat:@0}); +} + +// Build weight blob matching inmem_peak format (single chunk) +static NSData *build_weight_blob(_Float16 *w, int rows, int cols) { + int ws = rows * cols * 2; + int tot = 128 + ws; + uint8_t *b = (uint8_t*)calloc(tot, 1); + b[0] = 1; b[4] = 2; + b[64] = 0xEF; b[65] = 0xBE; b[66] = 0xAD; b[67] = 0xDE; b[68] = 1; + *(uint32_t*)(b+72) = ws; + *(uint32_t*)(b+80) = 128; + memcpy(b + 128, w, ws); + return [NSData dataWithBytesNoCopy:b length:tot freeWhenDone:YES]; +} + +// Generate MIL for a simple conv: fp32 in → cast fp16 → conv → cast fp32 out +static NSString *gen_mil(int ch, int sp) { + return [NSString stringWithFormat: + @"program(1.3)\n" + "[buildInfo = dict({{\"coremlc-component-MIL\", \"3510.2.1\"}, " + "{\"coremlc-version\", \"3505.4.1\"}, {\"coremltools-component-milinternal\", \"\"}, " + "{\"coremltools-version\", \"9.0\"}})]\n" + "{\n" + " func main(tensor x) {\n" + " string pt = const()[name=string(\"pt\"), val=string(\"valid\")];\n" + " tensor st = const()[name=string(\"st\"), val=tensor([1,1])];\n" + " tensor pd = const()[name=string(\"pd\"), val=tensor([0,0,0,0])];\n" + " tensor dl = const()[name=string(\"dl\"), val=tensor([1,1])];\n" + " int32 gr = const()[name=string(\"gr\"), val=int32(1)];\n" + " string to16 = const()[name=string(\"to16\"), val=string(\"fp16\")];\n" + " tensor x16 = cast(dtype=to16,x=x)[name=string(\"cin\")];\n" + " tensor W = const()[name=string(\"W\"), " + "val=tensor(BLOBFILE(path=string(\"@model_path/weights/weight.bin\"), offset=uint64(64)))];\n" + " tensor y16 = conv(dilations=dl,groups=gr,pad=pd,pad_type=pt,strides=st,weight=W,x=x16)" + "[name=string(\"conv\")];\n" + " string to32 = const()[name=string(\"to32\"), val=string(\"fp32\")];\n" + " tensor y = cast(dtype=to32,x=y16)[name=string(\"cout\")];\n" + " } -> (y);\n" + "}\n", ch, sp, ch, sp, ch, ch, ch, ch, ch, sp, ch, sp]; +} + +int main() { + @autoreleasepool { + setbuf(stdout, NULL); + mach_timebase_info(&g_tb); + dlopen("/System/Library/PrivateFrameworks/AppleNeuralEngine.framework/AppleNeuralEngine", RTLD_NOW); + + Class g_D = NSClassFromString(@"_ANEInMemoryModelDescriptor"); + Class g_I = NSClassFromString(@"_ANEInMemoryModel"); + Class g_AR = NSClassFromString(@"_ANERequest"); + Class g_AIO= NSClassFromString(@"_ANEIOSurfaceObject"); + + if (!g_D || !g_I || !g_AR || !g_AIO) { + printf("FAIL: ANE classes not found\n"); + return 1; + } + + // Use 64-channel conv, spatial=32 (known to work on ANE) + int CH = 64, SP = 32; + + // Weight set A: scaled identity (1.0 on diagonal) + _Float16 *weightsA = (_Float16*)calloc(CH*CH, sizeof(_Float16)); + for (int i = 0; i < CH; i++) weightsA[i*CH+i] = (_Float16)1.0f; + + // Weight set B: 3x identity + _Float16 *weightsB = (_Float16*)calloc(CH*CH, sizeof(_Float16)); + for (int i = 0; i < CH; i++) weightsB[i*CH+i] = (_Float16)3.0f; + + NSData *wdataA = build_weight_blob(weightsA, CH, CH); + NSString *mil = gen_mil(CH, SP); + NSDictionary *weights = @{ + @"@model_path/weights/weight.bin": @{@"offset": @0, @"data": wdataA} + }; + NSData *milData = [mil dataUsingEncoding:NSUTF8StringEncoding]; + + // === Compile with weights A === + printf("=== Step 1: Compile with weights A (identity) ===\n"); + printf(" Kernel: %dx%d