Apple M1 Microarchitecture Research by Dougall Johnson

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

CMLT (zero, D)

Test 1: uops

Code:

  cmlt d0, d0, #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)03091e3f4e51inst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073216221828100020382038203820382038
1004203717006116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
1004203716006116862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
1004203716006116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
1004203716006116862510001000100026452112018203720371571318951000100010002037203711100110001073216221786100020382038203820382038
1004203716006116862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
1004203716006116862510001000100026452112018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
10042037150186116862510001000100026452102018203720371571318951000100010002037203711100110000073216221786100020382038203820382038
10042037150010316862510001000100026452112018203720371571318951000100010002037203711100110000373216221786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmlt d0, d0, #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)0308091e3f4e51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000361196644510133104100121171000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001002307101161319827100001002003820038200382003820038
102042008515000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001001007101161119791100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001001307101161119791100001002003820038200382003820038
102042003715000961196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000907101161119791100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000061196862510100100100001001000050028475211200652003720037184213187451010020010000200100002003720037111020110099100100100001001007101161119791100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010015007101161119791100001002003820038200382003820038
1020420037150000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010036307101161119791100001002003820038200382003820038

1000 unrolls and 10 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)696d6edispatch 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500145196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010010640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820085
1002420037150061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500762196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150082196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmlt d0, d8, #0
  cmlt d1, d8, #0
  cmlt d2, d8, #0
  cmlt d3, d8, #0
  cmlt d4, d8, #0
  cmlt d5, d8, #0
  cmlt d6, d8, #0
  cmlt d7, d8, #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)03081e3f51inst 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)9fa0a6a8acc5branch mispredict (cb)cdcfd5d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003815000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
80204200381500050425801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000316111511801620035800001002003920039200392003920039
8020420038150004732580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
802042003815000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
802042003815004774042580108100800081008002050064075602001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
802042003815100292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
802042003815000922580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
802042003815000712580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
8020420038150001762580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920039200392003920039
8020420038150001962580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000000111511801620035800001002003920100200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e1f3f51inst 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)9fa6a7a8acc2cficache miss (d3)d5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200401500003752580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100005080502006160562003580000102003920039200392003920039
8002420038150091083925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000000502007160552003580000102003920039200392003920039
800242003815000012725800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000000502005160452003580000102003920039200392003920039
800242003815000012325800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000000502004160452003580000102003920039200392003920039
80024200381500003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000100502005160562003580000102003920039200392003920039
800242003815000016725800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001020100502005160552003580000102003920039200392003920039
80024200381500003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000000502005160662003580000102003920039200392003920039
80024200381500003925800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000000502005160662003580000102003920039200392003920039
80024200381500003925800101080000108000050640000120019200382003899963100188001020800002080000200382008911800211091010800001000000502007160652003580000102003920039200392003920039
80024200381500008125800101080000108000050640000120019200382003899963100188001020800002080000200382003811800211091010800001000000502005160552003580000102003920039200392003920039