Apple M1

Apple M1 (4x Firestorm 3200 MHz + 4x Icestorm 2064 MHz), RAM: 16 GB, 8x 16-bit LPDDR4X-4266.

Icestorm (Small Core):

L1 Data cache = 64 KB, ? B/line, ?-WAY.
L1 Instruction cache = 128 KB, ? B/line, ?-WAY.
L2 Cache = 4 MB (per 4 cores), ? B/line, ?-WAY.

Firestorm (Big Core):

L1 Data cache = 128 KB, 64 B/line, ?-WAY.
L1 Instruction cache = 192 KB, ? B/line, ?-WAY.
L2 Cache = 12 MB (per 4 cores), 128 ? B/line, ?-WAY.

L1 Data Cache Latency = 3 cycles for simple access via pointer
L1 Data Cache Latency = 4 cycles for access with complex address calculation (size_t n, *p; n = p[n]).

L2 Cache Latency = 18 cycles

Shared Cache:

L3 Cache = 8 MB (shared for all clusters), 128 ? B/line, ?-WAY. Exclusive ? with L2 Cache.

L3 Cache Latency = 18 cycles + (10-15 ns) : for Firestorm - Big Core

RAM Latency = 18 cycles + 91 ns : for Firestorm - Big Core

16 KB pages mode (Firestorm - Big Core)

Data TLB L1: 160 items. ?-way? Miss penalty = 6 cycles. Parallel miss: 1.35 cycles per access
Data TLB L2: 3K items. ?-way. Miss penalty = 26 cycles (page walk to L2 cache ? ). Parallel miss: 6.4 cycles per access (including L2 cache access for data and page walk).
page directory cache: cover 768 MB = (24 items * 32 MB block). Miss penalty = 24 ? cycles (page walk to L2 cache ? ).

  Size       Latency        Increase   Description

 128 K     3                           
 256 K    11               8           + 15 (L2)
 512 K    15               4   
   1 M    16               1
   2 M    17               1           
   4 M    20               3           + 6 (L1 TLB miss)        
   8 M    23               3 
  16 M    24 +  9 ns       1 +  9 ns   
  32 M    24 + 44 ns       0 + 35 ns   + 91 ns (RAM) 
  64 M    32 + 66 ns       8 + 22 ns   + 26 (L2 TLB miss)
 128 M    42 + 78 ns      10 + 12 ns   
 256 M    46 + 85 ns       4 +  7 ns
 512 M    48 + 88 ns       2 +  3 ns
   1 G    55 + 90 ns       7 +  2 ns   + 24 (directory cache miss)
   2 G    64 + 91 ns       9 +  1 ns

MISC (Firestorm - Big Core)

Branch misprediction penalty = 13 cycles

8-bytes range cross penalty = 1 cycle

L1 B/W (Parallel Random Read) = 0.34 cycles per one access
L1 Write throughput = 0.5 cycles per one write

L2->L1 B/W (Parallel Random Read) = 2.0 cycles per cache line
L2->L1 B/W (Read, 64 bytes step) = 2.0 cycles per cache line
L2->L1 B/W (Read, 64 Bytes step - pointer chasing) = ? cycles per cache line (HW prefetch)
L2 Write (Write, 64 bytes step) = 2.0 cycles per write

L3->L1 B/W (Parallel Random Read) = 5 cycles per cache line
L3->L1 B/W (Read, 64 bytes step) = ? cycles per cache line
L3->L1 B/W (Read, 64 Bytes step - pointer chasing) = ? cycles per cache line (HW prefetch)
L3 Write (Write, 64 bytes step) = ? cycles per write

RAM Read B/W (Parallel Random Read) = 4 ns / access line (128 bytes ?)
RAM Read B/W (Read, 16-64 Bytes step) = 64 GB/s
RAM Read B/W (Read, 64 Bytes step - pointer chasing) = 52 GB/s (HW prefetch)
RAM Write B/W (Write, full, 8 Bytes step) = 32-63 GB/s
RAM Write B/W (Write, partial, 16-64 Bytes step) = 29 GB/s

7-Zip Benchmark

Notes:

7z b : MIPS values are normalized with Intel Core 2 cpu.

7z b -mm=* : MIPS and Effectiveness values are normalized with AMD K8 cpu.


