1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118
| $ TORCHINDUCTOR_CACHE_DIR=./dev_cache \ TRITON_CACHE_DIR=./dev_cache/triton \ TORCH_LOGS="autotuning" \ python compile_aoti.py No 'aoti_cache.tar.gz' found; will autotune if disk cache is cold. V1116 07:22:40.661000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess ExternKernelBenchmarkRequest(extern_kernels.mm): load 0.000005, create tensor 0.000000, bench 0.142278 V1116 07:22:40.664000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: cd5p4wrvq5iidlqri5x2fjrvrjh2ef7hg5tkv5ldomwi2voftd67, path: /mnt/dev_cache/d5/cd5p4wrvq5iidlqri5x2fjrvrjh2ef7hg5tkv5ldomwi2voftd67.py V1116 07:22:40.689000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/d5/cd5p4wrvq5iidlqri5x2fjrvrjh2ef7hg5tkv5ldomwi2voftd67.py', self.module_cache_key='cd5p4wrvq5iidlqri5x2fjrvrjh2ef7hg5tkv5ldomwi2voftd67': load 0.002170, create tensor 0.000000, bench 0.024590 V1116 07:22:40.691000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: csrroaexmdv2c7ph7w4cwochqoha7xws6ek4banbqx5oo6indtjz, path: /mnt/dev_cache/sr/csrroaexmdv2c7ph7w4cwochqoha7xws6ek4banbqx5oo6indtjz.py V1116 07:22:40.713000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/sr/csrroaexmdv2c7ph7w4cwochqoha7xws6ek4banbqx5oo6indtjz.py', self.module_cache_key='csrroaexmdv2c7ph7w4cwochqoha7xws6ek4banbqx5oo6indtjz': load 0.002307, create tensor 0.000000, bench 0.021628 V1116 07:22:40.715000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: ctyeqjd6jv2an637kbcvfkk6mtbeanggv6jkyjarkfexwiz2sewl, path: /mnt/dev_cache/ty/ctyeqjd6jv2an637kbcvfkk6mtbeanggv6jkyjarkfexwiz2sewl.py V1116 07:22:40.737000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/ty/ctyeqjd6jv2an637kbcvfkk6mtbeanggv6jkyjarkfexwiz2sewl.py', self.module_cache_key='ctyeqjd6jv2an637kbcvfkk6mtbeanggv6jkyjarkfexwiz2sewl': load 0.002234, create tensor 0.000000, bench 0.021785 V1116 07:22:40.740000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: cohiwiqm7kfnrthaag35heyouv4sg5mbhafyv3e6gqj7t2dd5oqx, path: /mnt/dev_cache/oh/cohiwiqm7kfnrthaag35heyouv4sg5mbhafyv3e6gqj7t2dd5oqx.py V1116 07:22:40.762000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/oh/cohiwiqm7kfnrthaag35heyouv4sg5mbhafyv3e6gqj7t2dd5oqx.py', self.module_cache_key='cohiwiqm7kfnrthaag35heyouv4sg5mbhafyv3e6gqj7t2dd5oqx': load 0.002160, create tensor 0.000000, bench 0.022156 V1116 07:22:40.764000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: ck4bnfm3vh67gec2gq7xvqw66lyiefipgr55hlnmit5ognovox65, path: /mnt/dev_cache/k4/ck4bnfm3vh67gec2gq7xvqw66lyiefipgr55hlnmit5ognovox65.py V1116 07:22:40.787000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/k4/ck4bnfm3vh67gec2gq7xvqw66lyiefipgr55hlnmit5ognovox65.py', self.module_cache_key='ck4bnfm3vh67gec2gq7xvqw66lyiefipgr55hlnmit5ognovox65': load 0.002336, create tensor 0.000000, bench 0.022160 V1116 07:22:40.789000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: chjdn3rk7iey5a644aao3z35tsdsjzvsmrdzkyhxz5fn3oadkijh, path: /mnt/dev_cache/hj/chjdn3rk7iey5a644aao3z35tsdsjzvsmrdzkyhxz5fn3oadkijh.py V1116 07:22:40.814000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/hj/chjdn3rk7iey5a644aao3z35tsdsjzvsmrdzkyhxz5fn3oadkijh.py', self.module_cache_key='chjdn3rk7iey5a644aao3z35tsdsjzvsmrdzkyhxz5fn3oadkijh': load 0.002139, create tensor 0.000000, bench 0.024451 V1116 07:22:40.816000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: ce7t5tivu2e7ylsdixrbzdbjknui74yyi3d6vxgbyazfj6teb6jx, path: /mnt/dev_cache/e7/ce7t5tivu2e7ylsdixrbzdbjknui74yyi3d6vxgbyazfj6teb6jx.py V1116 07:22:40.840000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/e7/ce7t5tivu2e7ylsdixrbzdbjknui74yyi3d6vxgbyazfj6teb6jx.py', self.module_cache_key='ce7t5tivu2e7ylsdixrbzdbjknui74yyi3d6vxgbyazfj6teb6jx': load 0.002221, create tensor 0.000000, bench 0.023701 V1116 07:22:40.842000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: c6usc4weo57xa55nklmwiuuwrwcyq7z4kuh3fonwqfjy6wtcrxun, path: /mnt/dev_cache/6u/c6usc4weo57xa55nklmwiuuwrwcyq7z4kuh3fonwqfjy6wtcrxun.py V1116 07:22:40.865000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/6u/c6usc4weo57xa55nklmwiuuwrwcyq7z4kuh3fonwqfjy6wtcrxun.py', self.module_cache_key='c6usc4weo57xa55nklmwiuuwrwcyq7z4kuh3fonwqfjy6wtcrxun': load 0.002308, create tensor 0.000000, bench 0.022549 V1116 07:22:40.867000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: crrz34b5rgtt5uogf5ug4tsio6rlrmpbdnsa3kbjpxchx4qftnku, path: /mnt/dev_cache/rr/crrz34b5rgtt5uogf5ug4tsio6rlrmpbdnsa3kbjpxchx4qftnku.py V1116 07:22:40.891000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/rr/crrz34b5rgtt5uogf5ug4tsio6rlrmpbdnsa3kbjpxchx4qftnku.py', self.module_cache_key='crrz34b5rgtt5uogf5ug4tsio6rlrmpbdnsa3kbjpxchx4qftnku': load 0.002243, create tensor 0.000000, bench 0.023495 V1116 07:22:40.893000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: cgvv3rsvsk4nswjlx6iqm2gkojl6bzweyfqo7wsilgq66hmedgzw, path: /mnt/dev_cache/gv/cgvv3rsvsk4nswjlx6iqm2gkojl6bzweyfqo7wsilgq66hmedgzw.py V1116 07:22:40.917000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/gv/cgvv3rsvsk4nswjlx6iqm2gkojl6bzweyfqo7wsilgq66hmedgzw.py', self.module_cache_key='cgvv3rsvsk4nswjlx6iqm2gkojl6bzweyfqo7wsilgq66hmedgzw': load 0.002159, create tensor 0.000000, bench 0.023397 V1116 07:22:40.919000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: co5sj5jtzldgl4dnqqtsrjs3kcd3hewdq5ipv35qfypiqjqjxyea, path: /mnt/dev_cache/o5/co5sj5jtzldgl4dnqqtsrjs3kcd3hewdq5ipv35qfypiqjqjxyea.py V1116 07:22:40.942000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/o5/co5sj5jtzldgl4dnqqtsrjs3kcd3hewdq5ipv35qfypiqjqjxyea.py', self.module_cache_key='co5sj5jtzldgl4dnqqtsrjs3kcd3hewdq5ipv35qfypiqjqjxyea': load 0.002196, create tensor 0.000000, bench 0.022916 V1116 07:22:40.945000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: ctbpmwbdrkvvv5kngs7mt52usdnmxfxpw33djsvxz3baqmdldu45, path: /mnt/dev_cache/tb/ctbpmwbdrkvvv5kngs7mt52usdnmxfxpw33djsvxz3baqmdldu45.py