dummpy h100 config

gpu-simulator/configs/tested-cfgs/SM90_H100/trace.config

@@ -0,0 +1,23 @@
+-trace_opcode_latency_initiation_int 2,2
+-trace_opcode_latency_initiation_sp 2,1
+-trace_opcode_latency_initiation_dp 64,64
+-trace_opcode_latency_initiation_sfu 21,8
+-trace_opcode_latency_initiation_tensor 32,32
+
+#execute branch insts on spec unit 1
+#<enabled>,<num_units>,<max_latency>,<ID_OC_SPEC>,<OC_EX_SPEC>,<NAME>
+-specialized_unit_1 1,4,4,4,4,BRA
+-trace_opcode_latency_initiation_spec_op_1 4,4
+
+#TEX unit, make fixed latency for all tex insts
+-specialized_unit_2 1,4,200,4,4,TEX
+-trace_opcode_latency_initiation_spec_op_2 200,4
+
+#tensor unit
+-specialized_unit_3 1,4,32,4,4,TENSOR
+-trace_opcode_latency_initiation_spec_op_3 32,32
+
+#UDP unit, for turing and above
+#for more info about UDP, see https://www.hotchips.org/hc31/HC31_2.12_NVIDIA_final.pdf
+-specialized_unit_4 1,4,4,4,4,UDP
+-trace_opcode_latency_initiation_spec_op_4 4,1