7-Zip (z) 21.03 beta (arm64) : Copyright (c) 1999-2021 Igor Pavlov : 2021-07-20
 64-bit arm_v:8 locale=en_US.UTF-8 Threads:8, ASM

 mt1
Compiler: Apple LLVM 12.0.5 (clang-1205.0.22.9) GCC 4.2.1 CLANG 12.0
Darwin : 20.4.0 : Darwin Kernel Version 20.4.0:
PageSize:16KB
Apple M1 8C8T 

1T CPU Freq (MHz):  3197  3202  3201  3200  3201  3196  3200

RAM size:   16384 MB,  # CPU hardware threads:   8
RAM usage:    437 MB,  # Benchmark threads:      1

                       Compressing  |                  Decompressing
Dict     Speed Usage    R/U Rating  |      Speed Usage    R/U Rating
         KiB/s     %   MIPS   MIPS  |      KiB/s     %   MIPS   MIPS

22:       9360   100   9106   9106  |      92791   100   7886   7923
23:       7681   100   7826   7826  |      92576   100   8013   8013
24:       6748   100   7227   7256  |      91972   100   8074   8074
25:       6210   100   7064   7091  |      90644    99   8113   8068
----------------------------------  | ------------------------------
Avr:      7500   100   7806   7820  |      91996   100   8022   8020
Tot:             100   7914   7920



2T CPU Freq (MHz): 199% 3092   199% 3091  

RAM size:   16384 MB,  # CPU hardware threads:   8
RAM usage:    444 MB,  # Benchmark threads:      2

                       Compressing  |                  Decompressing
Dict     Speed Usage    R/U Rating  |      Speed Usage    R/U Rating
         KiB/s     %   MIPS   MIPS  |      KiB/s     %   MIPS   MIPS

22:      19107   167  11084  18587  |     179284   200   7636  15307
23:      18679   186  10212  19032  |     178557   200   7710  15456
24:      18481   192  10226  19871  |     175908   200   7703  15443
25:      18154   193  10691  20728  |     171824   200   7627  15293
----------------------------------  | ------------------------------
Avr:     18605   184  10553  19555  |     176393   200   7669  15375
Tot:             192   9111  17465



4T CPU Freq (MHz): 399% 2983   399% 2984  

RAM size:   16384 MB,  # CPU hardware threads:   8
RAM usage:    889 MB,  # Benchmark threads:      4

                       Compressing  |                  Decompressing
Dict     Speed Usage    R/U Rating  |      Speed Usage    R/U Rating
         KiB/s     %   MIPS   MIPS  |      KiB/s     %   MIPS   MIPS

22:      33903   376   8692  32981  |     345453   400   7360  29472
23:      33015   402   8368  33639  |     341224   400   7381  29526
24:      32683   416   8387  35141  |     334122   400   7313  29322
25:      31855   413   8804  36372  |     326422   400   7254  29051
----------------------------------  | ------------------------------
Avr:     32864   402   8563  34533  |     336805   400   7327  29343
Tot:             401   7945  31938


RAM size:   16384 MB,  # CPU hardware threads:   8
RAM usage:   1779 MB,  # Benchmark threads:      8

                       Compressing  |                  Decompressing
Dict     Speed Usage    R/U Rating  |      Speed Usage    R/U Rating
         KiB/s     %   MIPS   MIPS  |      KiB/s     %   MIPS   MIPS

22:      51020   750   6559  49633  |     538251   795   5762  45898
23:      46106   727   6402  46977  |     529572   795   5757  45809
24:      45006   749   6452  48391  |     515399   788   5722  45221
25:      44111   759   6616  50365  |     505839   793   5664  45009
----------------------------------  | ------------------------------
Avr:     46561   747   6507  48841  |     522265   792   5726  45484
Tot:             770   6117  47163




 m=* mt1

1T CPU Freq (MHz):  3202  3198  3187  3201  3200  3200  3198

RAM size:   16384 MB,  # CPU hardware threads:   8
RAM usage:    227 MB,  # Benchmark threads:      1


Method           Speed Usage    R/U Rating   E/U Effec
                 KiB/s     %   MIPS   MIPS     %     %

CPU                      100   3205   3199
CPU                      100   3199   3199
CPU                      100   3188   3200   100   100

LZMA:x1          36891   100  13447  13600   424   425
                 93007   100   7440   7440   233   233
LZMA:x3          14926   100   9088   9171   286   287
                 91665   100   7693   7693   241   240
LZMA:x5:mt1       6759   100   8409   8444   263   264
                 92037   100   7727   7763   242   243
LZMA:x5:mt2      18523   191  12049  23141   379   723
                 92076   100   7766   7766   243   243
Deflate:x1       73983   100   9394   9394   294   294
                210712   100   6521   6547   204   205
Deflate:x5       24379   100   9387   9387   294   293
                211175   100   6530   6556   204   205
Deflate:x7        9531   100  10499  10561   330   330
                212455   100   6593   6593   206   206
Deflate64:x5     21953   100   9423   9487   295   296
                210431   100   6582   6582   206   206
BZip2:x1         11558   100   6934   6983   218   218
                 60655   100   6575   6575   206   205
BZip2:x5         10868   101   8951   9071   281   283
                 54080   100  10614  10614   333   332
BZip2:x5:mt2     20218   194   8705  16873   272   527
                 73964   140  10302  14517   324   454
BZip2:x7          3076   100   7970   7970   249   249
                 54721   100  10731  10731   337   335
PPMD:x1           9075   100   9335   9386   293   293
                  8270   100   9739   9739   305   304
PPMD:x5           7101   100  12036  12036   377   376
                  6315   101  11744  11834   368   370
Delta:4        3930908   100  12076  12076   378   377
                856569   100   3509   3509   110   110
BCJ            2360312   100   9614   9668   302   302
               2425885   100   9879   9936   310   311
AES256CBC:1     241976   100   5926   5947   186   186
                277607   100   6822   6822   214   213
AES256CBC:2    1037874   100   8460   8502   264   266
              10494305   100  10679  10746   336   336
AES256CBC:3 

