SliceOp support S->S, not support S->P(TODO)

[wyg1997]

SliceOp 先只支持 S->S(FullSlice)，P->P，B->B，先解决 https://github.com/Oneflow-Inc/OneTeam/issues/1514#issuecomment-1169585270 中的推导问题。

后续再支持 S->P。

[github-actions]

Static analysis with clang failed. PR label automerge has been removed

[github-actions]

View latest API docs preview at: https://staging.oneflow.info/docs/Oneflow-Inc/oneflow/pr/8521/

[github-actions]

Speed stats:

GPU Name: NVIDIA GeForce GTX 1080 

❌ OneFlow resnet50 time: 129.3ms (= 12926.3ms / 100, input_shape=[16, 3, 224, 224])
PyTorch resnet50 time: 143.6ms (= 14361.4ms / 100, input_shape=[16, 3, 224, 224])
✔️ Relative speed: 1.11 (= 143.6ms / 129.3ms)

OneFlow resnet50 time: 75.7ms (= 7568.5ms / 100, input_shape=[8, 3, 224, 224])
PyTorch resnet50 time: 85.6ms (= 8562.0ms / 100, input_shape=[8, 3, 224, 224])
✔️ Relative speed: 1.13 (= 85.6ms / 75.7ms)

OneFlow resnet50 time: 47.7ms (= 9542.8ms / 200, input_shape=[4, 3, 224, 224])
PyTorch resnet50 time: 53.0ms (= 10601.1ms / 200, input_shape=[4, 3, 224, 224])
✔️ Relative speed: 1.11 (= 53.0ms / 47.7ms)

OneFlow resnet50 time: 39.9ms (= 7988.5ms / 200, input_shape=[2, 3, 224, 224])
PyTorch resnet50 time: 45.0ms (= 8994.0ms / 200, input_shape=[2, 3, 224, 224])
✔️ Relative speed: 1.13 (= 45.0ms / 39.9ms)

OneFlow resnet50 time: 35.5ms (= 7091.2ms / 200, input_shape=[1, 3, 224, 224])
PyTorch resnet50 time: 42.1ms (= 8417.4ms / 200, input_shape=[1, 3, 224, 224])
✔️ Relative speed: 1.19 (= 42.1ms / 35.5ms)

OneFlow swin dataloader time: 0.268s (= 53.518s / 200, num_workers=1)
PyTorch swin dataloader time: 0.151s (= 30.149s / 200, num_workers=1)
Relative speed: 0.563 (= 0.151s / 0.268s)

OneFlow swin dataloader time: 0.075s (= 14.975s / 200, num_workers=4)
PyTorch swin dataloader time: 0.042s (= 8.430s / 200, num_workers=4)
Relative speed: 0.563 (= 0.042s / 0.075s)

OneFlow swin dataloader time: 0.062s (= 12.313s / 200, num_workers=8)
PyTorch swin dataloader time: 0.022s (= 4.383s / 200, num_workers=8)
Relative speed: 0.356 (= 0.022s / 0.062s)

❌ OneFlow resnet50 time: 144.9ms (= 14488.3ms / 100, input_shape=[16, 3, 224, 224], ddp, world size=2)
PyTorch resnet50 time: 170.1ms (= 17011.8ms / 100, input_shape=[16, 3, 224, 224], ddp, world size=2)
✔️ Relative speed: 1.17 (= 170.1ms / 144.9ms)

OneFlow resnet50 time: 93.2ms (= 9319.3ms / 100, input_shape=[8, 3, 224, 224], ddp, world size=2)
PyTorch resnet50 time: 113.6ms (= 11360.1ms / 100, input_shape=[8, 3, 224, 224], ddp, world size=2)
✔️ Relative speed: 1.22 (= 113.6ms / 93.2ms)

OneFlow resnet50 time: 69.6ms (= 13925.9ms / 200, input_shape=[4, 3, 224, 224], ddp, world size=2)
PyTorch resnet50 time: 87.7ms (= 17531.0ms / 200, input_shape=[4, 3, 224, 224], ddp, world size=2)
✔️ Relative speed: 1.26 (= 87.7ms / 69.6ms)

OneFlow resnet50 time: 56.9ms (= 11389.2ms / 200, input_shape=[2, 3, 224, 224], ddp, world size=2)
PyTorch resnet50 time: 74.5ms (= 14891.4ms / 200, input_shape=[2, 3, 224, 224], ddp, world size=2)
✔️ Relative speed: 1.31 (= 74.5ms / 56.9ms)

OneFlow resnet50 time: 51.4ms (= 10272.8ms / 200, input_shape=[1, 3, 224, 224], ddp, world size=2)
PyTorch resnet50 time: 68.2ms (= 13647.9ms / 200, input_shape=[1, 3, 224, 224], ddp, world size=2)
✔️ Relative speed: 1.33 (= 68.2ms / 51.4ms)