Apple M1 Microarchitecture Research by Dougall Johnson

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

FNMUL (scalar, D)

Test 1: uops

Code:

  fnmul d0, d0, d1
  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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004403731061340725100010001000531908040184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
1004403730061340725100010001000531908040184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
1004403730061340725100010001000531908040184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
1004403731061340725100010001000531908040184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
1004403730061340725100010001000531908040184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
1004403730061340725100010001000531908040184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
1004403731061340725100010001000531908040184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
1004403730061340725100010001000531908040184037403732583389510001000200040374037111001100000073116113473100040384038403840384038
1004403730061340725100010001000531908040184037403732583389510001000200040374037111001100060073116113473100040384038403840384038
1004403730061340725100010001000531908140184037403732583389510001000200040374037111001100000073116113473100040384038403840384038

Test 2: Latency 1->2

Code:

  fnmul d0, d0, d1
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037299000000187394072510100100100001001000050057069081400184003740037381083387451010020010000200200004003740037111020110099100100100001000000071011611394790100001004003840038400384003840038
102044003730000000061394072510100100100001001000050057069081400184003740037381083387451072120010000200200004003740037111020110099100100100001000000071011611394790100001004003840038400384003840038
1020440037300000000251394072510100100100001001000050057069080400184003740037381083387451010020010000200200004003740037111020110099100100100001000000071011611394790100001004003840038400384003840038
102044003730000000061394072510100100100001001000050057069081400534003740037381083387451010020010000200200004003740037111020110099100100100001000000071011611394790100001004003840038400384003840038
102044003729900000061394072510100105100061001000050057069081400534003740310381083387631042520210000200200004003740037111020110099100100100001000000071031611394790100001004003840038400384003840038
102044003731000000010123940744101001001000010010000500570690814001840037400373810833874510100200100002002000040037400371110201100991001001000010000014318073911611394790100001004003840038400384003840471
10204400863100000301033940725101001001000010010000500570690814001840037403223810861388001010020010000200200004003740037111020110099100100100001000120271011611394790100001004003840038400384003840038
102044032431510000010339389641010010010000100107409645706908040053405604013338112338745101002001000022220000400374003711102011009910010010000100000307101112713957811100001004003840038400384056340038
10204400373110000001710394078410100100100001571000050057083880400184042040275381083387451010020010000234200004003740037111020110099100100100001000306471014921394790100001004003840038400384003840038
102044003730000000061394072510100106100001001000050057069080400184003740037381083387451010020010000200200004003740037111020110099100100100001000000071011611394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)03090b1e3f4e51inst 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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400372992002513940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000000640216223947310000104003840038400384003840038
1002440037300000613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000000640216223947310000104003840038400384003840038
1002440037300000893940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000000640216223947310000104003840038400384003840038
1002440037300000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000000640216223961710000104003840038400384003840038
1002440037300000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000006640216223947310000104003840038400384003840038
1002440037300000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000000640216223947310000104003840038400384003840038
1002440037300000613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000000640216223947310000104003840038400384003840038
1002440037299000613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000000640216223947310000104003840038400384003840038
1002440037300000613940725100101010000101000050570690814001840037400373813033876710010201000020200004008440037111002110910101000010000000640216223958110000104003840038400384003840038
1002440037299000613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000000640216223947310000104003840038400384003840038

Test 3: Latency 1->3

Code:

  fnmul d0, d1, d0
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)030818191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204400373000000061394072510100100100001001000050057069081400184003740037381083387451010020010000200200004003740037111020110099100100100001000000000071011611394790100001004003840038400384003840038
10204400373000000061394072510100100100001001000050057069081400184003740037381083387451010020010000200200004003740037111020110099100100100001000000000071011611394790100001004003840038400384003840038
1020440037300000495061394072510100100100001001000050057069081400184003740037381083387451010020010000200200004003740037111020110099100100100001000000000071011611394790100001004003840038400384003840038
10204400372990000076394072510100100100001001000050057069081400184003740037381083387451010020010000200200004003740037111020110099100100100001000000000071011611394790100001004003840038400384003840038
102044003730000000726394072510100100100001001000050057069081400184003740037381083387451010020010000200200004003740037111020110099100100100001000000000071011611394790100001004003840038400384003840038
10204400373000000061394072510100100100001001000050057069081400184003740037381083387451010020010000200200004003740037111020110099100100100001000000000071011611394790100001004003840038400384003840038
10204400373000000061394072510100100100001001000050057069081400184003740037381083387451010020010000200200004003740037111020110099100100100001000000000071011611394790100001004003840038400384003840038
1020440037300000591061394072510100100100001001000050057069081400184003740037381083387451010020010000200200004003740037111020110099100100100001000000000071011611394790100001004003840038400384003840038
10204400373000000061394072510100100100001001000050057069081400184003740037381083387451010020010000200200004003740037111020110099100100100001000000000071011611394790100001004003840038400384003840038
10204400373000000061394072510100100100001001000050057069081400184003740037381083387451010020010000200200004003740037111020110099100100100001000000000071011611394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003730000613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000640216423947310000104003840038400384003840038
100244003730000613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038
100244003730000613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000640216323947310000104003840038400384003840038
100244003730000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000640216323947310000104003840038400384003840038
100244003730000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000640216323947310000104003840038400384003840038
1002440037300001033940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000640216323947310000104003840038400384003840038
100244003730000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038
100244003730000613940725100101010000101000050570690814001840037400843813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038
100244003729900613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038
10024400373000062783940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000640216423947310000104003840038400384003840038

