Skip to content

Add sm_89 (Ada) support and RTX 4060 Laptop config #548

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
dzwduan wants to merge 1 commit into
base: dev
Choose a base branch
from
Open

Add sm_89 (Ada) support and RTX 4060 Laptop config #548

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions gpu-simulator/ISA_Def/ampere_opcode.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@

#define AMPERE_RTX_BINART_VERSION 86
#define AMPERE_A100_BINART_VERSION 80
#define ADA_RTX_BINART_VERSION 89

// TO DO: moving this to a yml or def files

Expand Down
23 changes: 23 additions & 0 deletions gpu-simulator/configs/tested-cfgs/SM89_RTX4060_LAPTOP/trace.config
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -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
3 changes: 2 additions & 1 deletion gpu-simulator/trace-driven/trace_driven.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,7 +103,8 @@ trace_kernel_info_t::trace_kernel_info_t(dim3 gridDim, dim3 blockDim,

// resolve the binary version
if (kernel_trace_info->binary_verion == AMPERE_RTX_BINART_VERSION ||
kernel_trace_info->binary_verion == AMPERE_A100_BINART_VERSION)
kernel_trace_info->binary_verion == AMPERE_A100_BINART_VERSION ||
kernel_trace_info->binary_verion == ADA_RTX_BINART_VERSION)
OpcodeMap = &Ampere_OpcodeMap;
else if (kernel_trace_info->binary_verion == VOLTA_BINART_VERSION)
OpcodeMap = &Volta_OpcodeMap;
Expand Down
4 changes: 4 additions & 0 deletions util/job_launching/configs/define-standard-cfgs.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,10 @@ TITANK:
RTX3070:
base_file: "$GPGPUSIM_ROOT/configs/tested-cfgs/SM86_RTX3070/gpgpusim.config"

#Ada RTX 4060 Laptop
RTX4060:
base_file: "$GPGPUSIM_ROOT/configs/tested-cfgs/SM89_RTX4060_LAPTOP/gpgpusim.config"

#Turing
RTX2060:
base_file: "$GPGPUSIM_ROOT/configs/tested-cfgs/SM75_RTX2060/gpgpusim.config"
Expand Down