Apple Silicon SoC
├── CPU cores (P + E cores)
├── GPU cores
├── Neural Engine (NPU)
└── Unified DRAM — single address space, no PCIe copy

# CPU and chip info
sysctl -n machdep.cpu.brand_string
sysctl hw.physicalcpu hw.logicalcpu
sysctl hw.memsize

# ARM64 features (keys vary by chip — grep if specific FEAT_* is missing)
sysctl -a hw.optional.arm 2>/dev/null | grep -iE 'sve|bf16|mte'

# Cache line size
sysctl hw.cachelinesize

# Page size (16KB on macOS Apple Silicon)
sysctl hw.pagesize    # 16384
getconf PAGESIZE

// Align hot buffers to page size
size_t page = sysconf(_SC_PAGESIZE);  // 16384
void *buf = aligned_alloc(page, size);

// mmap alignment must be page-aligned
mmap(NULL, size, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0);

// Accelerate framework — uses AMX internally for matrix ops
#include <Accelerate/Accelerate.h>

void matrix_multiply(const float *A, const float *B, float *C,
                     int M, int N, int K) {
    cblas_sgemm(CblasRowMajor, CblasNoTrans, CblasNoTrans,
                M, N, K, 1.0f, A, K, B, N, 0.0f, C, N);
}

# Link Accelerate (default on macOS)
clang -framework Accelerate -o gemm gemm.c -lcblas

// Objective-C / Swift — GPU compute via MPS
#import <Metal/Metal.h>
#import <MetalPerformanceShaders/MetalPerformanceShaders.h>

id<MTLDevice> device = MTLCreateSystemDefaultDevice();
id<MTLCommandQueue> queue = [device newCommandQueue];

MPSMatrixMultiplication *gemm = [[MPSMatrixMultiplication alloc]
    initWithDevice:device transposeLeft:NO transposeRight:NO
    resultRows:M columns:N interiorColumns:K alpha:1.0 beta:0.0];

# Command-line Instruments (xctrace)
xctrace record --template 'Time Profiler' --launch -- /path/to/app
xctrace record --template 'Allocations' --launch -- /path/to/app
xctrace record --template 'Leaks' --launch -- /path/to/app
xctrace export --input trace.trace --toc

# Process memory map
vmmap <pid>

# Heap analysis
heap <pid>
heap <pid> -addresses all  # all allocations

# Leak detection
leaks <pid>
leaks --list <pid>

# Sample call stacks
sample <pid> 5 -file sample.txt

# Check if process runs under Rosetta
sysctl sysctl.proc_translated   # 1 = translated x86

# Force arch
arch -arm64 ./native_binary
arch -x86_64 ./x86_binary

# Universal binary info
lipo -info myapp
file myapp

sysctl hw.optional.arm.FEAT_MTE  # when available

# Native optimized build
clang -arch arm64 -O3 -mcpu=apple-m1 -o app app.c
# Use -mcpu matching target: apple-m1, apple-m2, apple-m3, apple-m4

# P/E core awareness — dispatch heavy work to performance cores
# pthread_set_qos_class_self_np(QOS_CLASS_USER_INITIATED, 0);