conv, spatial=%d\n", CH, CH, SP); + uint64_t t0 = mach_absolute_time(); + id desc = ((id(*)(Class,SEL,id,id,id))objc_msgSend)(g_D, @selector(modelWithMILText:weights:optionsPlist:), milData, weights, nil); + if (!desc) { printf("FAIL: desc=NULL\n"); return 1; } + id mdl = ((id(*)(Class,SEL,id))objc_msgSend)(g_I, @selector(inMemoryModelWithDescriptor:), desc); + id hx = ((id(*)(id,SEL))objc_msgSend)(mdl, @selector(hexStringIdentifier)); + NSString *td = [NSTemporaryDirectory() stringByAppendingPathComponent:hx]; + NSFileManager *fm = [NSFileManager defaultManager]; + [fm createDirectoryAtPath:[td stringByAppendingPathComponent:@"weights"] withIntermediateDirectories:YES attributes:nil error:nil]; + [milData writeToFile:[td stringByAppendingPathComponent:@"model.mil"] atomically:YES]; + [wdataA writeToFile:[td stringByAppendingPathComponent:@"weights/weight.bin"] atomically:YES]; + + NSError *e = nil; + BOOL ok = ((BOOL(*)(id,SEL,unsigned int,id,NSError**))objc_msgSend)(mdl, @selector(compileWithQoS:options:error:), 21, @{}, &e); + if (!ok) { printf("FAIL: compile: %s\n", [[e description] UTF8String]); return 1; } + ok = ((BOOL(*)(id,SEL,unsigned int,id,NSError**))objc_msgSend)(mdl, @selector(loadWithQoS:options:error:), 21, @{}, &e); + if (!ok) { printf("FAIL: load: %s\n", [[e description] UTF8String]); return 1; } + double compile_ms = tb_ms(mach_absolute_time() - t0); + printf(" Compile+load: %.1fms\n", compile_ms); + printf(" tmpDir: %s\n", [td UTF8String]); + + // Build request and IOSurfaces (fp32 I/O) + int inBytes = CH * SP * 4; // fp32 + int outBytes = CH * SP * 4; + IOSurfaceRef ioIn = make_surface(inBytes); + IOSurfaceRef ioOut = make_surface(outBytes); + id wI = ((id(*)(Class,SEL,IOSurfaceRef))objc_msgSend)(g_AIO, @selector(objectWithIOSurface:), ioIn); + id wO = ((id(*)(Class,SEL,IOSurfaceRef))objc_msgSend)(g_AIO, @selector(objectWithIOSurface:), ioOut); + id req = ((id(*)(Class,SEL,id,id,id,id,id,id,id))objc_msgSend)(g_AR, + @selector(requestWithInputs:inputIndices:outputs:outputIndices:weightsBuffer:perfStats:procedureIndex:), + @[wI], @[@0], @[wO], @[@0], nil, nil, @0); + + // Write input: channel c, spatial s = (c*SP + s + 1) * 0.01 + IOSurfaceLock(ioIn, 0, NULL); + float *inp = (float*)IOSurfaceGetBaseAddress(ioIn); + for (int c = 0; c < CH; c++) + for (int s = 0; s < SP; s++) + inp[c*SP+s] = (float)(c*SP + s + 1) * 0.01f; + IOSurfaceUnlock(ioIn, 0, NULL); + + // Eval with weights A + printf("\n=== Step 2: Eval with weights A ===\n"); + ok = ((BOOL(*)(id,SEL,unsigned int,id,id,NSError**))objc_msgSend)(mdl, @selector(evaluateWithQoS:options:request:error:), 21, @{}, req, &e); + if (!ok) { printf("FAIL: eval: %s\n", e ? [[e description] UTF8String] : "?"); return 1; } + + IOSurfaceLock(ioOut, kIOSurfaceLockReadOnly, NULL); + float *outA = (float*)IOSurfaceGetBaseAddress(ioOut); + printf(" Output A[0..3]: [%.4f, %.4f, %.4f, %.4f]\n", outA[0], outA[1], outA[2], outA[3]); + printf(" Output A[%d..