Stack from ghstack (oldest at bottom):

• -> [inductor] [cpp] fix gemm_output_name conflict #136419
• [inductor] [cpp] fix the check of template_buffer_has_other_users if no epilogue_nodes #136518
• [inductor] [cpp] fix max-autotune for single-thread dynamic shapes #136418

Fixes the max-autotune failure of soft_actor_critic of Torchbench in FP32 single thread dynamic shape case:

  File "/home/user/inductor/pytorch/torch/_inductor/codegen/cpp_micro_gemm.py", line 136, in codegen_call
    C_ptr = f"&({kernel.index(C, [0, 0])})"
  File "/home/user/inductor/pytorch/torch/_inductor/codegen/cpp_template_kernel.py", line 135, in index
    else self.args.input(node.get_name())
  File "/home/user/inductor/pytorch/torch/_inductor/codegen/common.py", line 1251, in input
    assert name not in V.graph.removed_buffers, name
AssertionError: buf_GemmOut

The 1st and 2nd linear does not need to use local buffer while the 3rd linear needs to use local buffer.
The 3rd linear which uses local buffer will add its global buffer (named as buf_GemmOut) into V.graph.removed_buffers.

When scheduling the nodes, the 1st linear (won't use local buffer) will get its output buffer (also named as buf_GemmOut) from the input and found that it's in the V.graph.removed_buffers and raise AssertionError. The issue is that the output buffer of all these linears are all names with buf_GemmOut, which have a conflict.

Rename these buffers by adding the name of the template_buffer as the prefix.

cc @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @ipiszy @yf225 @chenyang78 @kadeng @muchulee8 @ColinPeppler @amjames @desertfire @chauhang