Apple M1 Microarchitecture Research by Dougall Johnson

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

FMADD (scalar, D)

Test 1: uops

Code:

  fmadd d0, d0, d1, d2
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(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)696d6edispatch 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
10044037300613407251000100010005319084018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
10044037300613407251000100010005319084018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
10044037300823407251000100010005319084018403740373258338951000100030004037403711100110000091116113473100040384038403840384038
10044037300613407251000100010005319084018403740373258338951000100030004037403711100110000673116113473100040384038403840384038
10044037310613407251000100010005319084018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
10044037300613407251000100010005319084018403740373258338951000100030004037403711100110000373116113473100040384038403840384038
10044037300613407251000100010005319084018403740373258338951000100030004037403711100110000373116113473100040384038403840384038
100440373001533407251000100010005319084018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
10044037300613407251000100010005319084018403740373258338951000100030004037403711100110000073116113473100040384038403840384038
10044037300613407251000100010005319084018403740373258338951000100030004037403711100110001073116113473100040384038403840384038

Test 2: Latency 1->2

Code:

  fmadd d0, d0, d1, d2
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 4.0037

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)9facc2cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037300741061394072510100100100001001000050057069080400184003740037381083387451070420010000200300004003740037111020110099100100100001000071003162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000071002162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038
1020440037300621061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069080400184003740037381083387451055420010000200300004003740037111020110099100100100001000071013162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000071012162239479100001004003840038400384003840038
102044003729900726394072510100100100001001000050057069080400184003740037381083387451010020010000200300004003740037111020110099100100100001000071012162339479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

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)60696b6d6edispatch stall (70)72scheduler 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)9fa8a9branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002440037299061394072510010101000010100005057069081400180400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037300061394072510010101000010100005057069081400180400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037300061394072510010101000010100005057069081400180400374003738130733876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037300061394072510010101000010100005057069081400180400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
10024400373000251394072510010101000010100005057069081400180400374003738130033876710010201000020300004003740037111002110910101000010001640216233947310000104003840038400384003840038
1002440037300061394072510010101000010100005057069081400180400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037300061394072510010101000010100005057069081400180400374003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037300061394072510010101000010100005057069081400180400844003738130033876710010201000020300004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037300061394072510010101000010100005057069081400180400374003738130033876710010201000020300004003740037111002110910101000010300640216223947310000104003840038400384003840038
1002440037300061394072510010101000010100005057069081400180400374003738130033876710010201000020300004003740037111002110910101000010000640316223947310000104003840038400384003840038

Test 3: Latency 1->3

Code:

  fmadd d0, d1, d0, d2
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 4.0037

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)72scheduler 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)9faccfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204400373000061394072510100100100001001000050057069081400184003740037381080338745101002001000020430000400374003711102011009910010010000100071012162339479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069081400184003740037381080338745101002001000020030000400374003711102011009910010010000100071002162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069081400184003740037381080338745101002001000020030000400374003711102011009910010010000100071002162239479100001004003840038400384003840038
102044003729912061394072510100100100001001000050057069081400184003740037381080338745101002001000020030000400374003711102011009910010010000100071012162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069081400184003740037381080338745101002001000020030000400374003711102011009910010010000100071012162239479100001004003840038400384003840038
10204400372990061394072510100100100001001000050057069081400184003740037381080338745101002081000020030000400374003711102011009910010010000100075812162239479100001004003840038400384003840084
102044003730000168394072510100100100001001000050057069081400184003740037381080338745101002001000020030000400374003711102011009910010010000100071012162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069081400184003740037381080338745101002001000020030000400374003711102011009910010010000100071212162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057083041400184003740037381080338745101002001000020030000400374003711102011009910010010000100071012162239479100001004003840038400384003840038
10204400373000061394072510100100100001001014750057069081400184003740037381080338745101002001000020230000400374003711102011009910010010000100071212162039479100001004003840038400384003840038

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)9fa8a9accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002440085300006139407251001010100001010000505706908040018400374003738135338787100102010000203049840037400371110021109101010000100000640316223947310000104003840038400384003840038
10024400372990126139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
10024400373000010339407251001010100001010000505706908140018400374003738130338767100102010000203000040037400371110021109101010000100000640216223951210000104003840085400854022640086
10024401323000010339407251001610100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000101000640216223947310000104003840038400384003840038
10024400372990126139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100000640116223947310000104003840038400384003840038
100244003729901261394072510010101000010100005057069080400184003740037381303387671001020100002030000400374003751100211091010100001010144330640216223947310000104003840038400384003840038
10024400372990216139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
1002440037300006139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
1002440037300006139407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038
1002440037300008239407251001010100001010000505706908040018400374003738130338767100102010000203000040037400371110021109101010000100000640216223947310000104003840038400384003840038

Test 4: Latency 1->4

Code:

  fmadd d0, d1, d2, d0
  movi v0.16b, 1
  movi v1.16b, 2
  movi v2.16b, 3

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst 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)72scheduler 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)9fa0a1a6a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037300000000061394072510100100100001001000050057069084001840037400373810803387451010020010000200300004003740037111020110099100100100001000000000710021622394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069084001840037400373810803387451010020010000200300004003740037111020110099100100100001000000000710021623394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069084001840037400373810803387451010020010000200300004003740037111020110099100100100001000000000710121622394790100001004003840038400384003840038
10204400372990000000187394072510100100100001001000050057069084001840037400373810803387451010020010000200300004003740037111020110099100100100001000000000710121622394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000052257069084001840037400373810803387451010020010000200300004003740037111020110099100100100001000000000710121622394790100001004003840085400384003840038
1020440037300000000082394072510100100100001001000050057069084001840037400373810803387451010020010000200300004003740037111020110099100100100001000000000710121622394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069084001840037400373810803387451010020010000200300004003740037111020110099100100100001000000000710121622394790100001004003840038400384003840038
10204400373000000000156394072510100100100001001000050057069084001840037400373810803387451010020010000200300004003740037111020110099100100100001000000000710121622394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069084001840037400373810803387451010020010000200300004003740037111020110099100100100001000000000710121622394790100001004003840038400384003840038
1020440037300000000061394072510100100100001001000050057069084001840037400373810803387451010020010000200300004003740037111020110099100100100001000000000710121622394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