V1116 07:22:40.969000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/tb/ctbpmwbdrkvvv5kngs7mt52usdnmxfxpw33djsvxz3baqmdldu45.py', self.module_cache_key='ctbpmwbdrkvvv5kngs7mt52usdnmxfxpw33djsvxz3baqmdldu45': load 0.002147, create tensor 0.000000, bench 0.023867 V1116 07:22:40.971000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: cszkh2jx4ryai5aktdtdp7bpzyqyth5nkf7ulmhlaelnr4p2ecck, path: /mnt/dev_cache/sz/cszkh2jx4ryai5aktdtdp7bpzyqyth5nkf7ulmhlaelnr4p2ecck.py V1116 07:22:40.996000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/sz/cszkh2jx4ryai5aktdtdp7bpzyqyth5nkf7ulmhlaelnr4p2ecck.py', self.module_cache_key='cszkh2jx4ryai5aktdtdp7bpzyqyth5nkf7ulmhlaelnr4p2ecck': load 0.002202, create tensor 0.000000, bench 0.024556 V1116 07:22:40.998000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: cngbjofxwx7eukrjgzaja7hagkllyk777vkjqb2ebqoubl4voqrg, path: /mnt/dev_cache/ng/cngbjofxwx7eukrjgzaja7hagkllyk777vkjqb2ebqoubl4voqrg.py V1116 07:22:41.020000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/ng/cngbjofxwx7eukrjgzaja7hagkllyk777vkjqb2ebqoubl4voqrg.py', self.module_cache_key='cngbjofxwx7eukrjgzaja7hagkllyk777vkjqb2ebqoubl4voqrg': load 0.002171, create tensor 0.000000, bench 0.022327 V1116 07:22:41.023000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: cw5vnawoymyzkba4cy4t3gqtrpq73bzc34m2zctnezqkudhskbwt, path: /mnt/dev_cache/w5/cw5vnawoymyzkba4cy4t3gqtrpq73bzc34m2zctnezqkudhskbwt.py V1116 07:22:41.045000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/w5/cw5vnawoymyzkba4cy4t3gqtrpq73bzc34m2zctnezqkudhskbwt.py', self.module_cache_key='cw5vnawoymyzkba4cy4t3gqtrpq73bzc34m2zctnezqkudhskbwt': load 0.002168, create tensor 0.000000, bench 0.022238 V1116 07:22:41.048000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: c2timucdtdplhy4lpaftkazykxhmgnb652y4k6qut4jnqobxt6bz, path: /mnt/dev_cache/2t/c2timucdtdplhy4lpaftkazykxhmgnb652y4k6qut4jnqobxt6bz.py V1116 07:22:41.072000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/2t/c2timucdtdplhy4lpaftkazykxhmgnb652y4k6qut4jnqobxt6bz.py', self.module_cache_key='c2timucdtdplhy4lpaftkazykxhmgnb652y4k6qut4jnqobxt6bz': load 0.002227, create tensor 0.000000, bench 0.024506 V1116 07:22:41.074000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: ctjjyomv6k3325epc5mvkmgnb37zwxdo5dinj4dhxnp3huqbugfe, path: /mnt/dev_cache/tj/ctjjyomv6k3325epc5mvkmgnb37zwxdo5dinj4dhxnp3huqbugfe.py V1116 07:22:41.097000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/tj/ctjjyomv6k3325epc5mvkmgnb37zwxdo5dinj4dhxnp3huqbugfe.py', self.module_cache_key='ctjjyomv6k3325epc5mvkmgnb37zwxdo5dinj4dhxnp3huqbugfe': load 0.002155, create tensor 0.000000, bench 0.022694 V1116 07:22:41.100000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: cfsur26ayhe7c2kapmokuidv7k3ztzfgsfjttu2435vbcdlrmbwu, path: /mnt/dev_cache/fs/cfsur26ayhe7c2kapmokuidv7k3ztzfgsfjttu2435vbcdlrmbwu.py V1116 