Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMGT (vector, zero, 2S)

Test 1: uops

Code:

  fcmgt v0.2s, v0.2s, #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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371606116862510001000100026452112018203720371571318951000100010002037203711100110000673116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100001873116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715126116862510001000100026452112018203720371571318951000100010002037203711100110001073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000673116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000373116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmgt v0.2s, v0.2s, #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)0318191e1f3f4e51inst 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)696b6d6edispatch 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150003061196862510100100100001001000050028475212001802003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000423196862510100100100001001000050028475212001802003720037184213187451010020010000200100002003720037111020110099100100100001000507101161119791100001002003820038200382003820038
10204200371500000166196862510100100100001001000050028475212001802003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475212001802003720037184213187451010020010000200100002003720037111020110099100100100001000037101161119791100001002003820038200382003820038
10204200371500000124196862510100100100001001000050028475212001802003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119855100001002003820038200382003820038
10204200371500000187196862510100100100001001000050028475212001802003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000168196862510100100100001001000050028475212001802003720037184213187451010020010000200100002003720037111020110099100100100001000037101161119791100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475212001802003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475212001802003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000124196862510100100100001001000050028475212001802003720037184213187451010020010000200100002003720037111020110099100100100001000037101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03081e3f4e51inst 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)9fa6accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
100242003715000611968625100101010000101000050284752112001820037200371844331876710010201000020100002016820037111002110910101000010006402242219786010000102003820038200382003820038
1002420037150004921968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
100242003715000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
100242003715000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
100242003715000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
1002420037150006711968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
1002420037150009431968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
100242003715000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038
1002420037150002751968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fcmgt v0.2s, v8.2s, #0
  fcmgt v1.2s, v8.2s, #0
  fcmgt v2.2s, v8.2s, #0
  fcmgt v3.2s, v8.2s, #0
  fcmgt v4.2s, v8.2s, #0
  fcmgt v5.2s, v8.2s, #0
  fcmgt v6.2s, v8.2s, #0
  fcmgt v7.2s, v8.2s, #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)031e3f51inst 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
80204200591500292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500712580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381490712580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500712580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002010520039200392003920039
80204200381500292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001001011151181160020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e3f51inst 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)9fa1a8a9acc5cficache miss (d3)d5d6ddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050150000051392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000005020041643200350080000102003920039200392003920039
80024200381500000258392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000005020041643200350080000102003920039200392003920039
8002420038150000012392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000005020041644200350080000102003920039200392003920039
800242003815000000392580010108000010800005064000000200192018820038999631001880010208000020800002003820038118002110910108000010000005020031645200350080000102003920039200642003920039
800242003815000000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000005020041644200350080000102003920039200392003920039
8002420038150000003925800101080000108000050640000012001920038200389996310018800102080000208000020038200381180021109101080000100000050200416342003522080000102003920039200392003920039
8002420038150000024392580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000005020031645200350080000102003920039200392003920039
800242003815000000392580010108000010800005064000000200192003820038999631001880010208000020800002003820038118002110910108000010000005020031635200350080000102003920039200392003920039
8002420038150000039398280102108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000005020041634200350080000102003920039200392003920039
8002420038150000002292580010108000010800005064000001200192003820038999631001880010208000020800002003820038118002110910108000010000005020041634200350080000102003920039200392003920039