iobuf: add RISC-V Vector (RVV) optimized memcpy for cp()

[Felix-Gong]

Description

Add a RVV-accelerated cp() path for RISC-V 64-bit systems with the Vector (RVV) extension.

The cp() function is the internal memcpy wrapper used throughout IOBuf for all buffer copy operations — optimizing it benefits append, cut, push_back, and all other IOBuf data movement.

Implementation

• Uses VL-agnostic RVV intrinsics with LMUL=8 (e8m8) for maximum vector width
• Falls back to memcpy for < 64 bytes (RVV overhead threshold)
• Uses __has_include(<riscv_vector.h>) for broad compiler compatibility
• Guarded by __riscv and __riscv_vector

Verification

• Compiled on RISC-V 64-bit (SG2044, rv64gcv) with Clang 17
• Verified RVV instructions generated: vsetvli, vle8.v, vse8.v in the object file
• libbrpc.a built successfully
• Non-RVV platforms and compilers without riscv_vector.h fall back to memcpy

[Felix-Gong]

Benchmark Results — SG2044 (rv64gcv, VLEN=128, Clang 17, -O2 -march=rv64gcv)

Measured on SOPHGO SG2044 RISC-V 64-bit hardware with PR #3375 changes compiled using Clang 17 + glibc 2.38. Each data point is the median of 5 runs with 64-byte aligned buffers.

Size	memcpy (glibc)	cp_rvv (RVV e8m8)	Speedup
64 B	2.92 GB/s	19.06 GB/s	6.5x
128 B	5.13 GB/s	21.08 GB/s	4.1x
256 B	7.90 GB/s	18.60 GB/s	2.4x
512 B	4.62 GB/s	15.79 GB/s	3.4x
1024 B	8.75 GB/s	10.83 GB/s	1.2x
4 KB	5.49 GB/s	5.92 GB/s	1.1x
16 KB	4.01 GB/s	4.01 GB/s	1.0x
64 KB+	~2.7-3.2 GB/s	~2.7-3.2 GB/s	~1.0x

Analysis

• Small buffers (64-1024 B, L1/L2 cache resident): RVV achieves 1.2x–6.5x speedup by issuing 128-bit vector load/store operations (LMUL=8 processes 128 bytes per iteration on VLEN=128 hardware). This is the sweet spot for IOBuf operations — typical append/cut/push_back involve small block copies.
• Medium buffers (4-64 KB, L3 cache): Both implementations converge to L3 bandwidth limits.
• Large buffers (>64 KB, DRAM): Both are memory-bandwidth bound; no regression.

Compiler Compatibility

The implementation uses __has_include(<riscv_vector.h>) to gracefully fall back to memcpy when the RVV intrinsic header is unavailable (e.g., GCC <= 13 without bundled riscv_vector.h). Clang 17+ ships riscv_vector.h by default.