07:22:41.124000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/fs/cfsur26ayhe7c2kapmokuidv7k3ztzfgsfjttu2435vbcdlrmbwu.py', self.module_cache_key='cfsur26ayhe7c2kapmokuidv7k3ztzfgsfjttu2435vbcdlrmbwu': load 0.002608, create tensor 0.000000, bench 0.024043 V1116 07:22:41.126000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: cp6ov26kqg2jyi25l3q2ygwqhgxakelu7sm2zz3pggfmqq5h7ekb, path: /mnt/dev_cache/p6/cp6ov26kqg2jyi25l3q2ygwqhgxakelu7sm2zz3pggfmqq5h7ekb.py V1116 07:22:41.153000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/p6/cp6ov26kqg2jyi25l3q2ygwqhgxakelu7sm2zz3pggfmqq5h7ekb.py', self.module_cache_key='cp6ov26kqg2jyi25l3q2ygwqhgxakelu7sm2zz3pggfmqq5h7ekb': load 0.002146, create tensor 0.000000, bench 0.026611 Autotune Choices Stats: {"num_choices": 20, "num_triton_choices": 19, "best_kernel": "mm", "best_time": 0.009983999654650688, "best_triton_pos": 1, "best_triton_time": 0.012256000190973282, "best_triton_kernel": "triton_mm_4", "best_triton_kernel_desc": "ACC_TYPE='tl.float32', ALLOW_TF32=False, BLOCK_K=128, BLOCK_M=64, BLOCK_N=32, EVEN_K=True, GROUP_M=8, USE_FAST_ACCUM=False, num_stages=5, num_warps=4"} AUTOTUNE mm(64x1024, 1024x2048) strides: [1024, 1], [1, 1024] dtypes: torch.bfloat16, torch.bfloat16 mm 0.0100 ms 100.0% triton_mm_4 0.0123 ms 81.5% ACC_TYPE='tl.float32', ALLOW_TF32=False, BLOCK_K=128, BLOCK_M=64, BLOCK_N=32, EVEN_K=True, GROUP_M=8, USE_FAST_ACCUM=False, num_stages=5, num_warps=4 triton_mm_1 0.0136 ms 73.2% ACC_TYPE='tl.float32', ALLOW_TF32=False, BLOCK_K=128, BLOCK_M=32, BLOCK_N=32, EVEN_K=True, GROUP_M=8, USE_FAST_ACCUM=False, num_stages=2, num_warps=4 triton_mm_3 0.0139 ms 72.1% ACC_TYPE='tl.float32', ALLOW_TF32=False, BLOCK_K=32, BLOCK_M=64, BLOCK_N=32, EVEN_K=True, GROUP_M=8, USE_FAST_ACCUM=False, num_stages=5, num_warps=8 triton_mm_7 0.0139 ms 72.1% ACC_TYPE='tl.float32', ALLOW_TF32=False, BLOCK_K=64, BLOCK_M=64, BLOCK_N=64, EVEN_K=True, GROUP_M=8, USE_FAST_ACCUM=False, num_stages=3, num_warps=8 triton_mm_13 0.0158 ms 63.0% ACC_TYPE='tl.float32', ALLOW_TF32=False, BLOCK_K=32, BLOCK_M=64, BLOCK_N=64, EVEN_K=True, GROUP_M=8, USE_FAST_ACCUM=False, num_stages=3, num_warps=4 triton_mm_14 0.0168 ms 59.5% ACC_TYPE='tl.float32', ALLOW_TF32=False, BLOCK_K=32, BLOCK_M=64, BLOCK_N=64, EVEN_K=True, GROUP_M=8, USE_FAST_ACCUM=False, num_stages=4, num_warps=8 triton_mm_11 0.0181 ms 55.0% ACC_TYPE='tl.float32', ALLOW_TF32=False, BLOCK_K=64, BLOCK_M=64, BLOCK_N=128, EVEN_K=True, GROUP_M=8, USE_FAST_ACCUM=False, num_stages=3, num_warps=4 triton_mm_2 0.0184 ms 54.3% ACC_TYPE='tl.float32', ALLOW_TF32=False, BLOCK_K=32, BLOCK_M=32, BLOCK_N=64, EVEN_K=True, GROUP_M=8, USE_FAST_ACCUM=False, num_stages=5, num_warps=8 triton_mm_16 0.0184 ms 54.2% ACC_TYPE='tl.float32', ALLOW_TF32=False, BLOCK_K=64, BLOCK_M=64, BLOCK_N=128, EVEN_K=True, GROUP_M=8, USE_FAST_ACCUM=False, num_stages=5, num_warps=8 SingleProcess AUTOTUNE benchmarking takes 0.6359 seconds and 1.4817 seconds precompiling for 20 choices V1116 