Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMGE (vector, zero, 2D)

Test 1: uops

Code:

  fcmge v0.2d, v0.2d, #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)0308181e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696b6d6edispatch 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371700061168625100010001000264521020180203720371571718951000100010002037203711100110000073116111786100020382038203820382038
100420371800061168625100010001000264521020180203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371800061168625100010001000264521020180203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203718000278168625100010001000264521020180203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371800061168625100010001000264521020180203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371700061168625100010001000264521020180203720371571318951000100010002037203711100110001073116111786100020382038203820382038
1004203717002161168625100010001000264521020180203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371800061168625100010001000264521020180203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371600061168625100010001000264521020180203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371600061168625100010001000264521020180203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmge v0.2d, v0.2d, #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)031e3a3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000348196864510100100100121091000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001001907101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010047607101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000027101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371503061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03070b191e1f3f4e51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000023706119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000102006402162219786010000102003820038200382003820038
1002420037150000006119686251001010100001010000502847521020018200372003718443318785100102010000201000020085200371110021109101010000101006402166619786010000102003820038200382003820038
1002420037150000006119686251001010100001010000602847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
10024200371500000072619686251001010100001010000502847521020018200372003718443318767100122010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
1002420037150000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006422162219786010000102003820038200382003820038
10024200371500002106119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200862003820038
1002420037150000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
10024200371500100025219686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100036402162219786010000102003820038200382003820038
1002420037150100006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786010000102003820038200382003820038
1002420037150000006119686251001010100001010000502847521020018200372003718443318767100102010000201000020037200371110021109101010000100006402162219786210000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fcmge v0.2d, v8.2d, #0
  fcmge v1.2d, v8.2d, #0
  fcmge v2.2d, v8.2d, #0
  fcmge v3.2d, v8.2d, #0
  fcmge v4.2d, v8.2d, #0
  fcmge v5.2d, v8.2d, #0
  fcmge v6.2d, v8.2d, #0
  fcmge v7.2d, v8.2d, #0
  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)030b181e1f3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042004815000002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010005711151182160020098800001002003920039200392003920039
802042003814900002192580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180290020035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0309181e3f51inst 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)9fa0a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242006915000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020716642003580000102003920039200392003920039
80024200381500003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000001505020316352003580000102003920039200392003920039
800242003815000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020516532003580000102003920039200392003920039
800242003815000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020516572003580000102003920039200392003920039
8002420038150000134258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020416352003580000102003920039200392003920039
80024200381500018639258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020516352003580000102003920039200392003920039
800242003815000039258001012800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020316352003580000102003920039200392003920039
800242003815000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020516552003580000102003920039200392003920039
80024200381500003947258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020516452003580000102003920039200392003920039
800242003815000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020616572003580000102003920039200392003920039