ub->gm传递l2_cache_ctl参数

[and0d0]

• 高层 pto.mte_ub_gm 增加了 l2_cache_ctl参数
• 底层 pto.copy_ubuf_to_gm 里原来的 reserved 语义改成 l2_cache_ctl
• 更新相关 VPTO emitter/接口处的字段命名和语义，使它表示 reserved -> L2 cache policy

[reedhecre]

Codex Review

该评论由 review 机器人自动更新。

• PR: ub->gm传递l2_cache_ctl参数 #920 ub->gm传递l2_cache_ctl参数
• Author: and0d0
• Base/Head: main / 489-ub-gm-l2-cache
• Head SHA: 9663c28a0b00
• Trigger: 检测到新的 open PR
• Generated At: 2026-07-09T02:40:47Z
• Status: failed at codex-review (exit=1)

Summary

Review failed at stage codex-review: exit=1

Findings

未生成结构化 findings，因为 review 过程提前失败。

Log Tail

 .../cases/micro-op/simt/simt-store-tid/kernel.pto  |  4 +-
 .../cases/micro-op/unary-vector/vabs/kernel.pto    | 32 ++++----
 .../cases/micro-op/unary-vector/vexp/kernel.pto    | 20 ++---
 .../cases/micro-op/unary-vector/vln/kernel.pto     | 24 +++---
 .../cases/micro-op/unary-vector/vnot/kernel.pto    |  4 +-
 .../cases/micro-op/unary-vector/vrelu/kernel.pto   |  4 +-
 .../cases/micro-op/vec-scalar/vaddcs/kernel.pto    | 32 ++++----
 .../cases/micro-op/vec-scalar/vadds/kernel.pto     | 36 ++++-----
 .../cases/micro-op/vec-scalar/vmaxs/kernel.pto     | 24 +++---
 .../cases/micro-op/vec-scalar/vshls/kernel.pto     | 16 ++--
 .../cbuf-ubuf-roundtrip-mixed/kernel.pto           |  4 +-
 .../dma-copy-rearrange/kernel.pto                  | 16 ++--
 .../vector-load-store/vldas-vldus/kernel.pto       | 40 +++++-----
 .../vector-load-store/vlds-brc-b16/kernel.pto      |  8 +-
 .../vector-load-store/vlds-brc-b32/kernel.pto      | 40 +++++-----
 .../vector-load-store/vlds-brc-blk/kernel.pto      |  4 +-
 .../vector-load-store/vlds-post-update/kernel.pto  | 12 +--
 .../vector-load-store/vlds-unpk-b16/kernel.pto     |  4 +-
 .../vreg-low-precision-ldst/kernel.pto             |  4 +-
 .../cases/onboard-only/simt-keep-resume/kernel.pto |  4 +-
 116 files changed, 780 insertions(+), 729 deletions(-)
===== END STAGE clone rc=0 @ 2026-07-09 10:40:39 =====

===== STAGE codex-review @ 2026-07-09 10:40:39 =====
set -euo pipefail
cd '/tmp/ptoas-pr-review-monitor/runs/20260709_104032_pr920/repo'
'codex' exec -C '/tmp/ptoas-pr-review-monitor/runs/20260709_104032_pr920/repo' -s read-only -c 'model_provider="codereview"' -c 'model="gpt-5.4"' -c 'model_reasoning_effort="xhigh"' --output-schema '/tmp/ptoas-pr-review-monitor/runs/20260709_104032_pr920/review_schema.json' -o '/tmp/ptoas-pr-review-monitor/runs/20260709_104032_pr920/codex_last_message.json' --color never - < '/tmp/ptoas-pr-review-monitor/runs/20260709_104032_pr920/review_prompt.txt'
[monitor] stage timeout: 1800s
OpenAI Codex v0.115.0 (research preview)
--------
workdir: /tmp/ptoas-pr-review-monitor/runs/20260709_104032_pr920/repo
model: gpt-5.4
provider: codereview
approval: never
sandbox: read-only
reasoning effort: xhigh
reasoning summaries: none
session id: 019f44bf-aa99-7173-8820-3961a9cf4561
--------
user
你现在在审查 GitHub PR。