07:22:41.433000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess ExternKernelBenchmarkRequest(extern_kernels.mm): load 0.000005, create tensor 0.000000, bench 0.030149 V1116 07:22:41.436000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: cmwgxwbladuod2lshztiz6ktwrslrbqsz3vx3rzvnxx6x3pbdtzu, path: /mnt/dev_cache/mw/cmwgxwbladuod2lshztiz6ktwrslrbqsz3vx3rzvnxx6x3pbdtzu.py V1116 07:22:41.462000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/mw/cmwgxwbladuod2lshztiz6ktwrslrbqsz3vx3rzvnxx6x3pbdtzu.py', self.module_cache_key='cmwgxwbladuod2lshztiz6ktwrslrbqsz3vx3rzvnxx6x3pbdtzu': load 0.002256, create tensor 0.000000, bench 0.026758 V1116 07:22:41.465000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: cjcfttw3fuotzx6gsolao3pfddpekwqkagdtbzf3iufp2t2ck34f, path: /mnt/dev_cache/jc/cjcfttw3fuotzx6gsolao3pfddpekwqkagdtbzf3iufp2t2ck34f.py V1116 07:22:41.487000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/jc/cjcfttw3fuotzx6gsolao3pfddpekwqkagdtbzf3iufp2t2ck34f.py', self.module_cache_key='cjcfttw3fuotzx6gsolao3pfddpekwqkagdtbzf3iufp2t2ck34f': load 0.002183, create tensor 0.000000, bench 0.022386 V1116 07:22:41.490000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: c6ewckuebz7l66li74hnvdshvk6mjs5h74que6jrbwkli3w7l7yc, path: /mnt/dev_cache/6e/c6ewckuebz7l66li74hnvdshvk6mjs5h74que6jrbwkli3w7l7yc.py V1116 07:22:41.511000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/6e/c6ewckuebz7l66li74hnvdshvk6mjs5h74que6jrbwkli3w7l7yc.py', self.module_cache_key='c6ewckuebz7l66li74hnvdshvk6mjs5h74que6jrbwkli3w7l7yc': load 0.002131, create tensor 0.000000, bench 0.021764 V1116 07:22:41.514000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: cjcp7xil2c3snoxysf3r36z4uoyuywe3roaqe3aoxglnlkreei6w, path: /mnt/dev_cache/jc/cjcp7xil2c3snoxysf3r36z4uoyuywe3roaqe3aoxglnlkreei6w.py V1116 07:22:41.536000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/jc/cjcp7xil2c3snoxysf3r36z4uoyuywe3roaqe3aoxglnlkreei6w.py', self.module_cache_key='cjcp7xil2c3snoxysf3r36z4uoyuywe3roaqe3aoxglnlkreei6w': load 0.002167, create tensor 0.000000, bench 0.022027 V1116 07:22:41.539000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: cnxvhj2eemjdhd7h3r4vdk52vmvk4flq32ohd4uoviigeznurnxd, path: /mnt/dev_cache/nx/cnxvhj2eemjdhd7h3r4vdk52vmvk4flq32ohd4uoviigeznurnxd.py V1116 07:22:41.561000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/nx/cnxvhj2eemjdhd7h3r4vdk52vmvk4flq32ohd4uoviigeznurnxd.py', self.module_cache_key='cnxvhj2eemjdhd7h3r4vdk52vmvk4flq32ohd4uoviigeznurnxd': load 0.003419, create tensor 0.000000, bench 0.020997 V1116 07:22:41.563000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: c3vsb2m6kx5sde3wnniolmitcqj37t75ev47l4iykt3zunuankz7, path: /mnt/dev_cache/3v/c3vsb2m6kx5sde3wnniolmitcqj37t75ev47l4iykt3zunuankz7.py V1116 07:22:41.590000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/3v/c3vsb2m6kx5sde3wnniolmitcqj37t75ev47l4iykt3zunuankz7.py', self.module_cache_key='c3vsb2m6kx5sde3wnniolmitcqj37t75ev47l4iykt3zunuankz7': load 