Add RVV vectorized FP32 kernel to CPU Adam (#8817)
## Description
On riscv64 hosts with the RISC-V Vector (RVV 1.0) extension, DeepSpeed
CPU Adam currently falls back to the scalar `Step_1` tail because
neither the op builder's `simd_width()` nor the kernel dispatch
recognizes the V extension. This PR adds an RVV FP32 tier to CPU Adam,
mirroring the existing SVE backend, so RVV-capable CPUs get a ~4x
single-core speedup on the optimizer step.
- `csrc/includes/rvv.h`: an RVV 1.0 FP32 Adam kernel. The hot loop
processes one `m4` block per iteration — at VLEN=128 each block covers a
full 64-byte cache line per stream — and runs entirely at the
loop-invariant vlmax; a single `vsetvl` truncates the trailing block, so
any tensor length is covered with no scalar tail. The arithmetic order
matches the scalar and SVE kernels, keeping every tier within the
existing test tolerance. Scalar hyperparameters ride the vf-form
intrinsics, so only epsilon occupies a vector register.
- `cpu_adam.h` / `cpu_adam_impl.cpp`: `Step_RVV` dispatch alongside
`Step_AVX` and `Step_SVE`; only the FP32 param/FP32 state pair is
vectorized, other dtype pairs keep the scalar path (same policy as SVE).
- `op_builder/builder.py`: detect the V extension from the
`/proc/cpuinfo` isa line with a per-character token test (a substring
test misreads `rv64imafdcvh` as having V), build with `-D__RVV__
-march=rv64gcv` on riscv64, and normalize py-cpuinfo's `RISCV_64` arch
string so the riscv64 branch actually fires. Hosts without V are
unaffected (`rv64gc`).
- `docs/_tutorials/zero-offload.md`: document the automatic RVV tier.
## Validation
**Hardware/software:** SG2044 60-core RISC-V server, VLEN=128, gcc-14.3,
torch 2.15 CPU-only build.
**Correctness:** `pytest tests/unit/ops/adam/test_cpu_adam.py` → **48
passed, 1 skipped, 0 failed**. The suite compares CPU Adam against the
PyTorch fused-Adam reference across fp32/fp16 and multiple sizes; the
fp16 equality tests pass (this tier keeps non-fp32 dtype pairs on the
scalar path).
Key log:
```
48 passed, 1 skipped, 3 warnings in 1283.18s (0:21:23)
```
**Performance** (single core, `OMP_NUM_THREADS=1 taskset -c 0`, 100
steps):
| Size | Scalar baseline | RVV (this PR) | Speedup |
|------|-----------------|---------------|---------|
| 1B params | 13.07 s/step | 3.15 s/step | ~4.2x |
| 2B params | 26.13 s/step | 6.31 s/step | ~4.1x |
Key log:
```
Elapsed Time is 3.1488167250156405
Elapsed Time is 6.313579152822495
```
---------
Signed-off-by: 张健10355098 <zhang.jian60@zte.com.cn>
