diff options
| author | tgrogers <[email protected]> | 2018-02-21 22:46:20 -0500 |
|---|---|---|
| committer | tgrogers <[email protected]> | 2018-02-21 22:46:20 -0500 |
| commit | 71d9ada37b64360a216dbceef5b7a26a6cab8480 (patch) | |
| tree | ac0180ec5fb467ea54cea51f9105c4c76e3ac26e /configs/GeForceGTX750Ti | |
| parent | 7796a731c2a7d14a58d1369af62c8ad589c63921 (diff) | |
| parent | 4a94401a277342cfd0799863b1a07abc95f954c7 (diff) | |
merging in the mainline
Diffstat (limited to 'configs/GeForceGTX750Ti')
| -rw-r--r-- | configs/GeForceGTX750Ti/gpgpusim.config | 17 |
1 files changed, 9 insertions, 8 deletions
diff --git a/configs/GeForceGTX750Ti/gpgpusim.config b/configs/GeForceGTX750Ti/gpgpusim.config index 8b030b6..9366f93 100644 --- a/configs/GeForceGTX750Ti/gpgpusim.config +++ b/configs/GeForceGTX750Ti/gpgpusim.config @@ -28,10 +28,11 @@ -gpgpu_simd_model 1 # Pipeline widths and number of FUs -# ID_OC_SP,ID_OC_SFU,ID_OC_MEM,OC_EX_SP,OC_EX_SFU,OC_EX_MEM,EX_WB --gpgpu_pipeline_widths 2,1,1,2,1,1,2 +# ID_OC_SP,ID_OC_DP,ID_OC_SFU,ID_OC_MEM,OC_EX_SP,OC_EX_DP,OC_EX_SFU,OC_EX_MEM,EX_WB +-gpgpu_pipeline_widths 2,0,1,1,2,0,1,1,2 -gpgpu_num_sp_units 8 -gpgpu_num_sfu_units 32 +-gpgpu_num_dp_units 0 # Instruction latencies and initiation intervals # "ADD,MAX,MUL,MAD,DIV" @@ -42,21 +43,21 @@ -ptx_opcode_latency_dp 8,19,8,8,330 -ptx_opcode_initiation_dp 8,16,8,8,130 --gpgpu_cache:dl1 32:128:4,L:L:m:N:H,A:32:8,8 +-gpgpu_cache:dl1 N:32:128:4,L:L:m:N:H,A:32:8,8 -gmem_skip_L1D 1 -gpgpu_shmem_size 65536 # The alternative configuration for fermi in case cudaFuncCachePreferL1 is selected -#-gpgpu_cache:dl1 64:128:6,L:L:m:N:H,A:32:8,8 +#-gpgpu_cache:dl1 N:64:128:6,L:L:m:N:H,A:32:8,8 #-gpgpu_shmem_size 16384 # 1024 sets, each 128 bytes 8-way for each memory sub partition. This gives 2MB L2 cache --gpgpu_cache:dl2 1024:128:8,L:B:m:W:L,A:32:4,4:0,32 +-gpgpu_cache:dl2 N:1024:128:8,L:B:m:W:L,A:32:4,4:0,32 -gpgpu_cache:dl2_texture_only 0 --gpgpu_cache:il1 4:128:4,L:R:f:N:L,A:2:32,4 --gpgpu_tex_cache:l1 16:128:32,L:R:m:N:L,F:128:4,128:2 --gpgpu_const_cache:l1 64:64:2,L:R:f:N:L,A:2:32,4 +-gpgpu_cache:il1 N:4:128:4,L:R:f:N:L,A:2:32,4 +-gpgpu_tex_cache:l1 N:16:128:32,L:R:m:N:L,F:128:4,128:2 +-gpgpu_const_cache:l1 N:64:64:2,L:R:f:N:L,A:2:32,4 # enable operand collector -gpgpu_operand_collector_num_units_sp 6 |