0.002177, create tensor 0.000000, bench 0.027241 V1116 07:22:41.593000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: cppdejonesxil6mjfu55iwnctrazkevff3ewmhjljqd4hiri6pfp, path: /mnt/dev_cache/pp/cppdejonesxil6mjfu55iwnctrazkevff3ewmhjljqd4hiri6pfp.py V1116 07:22:41.617000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/pp/cppdejonesxil6mjfu55iwnctrazkevff3ewmhjljqd4hiri6pfp.py', self.module_cache_key='cppdejonesxil6mjfu55iwnctrazkevff3ewmhjljqd4hiri6pfp': load 0.002128, create tensor 0.000000, bench 0.024184 V1116 07:22:41.619000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: c7snjkmvhyldusr2xifxcn4vadadytmppfcozunfzhasda4i4chn, path: /mnt/dev_cache/7s/c7snjkmvhyldusr2xifxcn4vadadytmppfcozunfzhasda4i4chn.py V1116 07:22:41.640000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/7s/c7snjkmvhyldusr2xifxcn4vadadytmppfcozunfzhasda4i4chn.py', self.module_cache_key='c7snjkmvhyldusr2xifxcn4vadadytmppfcozunfzhasda4i4chn': load 0.002138, create tensor 0.000000, bench 0.021063 V1116 07:22:41.643000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: cpeclnbmjef4zcf34qooorozuzahofx2d2puhvminst4q5b6f7nx, path: /mnt/dev_cache/pe/cpeclnbmjef4zcf34qooorozuzahofx2d2puhvminst4q5b6f7nx.py V1116 07:22:41.667000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/pe/cpeclnbmjef4zcf34qooorozuzahofx2d2puhvminst4q5b6f7nx.py', self.module_cache_key='cpeclnbmjef4zcf34qooorozuzahofx2d2puhvminst4q5b6f7nx': load 0.002104, create tensor 0.000000, bench 0.023982 V1116 07:22:41.669000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: cv3pt6bjxbkkmys7gka5bq5ns2ayb2owazohwy66jt3eckw2kca3, path: /mnt/dev_cache/v3/cv3pt6bjxbkkmys7gka5bq5ns2ayb2owazohwy66jt3eckw2kca3.py V1116 07:22:41.692000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/v3/cv3pt6bjxbkkmys7gka5bq5ns2ayb2owazohwy66jt3eckw2kca3.py', self.module_cache_key='cv3pt6bjxbkkmys7gka5bq5ns2ayb2owazohwy66jt3eckw2kca3': load 0.002136, create tensor 0.000000, bench 0.023215 V1116 07:22:41.695000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: c4jlyq7rb77ebf4rvn4ikhtfnbhd6pqtrbxquteeuzquwime3nrk, path: /mnt/dev_cache/4j/c4jlyq7rb77ebf4rvn4ikhtfnbhd6pqtrbxquteeuzquwime3nrk.py V1116 07:22:41.717000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/4j/c4jlyq7rb77ebf4rvn4ikhtfnbhd6pqtrbxquteeuzquwime3nrk.py', self.module_cache_key='c4jlyq7rb77ebf4rvn4ikhtfnbhd6pqtrbxquteeuzquwime3nrk': load 0.002173, create tensor 0.000000, bench 0.022147 V1116 07:22:41.719000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: crcbalw7w5z67y3jpfc4zfqhhx7irjjgaywopxdonysfd34iinrz, path: /mnt/dev_cache/rc/crcbalw7w5z67y3jpfc4zfqhhx7irjjgaywopxdonysfd34iinrz.py V1116 07:22:41.742000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/rc/crcbalw7w5z67y3jpfc4zfqhhx7irjjgaywopxdonysfd34iinrz.py', self.module_cache_key='crcbalw7w5z67y3jpfc4zfqhhx7irjjgaywopxdonysfd34iinrz': load 0.002204, create tensor 