Apple M1 Microarchitecture Research by Dougall Johnson

Firestorm: Overview | Base Instructions | SIMD and FP Instructions
Icestorm:  Overview | Base Instructions | SIMD and FP Instructions

CNT (16B)

Test 1: uops

Code:

  cnt v0.16b, v0.16b
  movi v0.16b, 1
  movi v1.16b, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037160126168625100010001000264521201820372037157131895100010001000203720371110011000073216231786100020382038203820382038
1004203715061168625100010001000264521201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
1004203715061168625100010001000264521201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
10042037152161168625100010001000264521201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
1004203715061168625100010001000264521201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
1004203715061168625100010001000264521201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
10042037150215168625100010001000264521201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
1004203716082168625100010001000264521201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
1004203715061168625100010001000264521201820372037157131895100010001000203720371110011000073216221786100020382038203820382038
1004203715061168625100010001000264521201820372037157131895100010001000203720371110011000073216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  cnt v0.16b, v0.16b
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03090b1e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000180611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000180611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100001871011611197910100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715000180611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200841500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150300103196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037151222061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500082196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715018061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001003640216221978610000102003820038200382003820038
100242003715000232196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715030061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150507061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cnt v0.16b, v8.16b
  cnt v1.16b, v8.16b
  cnt v2.16b, v8.16b
  cnt v3.16b, v8.16b
  cnt v4.16b, v8.16b
  cnt v5.16b, v8.16b
  cnt v6.16b, v8.16b
  cnt v7.16b, v8.16b
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)031e1f3a3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa6a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003815060029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100002528111511801600200350800001002003920039200392003920039
8020420038150000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801600200350800001002003920039200392003920039
8020420038150900292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801600200350800001002003920039200392003920039
8020420038150000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801600200350800001002003920039200392003920039
80204200381502400292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801600200350800001002003920039200392003920039
802042003815002640292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801600200350800001002003920039200392003920039
802042003815032400292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801600200350800001002003920039200392003920039
8020420038150000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801600200350800001002003920039200392003920039
8020420038150000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801600200350800001002003920039200392003920039
80204200381500005042580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801600200350800001002003920039200392003920039

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)0307080a0b18191e1f3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)5f60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200381500000002403925800101080000108000050640000012001920038200389989310011800102080000208000020038200381180021109101080000100000000050207167720035080000102003920039200392003920039
8002420038150000000162883925800101080000108000050640000012001920038200389989310011800102080000208000020038200381180021109101080000100002000050207165720035080000102003920039200392003920039
80024200381500000001503925800101080000108000050640000012001920038200389989310011800102080000208000020038200381180021109101080000100000000050205165720035080000102003920039200392003920039
80024200381500000001503925800101080000108000050640000012001920038200389989310011800102080000208000020038200381180021109101080000100000000050207165720035080000102003920039200392003920039
80024200381500000001803925800101080000108000050640000012001920038200389989310011800102080000208000020038200381180021109101080000100000000050205165720035080000102003920039200392003920039
80024200381500000001203925800101080000108000050640000012001920038200389989310011800102080000208000020038200381180021109101080000100000000050207165720035080000102003920039200392003920039
80024200381500000001203925800101080000108000050640000012001920038200389989310011800102080000208000020038200381180021109101080000100000000050207167520035080000102003920039200392003920039
80024200381500000003603925800101080000108000050640000012001920038200389989310011800102080000208000020038200381180021109101080000100000000050205165720035080000102003920039200392003920039
80024200381500000001203925800101080000108000050640000012001920038200389989310011800102080000208000020038200381180021109101080000100000000050207167520035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000112001920038200389989310011800102080000208000020038200381180021109101080000100000000050207167520035080000102003920039200392003920039