Apple M1 Microarchitecture Research by Dougall Johnson

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

CMGT (zero, 8B)

Test 1: uops

Code:

  cmgt v0.8b, v0.8b, #0
  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)60696d6edispatch 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)a0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715082168625100010001000264521120182037203715713189510001000100020372037111001100000073216211786100020382038203820382038
10042037150105168625100010001000264521120182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073216331786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073216331786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073216221786100020382038203820382038
1004203716061168625100010001000264521120182037203715713189510001000100020372037111001100000073216331786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000073116331786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100000373216221841100020382038203820382038
10042037150105168625100010001000264521020182037203715713189510001000100020372037111001100000073216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmgt v0.8b, v0.8b, #0
  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)031e3f4e51inst 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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715001031968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030818191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000821968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006405162219786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
10024200371500000002511968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038
1002420037150000000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmgt v0.8b, v8.8b, #0
  cmgt v1.8b, v8.8b, #0
  cmgt v2.8b, v8.8b, #0
  cmgt v3.8b, v8.8b, #0
  cmgt v4.8b, v8.8b, #0
  cmgt v5.8b, v8.8b, #0
  cmgt v6.8b, v8.8b, #0
  cmgt v7.8b, v8.8b, #0
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)03080b18191e1f3f51inst 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)9fa0a1acc5branch mispredict (cb)cdcfd5d6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420061150001200292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118116020035800001002003920039200392003920039
8020420094150000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038518020110099100100800001000001115118016020035800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000201115118016020035800001002003920039200392003920039
8020420038150000000292580108100800081008022150064013202001920038200389977699898012020080032200800322003820087218020110099100100800001000001115118016020035800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
8020420038150000000292580108100800081008002050064242802001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
8020420038150000300292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038518020110099100100800001000001115118016020035800001002003920039200392003920039
8020420038150000000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03091e1f3f51inst 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)9fcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050150000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000105020616552003580000102003920039200392003920039
8002420038150000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000105020516542003580000102003920039200392003920039
8002420038150000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000105020416542003580000102003920039200392003920039
8002420038150000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000105020516452003580000102003920039200392003920039
8002420038150000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000105020416552003580000102003920039200392003920039
8002420038150000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000105020416542003580000102003920039200392003920039
8002420038150000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000105020516552003580000102003920039200392003920039
8002420038150000392580010108009310800005064000012001920038200389996310018800102080000208000020038200381180021109101080000105020516552003580000102003920039200392003920039
8002420038150000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000105020516542003580000102003920039200392003920039
8002420038150000602580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000105020516552003580000102003920039200392003920039