Test 4: throughput

Count: 8

Code:

  fnmul d0, d8, d9
  fnmul d1, d8, d9
  fnmul d2, d8, d9
  fnmul d3, d8, d9
  fnmul d4, d8, d9
  fnmul d5, d8, d9
  fnmul d6, d8, d9
  fnmul d7, d8, d9
  movi v8.16b, 9
  movi v9.16b, 10

(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)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)9fa0a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591500000004225801001008000010080000500640000200210200402004099733999880100200800002001600002004020040118020110099100100800001000000000511021611200370800001002004120041200412004120041
80204200401500000004225801001008000010080000500640000200210200402004099733999880100200800002001600002004020040118020110099100100800001000000000511011611200370800001002004120041200412004120041
80204200401500000004225801001008000010080000500640000200210200402004099733999880100200800002001600002004020040118020110099100100800001000000030511011611200370800001002004120041200412004120041
80204200401500000004225801001008000010080000500640000200210200402004099733999880100200800002001600002004020040118020110099100100800001000000000511011611200370800001002004120041200412004120041
80204200401500000004225801001008000010080000500640000200210200402004099733999880100200800002001600002004020040118020110099100100800001000000000511011621200370800001002004120041200412004120041
80204200401500000004225801001008000010080000500640000200210200402004099733999880100200800002001600002004020040118020110099100100800001000000000511011611200370800001002004120041200412004120041
80204200401500000004225801001008000010080000500640000200210200402004099733999880100200800002001600002004020040118020110099100100800001000000000512811611200370800001002009320041200412004120096
802042004015011004808425801001188000010880000500640000200210200402004099823100258010020080000200160000200402004021802011009910010080000100401424782512711611200370800001002004120094200942010220041
80204200941500000004225801001008000010080000500640000200210200402004099733999880100200800002001600002004020040118020110099100100800001000000000511011611200370800001002004120041200412004120041
80204200401500000004225801001008000010080000500640000200210200402004099733999880100200800002001600002004020040118020110099100100800001000000000511011611200370800001002004120041200412004120041

1000 unrolls and 10 iterations

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

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)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)9fa8cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420040150041258001010800001080000506400002002120040200409996310020800102080000201600002004020040118002110910108000010050200316442003780000102004120041200412004120041
8002420040150041258001010800001080000506400002002120040200409996310020800102080000201600002004020040118002110910108000010050200416352003780000102004120041200412004120041
8002420040150041258001010800001080000506400002002120040200409996310020800102080000201600002004020040118002110910108000010050200416442003780000102004120041200412004120041
8002420040150041258001010800001080000506400002002120040200409996310020800102080000201600002004020040118002110910108000010050200416332003780000102004120041200412004120041
8002420040150041258001010800001080000506400002002120040200409996310020800102080000201600002004020040118002110910108000010050200316442003780000102004120041200412004120041
8002420040160041258001010800001080000506400002002120040200409996310020800102080000201600002004020040118002110910108000010050200316352003780000102004120041200412004120041
80024200401500106258001010800001080000506400002002120040200409996310020800102080000201600002004020040118002110910108000010050200416432003780000102004120041200412004120041
8002420040150041258001010800001080000506400002002120040200409996310020800102080000201600002004020040118002110910108000010050200516552003780000102004120041200412004120041
8002420040150041258001010800001080000506400002002120040200409996310020800102080000201600002004020040118002110910108000010050200416342003780000102004120041200412004120041
8002420040150041258001010800001080000506400002002120040200409996310020800102080000201600002004020040118002110910108000010050200316532003780000102004120041200412004120041