0.000000, bench 0.022645 V1116 07:22:41.744000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: codfiw5qgjj5hqgd6t6zsv2szo4zjoahyfdsvfh56hnbgq7vnv3j, path: /mnt/dev_cache/od/codfiw5qgjj5hqgd6t6zsv2szo4zjoahyfdsvfh56hnbgq7vnv3j.py V1116 07:22:41.772000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/od/codfiw5qgjj5hqgd6t6zsv2szo4zjoahyfdsvfh56hnbgq7vnv3j.py', self.module_cache_key='codfiw5qgjj5hqgd6t6zsv2szo4zjoahyfdsvfh56hnbgq7vnv3j': load 0.002155, create tensor 0.000000, bench 0.027098 V1116 07:22:41.774000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: cvydnimncazdmxph7sxasjhvtsyllgmbuof75bklhpu57m7yrxx6, path: /mnt/dev_cache/vy/cvydnimncazdmxph7sxasjhvtsyllgmbuof75bklhpu57m7yrxx6.py V1116 07:22:41.797000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/vy/cvydnimncazdmxph7sxasjhvtsyllgmbuof75bklhpu57m7yrxx6.py', self.module_cache_key='cvydnimncazdmxph7sxasjhvtsyllgmbuof75bklhpu57m7yrxx6': load 0.002473, create tensor 0.000000, bench 0.022209 V1116 07:22:41.799000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: cvztnzlt5tlyricy2bshow75wusnx6cdc2hh6jc6itq643vvmygo, path: /mnt/dev_cache/vz/cvztnzlt5tlyricy2bshow75wusnx6cdc2hh6jc6itq643vvmygo.py V1116 07:22:41.821000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/vz/cvztnzlt5tlyricy2bshow75wusnx6cdc2hh6jc6itq643vvmygo.py', self.module_cache_key='cvztnzlt5tlyricy2bshow75wusnx6cdc2hh6jc6itq643vvmygo': load 0.002101, create tensor 0.000000, bench 0.021599 V1116 07:22:41.823000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: chxhx5e76spsou4xzqh2ifnxdwx4fuytkirzkav5bbhnw4dg2cba, path: /mnt/dev_cache/hx/chxhx5e76spsou4xzqh2ifnxdwx4fuytkirzkav5bbhnw4dg2cba.py V1116 07:22:41.849000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/hx/chxhx5e76spsou4xzqh2ifnxdwx4fuytkirzkav5bbhnw4dg2cba.py', self.module_cache_key='chxhx5e76spsou4xzqh2ifnxdwx4fuytkirzkav5bbhnw4dg2cba': load 0.002681, create tensor 0.000000, bench 0.025591 V1116 07:22:41.852000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: cm26eqy5sxjmedj2xbsngtunj5snlfj6q2i7k4jcrqk6sjbzvljq, path: /mnt/dev_cache/m2/cm26eqy5sxjmedj2xbsngtunj5snlfj6q2i7k4jcrqk6sjbzvljq.py V1116 07:22:41.874000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/m2/cm26eqy5sxjmedj2xbsngtunj5snlfj6q2i7k4jcrqk6sjbzvljq.py', self.module_cache_key='cm26eqy5sxjmedj2xbsngtunj5snlfj6q2i7k4jcrqk6sjbzvljq': load 0.002357, create tensor 0.000000, bench 0.022555 V1116 07:22:41.877000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: cvtl254oljcn7lkpyxehxyff2wpt77qy5ilagkecbxvomyhjgugy, path: /mnt/dev_cache/vt/cvtl254oljcn7lkpyxehxyff2wpt77qy5ilagkecbxvomyhjgugy.py V1116 07:22:41.902000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/vt/cvtl254oljcn7lkpyxehxyff2wpt77qy5ilagkecbxvomyhjgugy.py', self.module_cache_key='cvtl254oljcn7lkpyxehxyff2wpt77qy5ilagkecbxvomyhjgugy': load 0.002104, create tensor 0.000000, bench 0.025068 V1116 07:22:41.904000 2128 