%d]: [%.4f, %.4f, %.4f, %.4f]\n", CH*SP-4, CH*SP-1, + outA[CH*SP-4], outA[CH*SP-3], outA[CH*SP-2], outA[CH*SP-1]); + // Save copy + float *outA_copy = (float*)malloc(outBytes); + memcpy(outA_copy, outA, outBytes); + IOSurfaceUnlock(ioOut, kIOSurfaceLockReadOnly, NULL); + + // === Step 3: Overwrite weight file with B, unload+load === + printf("\n=== Step 3: Overwrite weight.bin with B (3x identity), unload+load ===\n"); + NSData *wdataB = build_weight_blob(weightsB, CH, CH); + NSString *weightPath = [td stringByAppendingPathComponent:@"weights/weight.bin"]; + [wdataB writeToFile:weightPath atomically:YES]; + printf(" Wrote new weight.bin\n"); + + // Unload + t0 = mach_absolute_time(); + ok = ((BOOL(*)(id,SEL,unsigned int,NSError**))objc_msgSend)(mdl, @selector(unloadWithQoS:error:), 21, &e); + double unload_ms = tb_ms(mach_absolute_time() - t0); + printf(" Unload: %s (%.2fms)\n", ok ? "OK" : "FAIL", unload_ms); + + // Reload (no compile!) + t0 = mach_absolute_time(); + ok = ((BOOL(*)(id,SEL,unsigned int,id,NSError**))objc_msgSend)(mdl, @selector(loadWithQoS:options:error:), 21, @{}, &e); + double reload_ms = tb_ms(mach_absolute_time() - t0); + printf(" Load (no recompile): %s (%.2fms)\n", ok ? "OK" : [[e description] UTF8String], reload_ms); + + if (!ok) { + printf("\n*** Load-after-overwrite FAILED — trying recompile+load ***\n"); + t0 = mach_absolute_time(); + ok = ((BOOL(*)(id,SEL,unsigned int,id,NSError**))objc_msgSend)(mdl, @selector(compileWithQoS:options:error:), 21, @{}, &e); + printf(" Re-compile: %s (%.2fms)\n", ok ? "OK" : "FAIL", tb_ms(mach_absolute_time() - t0)); + t0 = mach_absolute_time(); + ok = ((BOOL(*)(id,SEL,unsigned int,id,NSError**))objc_msgSend)(mdl, @selector(loadWithQoS:options:error:), 21, @{}, &e); + printf(" Re-load: %s (%.2fms)\n", ok ? "OK" : "FAIL", tb_ms(mach_absolute_time() - t0)); + } + + // Build new request (re-use same surfaces) + wI = ((id(*)(Class,SEL,IOSurfaceRef))objc_msgSend)(g_AIO, @selector(objectWithIOSurface:), ioIn); + wO = ((id(*)(Class,SEL,IOSurfaceRef))objc_msgSend)(g_AIO, @selector(objectWithIOSurface:), ioOut); + req = ((id(*)(Class,SEL,id,id,id,id,id,id,id))objc_msgSend)(g_AR, + @selector(requestWithInputs:inputIndices:outputs:outputIndices:weightsBuffer:perfStats:procedureIndex:), + @[wI], @[@0], @[wO], @[@0], nil, nil, @0); + + // Re-write same input + IOSurfaceLock(ioIn, 0, NULL); + inp = (float*)IOSurfaceGetBaseAddress(ioIn); + for (int c = 0; c < CH; c++) + for (int s = 0; s < SP; s++) + inp[c*SP+s] = (float)(c*SP + s + 1) * 0.01f; + IOSurfaceUnlock(ioIn, 0, NULL); + + // Eval with (possibly reloaded) weights B + printf("\n=== Step 4: Eval after reload ===\n"); + ok = ((BOOL(*)(id,SEL,unsigned int,id,id,NSError**))objc_msgSend)(mdl, @selector(evaluateWithQoS:options:request:error:), 21, @{}, req, &e); + if (!ok) { printf("FAIL: eval after reload: %s\n", e ? [[e description] UTF8String] : "?"); return 1; } + + IOSurfaceLock(ioOut, kIOSurfaceLockReadOnly, NULL); + float *outB = (float*)IOSurfaceGetBaseAddress(ioOut); + printf(" Output B[0..3]: [%.4f, %.4f, %.4f, %.4f]\n", outB[0], outB[1], outB[2], outB[3]); + printf(" Output B[%d..