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)9fa1a6a8acc5cfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400372990006139407251001010100001010000505706908140018400374003738130338767100102010000203000040037400371110021109101010000100001506402162339473010000104003840038400384003840038
1002440037300000613940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010000906402162239473110000104003840038400384003840038
1002440037300000613940725100101010000101000050570690814001840037400373813033876710010201000020300004003740037111002110910101000010000306402162239473010000104003840038400384003840038
100244003730000061394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000013806402162239473010000104003840038400384003840038
100244003730000061394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100221091010100001000017706402162239473010000104003840038400384003840038
100244003730010090939407251001010100001010000505706908140018400374003738130338767100102010000203000040037400371110021109101010000100005406402162239473010000104003840038400384003840038
1002440037300000726394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000019506402162239473010000104003840038400384003840038
100244003730000061394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000019206402162239473010000104003840038400384003840038
100244003730000061394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000015006402162239480010000104003840038400384003840038
100244003730000061394072510010101000010100005057069081400184003740037381303387671001020100002030000400374003711100211091010100001000019206402162239473010000104003840038400384003840038

Test 5: throughput

Count: 8

Code:

  fmadd d0, d8, d9, d10
  fmadd d1, d8, d9, d10
  fmadd d2, d8, d9, d10
  fmadd d3, d8, d9, d10
  fmadd d4, d8, d9, d10
  fmadd d5, d8, d9, d10
  fmadd d6, d8, d9, d10
  fmadd d7, d8, d9, d10
  movi v8.16b, 9
  movi v9.16b, 10
  movi v10.16b, 11

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)0308090b18191e1f3f51inst 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)6061696d6edispatch 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)9fa0a6a8a9accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015000000004225801001008000010080000500640000102002120040200409973399988010020080000200240000200402004011802011009910010080000100001005110002162220037800001002004120041200412004120041
802042004015000000004225801001008000010080000500640000102002120040200409973399988010020080000200240000200402004011802011009910010080000100000005110002162220037800001002004120041200412004120041
80204200401500000012042258010010080000100800005006400001020021200402004099733100808010020080000200240000200402004011802011009910010080000100023005110002162220037800001002004120041200412004120041
802042004015000000004225801001008000010080000500640000052002120040200409973399988010020080000200240000200402004011802011009910010080000100000005110002162220037800001002004120041200412004120041
802042004015000000004225801001008000010080000500640000002002120040200409973399988010020080000200240000200402004011802011009910010080000100000005110002292220037800001002004120041200412004120041
802042004015000000004225801001008000010080000500640000002002120040200409973399988010020080000200240000200402004011802011009910010080000100000005110512162220037800001002004120041200412004120041
8020420040150000041504225801001008000010080000500640000052002120040200409973399988010020080000200240000200402004011802011009910010080000100000005110002162220037800001002004120041200412004120041
802042004015000000004225801001008000010080000500640000052002120040200409973399988010020080000200240000200402004011802011009910010080000100000005110002162220037800001002004120041200412004120041
802042004015000000004225801001008000010080000500640000102002120040200409973399988010020080000200240000200402004011802011009910010080000100000005110512162220037800001002004120041200412004120041
802042004015000000004225801001008000010080000500640000002002120040200409973399988010020080000200240000200402004011802011009910010080000100000035110002162220037800001002004120041200412004120041

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03040a0b18193a3f51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200401500000004125800101080000108000050640000120021200402004099963100208001020800002024000020040200401180021109101080000100005020516772003780000102004120041200412004120041
8002420040150000000412580010108000010800005064083212002120040200409996310020800102080000202403212010020100218002110910108000010004755020516752003780000102004120041200412004120402
80024200401500001104125800101080000108000050640000120021200402004099963100208001020800002024032120100201992180021109101080000100005038716772003780000102004120041200412004120041
80024200401500000004147800101080100108010650640840120021200402004099963100208001020800002024000020040200401180021109101080000100005020516572003780000102004120041200412004120041
80024200401500000004125800101080000108000050640000120021200402004099963100208001020800002024000020040200401180021109101080000100005020716752003780000102004120041200412004120041
80024200401500000004125800101080000108000050640000120021200402004099963100208001020800002024000020040200401180021109101080000100005020716572003780000102004120041200412004120041
80024200401500000004125800101080000108000050640000120021200402004099963100208001020800002024000020040200401180021109101080000100005020516752003780000102004120041200412004120041
80024200401500000004125800101080000108000050640000120021200402004099963100208001020800002024000020040200401180021109101080000100005020716742003780000102004120041200412004120041
80024200401500000004125800101080000108000050640000120021200402004099963100208001020800002024000020091200401180021109101080000100005020716572003780000102004120041200412004120041
80024200401500000004125800101080000108000050640000120021200402004099963100208001020800002024000020040200401180021109101080000100005020716572003780000102004120041200412004120041