torch/_inductor/autotune_process.py:797] [0/0] [__autotuning] benchmark module key: cqes7rpd6r2low2rn5znlbz5u67uxhbfpekix3pakyasdkdtqmhn, path: /mnt/dev_cache/qe/cqes7rpd6r2low2rn5znlbz5u67uxhbfpekix3pakyasdkdtqmhn.py V1116 07:22:41.933000 2128 torch/_inductor/autotune_process.py:610] [0/0] [__autotuning] InChildProcess self.kernel_name='triton_mm', self.module_path='/mnt/dev_cache/qe/cqes7rpd6r2low2rn5znlbz5u67uxhbfpekix3pakyasdkdtqmhn.py', self.module_cache_key='cqes7rpd6r2low2rn5znlbz5u67uxhbfpekix3pakyasdkdtqmhn': load 0.002103, create tensor 0.000000, bench 0.028835 Autotune Choices Stats: {"num_choices": 20, "num_triton_choices": 19, "best_kernel": "mm", "best_time": 0.01228800043463707, "best_triton_pos": 1, "best_triton_time": 0.01228800043463707, "best_triton_kernel": "triton_mm_23", "best_triton_kernel_desc": "ACC_TYPE='tl.float32', ALLOW_TF32=False, BLOCK_K=128, BLOCK_M=64, BLOCK_N=32, EVEN_K=True, GROUP_M=8, USE_FAST_ACCUM=False, num_stages=5, num_warps=4"} AUTOTUNE mm(64x2048, 2048x1024) strides: [2048, 1], [1, 2048] dtypes: torch.bfloat16, torch.bfloat16 mm 0.0123 ms 100.0% triton_mm_23 0.0123 ms 100.0% ACC_TYPE='tl.float32', ALLOW_TF32=False, BLOCK_K=128, BLOCK_M=64, BLOCK_N=32, EVEN_K=True, GROUP_M=8, USE_FAST_ACCUM=False, num_stages=5, num_warps=4 triton_mm_22 0.0161 ms 76.5% ACC_TYPE='tl.float32', ALLOW_TF32=False, BLOCK_K=32, BLOCK_M=64, BLOCK_N=32, EVEN_K=True, GROUP_M=8, USE_FAST_ACCUM=False, num_stages=5, num_warps=8 triton_mm_20 0.0179 ms 68.6% ACC_TYPE='tl.float32', ALLOW_TF32=False, BLOCK_K=128, BLOCK_M=32, BLOCK_N=32, EVEN_K=True, GROUP_M=8, USE_FAST_ACCUM=False, num_stages=2, num_warps=4 triton_mm_26 0.0209 ms 58.9% ACC_TYPE='tl.float32', ALLOW_TF32=False, BLOCK_K=64, BLOCK_M=64, BLOCK_N=64, EVEN_K=True, GROUP_M=8, USE_FAST_ACCUM=False, num_stages=3, num_warps=8 triton_mm_21 0.0221 ms 55.7% ACC_TYPE='tl.float32', ALLOW_TF32=False, BLOCK_K=32, BLOCK_M=32, BLOCK_N=64, EVEN_K=True, GROUP_M=8, USE_FAST_ACCUM=False, num_stages=5, num_warps=8 triton_mm_33 0.0250 ms 49.1% ACC_TYPE='tl.float32', ALLOW_TF32=False, BLOCK_K=32, BLOCK_M=64, BLOCK_N=64, EVEN_K=True, GROUP_M=8, USE_FAST_ACCUM=False, num_stages=4, num_warps=8 triton_mm_30 0.0291 ms 42.3% ACC_TYPE='tl.float32', ALLOW_TF32=False, BLOCK_K=64, BLOCK_M=64, BLOCK_N=128, EVEN_K=True, GROUP_M=8, USE_FAST_ACCUM=False, num_stages=3, num_warps=4 triton_mm_29 0.0301 ms 40.8% ACC_TYPE='tl.float32', ALLOW_TF32=False, BLOCK_K=32, BLOCK_M=64, BLOCK_N=128, EVEN_K=True, GROUP_M=8, USE_FAST_ACCUM=False, num_stages=4, num_warps=8 triton_mm_35 0.0301 ms 40.8% ACC_TYPE='tl.float32', ALLOW_TF32=False, BLOCK_K=64, BLOCK_M=64, BLOCK_N=128, EVEN_K=True, GROUP_M=8, USE_FAST_ACCUM=False, num_stages=5, num_warps=8 SingleProcess AUTOTUNE benchmarking takes 0.5319 seconds and 0.0020 seconds precompiling for 20 choices AOTInductor compile time: 14.32s Local correctness check passed. Saved 1 autotune cache files into 'aoti_cache.tar.gz' and 'aoti_cache_meta.json'.
|