%d]: [%.4f, %.4f, %.4f, %.4f]\n", CH*SP-4, CH*SP-1, + outB[CH*SP-4], outB[CH*SP-3], outB[CH*SP-2], outB[CH*SP-1]); + + // Check: did the output change? + bool changed = false; + float max_diff = 0; + for (int i = 0; i < CH*SP; i++) { + float d = fabsf(outB[i] - outA_copy[i]); + if (d > max_diff) max_diff = d; + if (d > 0.001f) changed = true; + } + // Expected: output B should be 3x output A + bool correct_3x = true; + float max_3x_err = 0; + for (int i = 0; i < CH*SP; i++) { + float expected = outA_copy[i] * 3.0f; + float err = fabsf(outB[i] - expected); + if (err > max_3x_err) max_3x_err = err; + if (err > 0.1f) correct_3x = false; + } + IOSurfaceUnlock(ioOut, kIOSurfaceLockReadOnly, NULL); + + printf("\n=== RESULT ===\n"); + printf(" Max A-B diff: %.6f\n", max_diff); + printf(" Max 3x error: %.6f\n", max_3x_err); + printf(" Compile+load: %.1fms | Unload: %.1fms | Reload: %.1fms\n", compile_ms, unload_ms, reload_ms); + + if (changed && correct_3x) { + printf("\nSUCCESS: Weight reload works! Output matches 3x identity.\n"); + printf(" Speedup: compile=%.1fms vs reload=%.1fms (%.1fx faster)\n", + compile_ms, unload_ms + reload_ms, compile_ms / (unload_ms + reload_ms)); + printf(">>> Compilation bottleneck can be eliminated <<<\n"); + } else if (changed && !correct_3x) { + printf("\nPARTIAL: Output changed but doesn't match expected 3x.\n"); + } else { + printf("\nFAIL: Output did NOT change. Weight reload does not work.\n"); + printf(" ANE cached the compiled model — weights baked at compile time.\n"); + printf(">>> Need alternative: weightsBuffer IOSurface or async recompile <<<\n"); + } + + // Cleanup + ((BOOL(*)(id,SEL,unsigned int,NSError**))objc_msgSend)(mdl, @selector(unloadWithQoS:error:), 21, &e); + [fm removeItemAtPath:td error:nil]; + CFRelease(ioIn); CFRelease(ioOut); + free(outA_copy); free(weightsA); free(weightsB); + } + return 0; +} diff --git a/training/train_large.m b/training/train_large.m index ee7e860..e58ce08 100644 --- a/training/train_large.m +++ b/training/train_large.m @@ -581,6 +581,16 @@ int main(int argc, char *argv[]) { steps_batch++; if (step % 10 == 0 || step == start_step) printf("step %-4d loss=%.4f\n", step, loss); + + // JSON telemetry to stderr + double step_ane = t_ane/steps_batch, step_io = t_io/steps_batch; + double step_cls = t_cls/steps_batch, step_elem = t_elem/steps_batch; + double step_rms = t_rms/steps_batch, step_cbw = t_cblas_wait/steps_batch; + fprintf(stderr, "{\"type\":\"step\",\"step\":%d,\"loss\":%.6f," + "\"t_ane\":%.3f,\"t_io\":%.3f,\"t_cls\":%.3f," + "\"t_elem\":%.3f,\"t_rms\":%.3f,\"t_cblas_wait\":%.3f," + "\"compiles\":%d}\n", + step, loss, step_ane, step_io, step_cls, step_elem, step_rms, step_cbw, g_compile_count); } double tms = tb_ms(mach_absolute_time() - tt); total_train_ms += tms; @@ -622,6 +632,19 @@ int main(int argc, char *argv[]) { printf(" ane=%.1f io=%.1f cls=%.1f elem=%.1f rms=%.1f cblas_wait=%.1f ms/step\n", t_ane/steps_batch, t_io/steps_batch, t_cls/steps_batch, t_elem/steps_batch, t_rms/steps_batch, t_cblas_wait/steps_batch); + + // JSON batch telemetry to stderr + { + double bf = NLAYERS * (4.0*2*DIM*DIM*SEQ + 2.0*2*DIM*HIDDEN*SEQ + 2.0*HIDDEN*DIM*SEQ); + double bs = NLAYERS * 2.0*HEADS*5*SEQ*SEQ*HD; + double ane_f_batch = (bf*2 + bs) * steps_batch; + double ane_tflops = ane_f_batch / (tms * 1e9); + fprintf(stderr, "{\"type\":\"batch\",\"batch\":%d,\"compile_ms\":%.1f," + "\"train_ms\":%.1f,\"ms_per_step\":%.1f}\n", + steps_batch, cms, tms, tms/steps_batch); + fprintf(stderr, "{\"type\":\"perf\",\"ane_tflops\":%.3f,\"ane_util_pct\":%.2f}\n", + ane_tflops, 100.0*ane_tflops/15.8); + } } // Efficiency report