CRC32:1         390617   100   2848   2844    89    89
CRC32:4        1237350   100   2757   2762    86    86
CRC32:8        1767907   100   2394   2397    75    75
CRC32:32       4167766   100   2134   2134    67    67
CRC32:64       8340065   100   2135   2135    67    67
CRC64          1123966   100   2302   2302    72    72
SHA256:1        334194   100   6764   6818   212   213
SHA256:2       2154461   100   4481   4481   140   140
SHA1:1          766750   100   7177   7177   225   224
SHA1:2         2245556   100   4361   4383   137   137
BLAKE2sp        552250   100  12150  12150   381   380

CPU                      100   3200   3200
------------------------------------------------------
Tot:                       7   8558   9962  4632   311


 m=* mt8

1T CPU Freq (MHz):  3202  3200  3201  3199  3200  3200  3199
4T CPU Freq (MHz): 399% 2983   399% 2983  

RAM size:   16384 MB,  # CPU hardware threads:   8
RAM usage:   1823 MB,  # Benchmark threads:      8


Method           Speed Usage    R/U Rating   E/U Effec
                 KiB/s     %   MIPS   MIPS     %     %

CPU                      793   2526  20052
CPU                      796   2526  20093
CPU                      789   2527  19963   101   800

LZMA:x1         160358   790   7464  59115   300  2369
                544998   793   5484  43587   220  1747
LZMA:x3          49446   793   3830  30380   154  1217
                527433   794   5566  44248   223  1773
LZMA:x5:mt1      31509   793   4955  39364   199  1577
                519169   795   5490  43771   221  1754
LZMA:x5:mt2      45586   793   7166  56951   288  2282
                514217   786   5498  43353   221  1737
Deflate:x1      413383   788   6643  52490   267  2103
               1197279   796   4671  37197   187  1491
Deflate:x5      131765   794   6358  50733   256  2033
               1198855   795   4673  37214   188  1491
Deflate:x7       50081   793   6979  55488   280  2224
               1206890   794   4709  37448   189  1501
Deflate64:x5    119239   795   6456  51527   260  2065
               1195602   794   4698  37389   189  1498
BZip2:x1         65020   795   4929  39283   198  1574
                350232   795   4765  37962   191  1521
BZip2:x5         53197   787   5630  44396   226  1779
                264370   789   6548  51882   263  2079
BZip2:x5:mt2     52544   790   5540  43851   222  1757
                270285   790   6700  53043   269  2126
BZip2:x7         16352   795   5327  42365   214  1698
                263319   786   6550  51632   263  2069
PPMD:x1          48469   794   6307  50129   253  2009
                 44031   790   6548  51852   263  2078
PPMD:x5          29516   790   6328  50022   254  2005
                 27012   790   6403  50620   257  2029
Delta:4       19560091   791   7573  60089   304  2408
               5630375   674   3419  23062   137   924
BCJ           12569112   791   6484  51483   261  2063
              13072910   793   6733  53547   271  2146
AES256CBC:1    1412581   795   4359  34716   175  1391
               1541264   795   4756  37878   191  1518
AES256CBC:2    6677083   795   6872  54699   276  2192
              50887730   776   6695  52109   269  2088
AES256CBC:3 

CRC32:1        2455264   796   2242  17874    90   716
CRC32:4        7926194   797   2218  17691    89   709
CRC32:8       11236307   793   1921  15236    77   611
CRC32:32      26057872   791   1686  13342    68   535
CRC32:64      52423286   797   1685  13420    68   538
CRC64          6975012   795   1796  14285    72   572
SHA256:1       1816771   794   4656  37062   187  1485
SHA256:2      13665981   788   3604  28425   145  1139
SHA1:1         4230588   797   4968  39598   199  1587
SHA1:2        13635641   792   3358  26617   135  1067
BLAKE2sp       2855657   791   7917  62824   318  2518

CPU                      793   2524  20038
------------------------------------------------------
Tot:                      51   5534  43917  3475  1760

Links

Apple M1 at Wikipedia