仓库：hw-native-sys/PTOAS
PR：#920 ub->gm传递l2_cache_ctl参数
作者：and0d0
base branch：origin/main
head branch：HEAD（当前已 checkout 到 PR head）

要求：
1. 只审查这个 PR 相对 origin/main 的改动，必要时可以看上下文文件。
2. 重点找真实的 correctness / regression / contract mismatch / CI / runtime / compatibility 问题。
3. 不要提纯风格建议，不要提低价值猜测。
4. 严格按优先级输出：
   - P1：高概率会导致错误结果、编译/运行失败、严重回归、发布阻断
   - P2：重要缺陷、行为回归、遗漏校验/测试、较大兼容性问题
   - P3：次要但明确可改的问题
5. 如果没有问题，summary 直接写：未检查到 PR #920 存在问题，并返回 findings=[]。
6. 如果有问题，summary 简洁概括，findings 里每条都要给出：
   - severity
   - title
   - body（说明为什么是问题，尽量具体）
   - file（尽量给相对路径）
   - line（能确定就填整数，否则 null）

建议先查看：
- git status --short
- git diff --stat origin/main...HEAD
- git diff --unified=80 origin/main...HEAD

最终输出必须严格匹配 JSON schema。

mcp startup: no servers
Reconnecting... 1/5 (unexpected status 403 Forbidden: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}, url: https://codex.0u0o.com/responses, cf-ray: a183f7183fd12283-LAX, request id: 1d0ec287-a871-4f20-92a6-2a10d628e0a3)
Reconnecting... 2/5 (unexpected status 403 Forbidden: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}, url: https://codex.0u0o.com/responses, cf-ray: a183f71ad9d85708-LAX, request id: ebf6c3b6-3264-4364-9bdd-f37111d9ab19)
Reconnecting... 3/5 (unexpected status 403 Forbidden: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}, url: https://codex.0u0o.com/responses, cf-ray: a183f71efa038f16-LAS, request id: dab2b83a-abbb-4832-af51-553413aeedcf)
Reconnecting... 4/5 (unexpected status 403 Forbidden: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}, url: https://codex.0u0o.com/responses, cf-ray: a183f7257bcbfca7-LAX, request id: 41883a4a-3594-4e3a-9e0b-9ff8d4fde5e9)
Reconnecting... 5/5 (unexpected status 403 Forbidden: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}, url: https://codex.0u0o.com/responses, cf-ray: a183f73118b39810-LAX, request id: 02552731-7add-4f75-9a78-a954270c894a)
ERROR: unexpected status 403 Forbidden: {"code":"INSUFFICIENT_BALANCE","message":"Insufficient account balance"}, url: https://codex.0u0o.com/responses, cf-ray: a183f7460c375808-LAS, request id: d8bd91fe-e63a-4c28-95ba-90cd00ea89dc
Warning: no last agent message; wrote empty content to /tmp/ptoas-pr-review-monitor/runs/20260709_104032_pr920/codex_last_message.json
===== END STAGE codex-review rc=1 @ 2026-07-09 10:40:47 =====

[gemini-code-assist]

Code Review

This pull request introduces support for GM store-side L2 cache control in the pto.mte_ub_gm and pto.copy_ubuf_to_gm operations by replacing a previously reserved field with the l2_cache_ctl parameter. The changes include updates to the dialect definition, parser, printer, verifier (ensuring constant values fit in the [0, 15] range), LLVM emitters, and documentation. Existing tests and examples have been updated to include the new parameter, and a new test file has been added to verify its roundtrip and expansion. There are no review comments, so I have no feedback to provide.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.