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, S)

Test 1: uops

Code:

  fnmul s0, s0, s1
  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
100440373006134072510001000100053190814018403740373258338951000100020004037403711100110005073116113473100040384038403840384038
100440373006134072510001000100053190804018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
1004403730011834072510001000100053190804018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
100440373006134072510001000100053190814018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
100440373006134072510001000100053190804018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
100440373006134072510001000100053190814018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
100440373006134072510001000100053190814018407140373258338951000100020004037403711100110000073116113473100040384038403840384038
100440373006134072510001000100053190804018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
100440373006134072510001000100053190804018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
100440373006134072510001000100053190804018403740373258338951000100020004037403711100110000073116113473100040384038403840384038

Test 2: Latency 1->2

Code:

  fnmul s0, s0, s1
  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)030b1e3f4e51inst 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)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
10204400373000061394072510100100100001001000050057069080400180400374003738108338745101002001000020020000400374003711102011009910010010000100000007102162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069080400180400374003738108338745101002001000020020000400374003711102011009910010010000100000007102162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069080400180400374003738108338745101002001000020020000400374003711102011009910010010000100000007102162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069080400180400374003738108338745101002001000020020000400374003711102011009910010010000100000007102162239479100001004003840038400384003840038
10204400372990061394072510100100100001001000050057069080400180400374003738108338745101002001000020020000400374003711102011009910010010000100000007102162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069080400180400374003738108338745101002001000020020000400374003711102011009910010010000100000007102162239479100001004003840038400384003840038
1020440037300052261394072510100100100001001000050057069080400180400374003738108338745101002001000020020000400374003711102021009910010010000100000007102162239479100001004003840038400384003840038
102044003730000166394072510100100100061051000050057069080400180400374003738108338745101002001018020020000400374003711102011009910010010000100000007102162239479100001004003840038400384003840038
10204400372990061394072510100100100001001000050057069080400180400374003738108338745101002001000020020000400374003711102011009910010010000100000007102162239479100001004003840038400384003840038
10204400373000061394072510100100100001001000050057069080400180400374003738108338745101002001000020020000400374003711102011009910010010000100000007102162239479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)03070a181e3a3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400372991100268394072510010101000010100005057069084001804003740037381303387671001020100002020000400374003711100211091010100001000644101610103947310000104003840038400384003840038
10024400373001100268394072510010101000010100005057069084001804003740037381303387671001020100002020000400374003711100211091010100001000672111611113947310000104003840038400384003840038
10024400373001100268394072510010101000010100005057069084001804003740037381303387671001020100002020000400374003711100211091010100001000644101610103947310000104003840038400384003840038
10024400373001100273339407251001010100001010000505706908400180400374003738130338767100102010000202000040037400371110021109101010000100064410161083947310000104003840038400384003840038
10024400373001100268394072510010101000010100005057069084001804003740037381303387671001020100002020000400374003711100211091010100001000644101610103947310000104003840038400384003840038
1002440037299110028939407251001010100001010000505706908400180400374003738130338767100102010000202000040037400371110021109101010000100064411166113947310000104003840038400384003840038
10024400373001100268394072510010101000010100005057069084001804003740037381303387671001020100002020000400374003711100211091010100001000644101610103947310000104003840038400384003840038
10024400373001100268394072510010101000010100005057069084001804003740037381303387671001020100002020000400374003711100211091010100001000644101610103947310000104003840038400384003840038
10024400373001100268394072510010101000010100005057069084001804003740037381303387671001020100002020000400374003711100211091010100001000644101610103947310000104003840038400384003840038
10024400373001100268394072510010101000010100005057069084001804003740037381303387671001020100002020000400374003711100211091010100001000644101611113947310000104003840038400384003840038

Test 3: Latency 1->3

Code:

  fnmul s0, s1, s0
  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)0308090b18191e3f4e51inst 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)9fa6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204400372990200006139407251010010010000100100005005706908140018400374003738108033874510100200100002002000040037400371110201100991001001000010001007101161139479100001004003840038400384003840038
10204400372990000006139407251010010010000100100005005706908140018400374003738108033874510100200100002002000040037400371110201100991001001000010003007101161139479100001004003840038400384003840038
10204400373000000006139407251010010010000100100005225706908040018400374003738108033874510100200100002002000040037400371110201100991001001000010002007101161139479100001004003840038400384003840038
102044003729900000072639398441010010010000100100005005706908140018400374003738108033874510100200100002002000040037400371110201100991001001000010002007101161139479100001004003840038400384003840038
10204400373000000006139407251010010010000100100005005706908140018400374003738108033874510100200100002002000040037400371110201100991001001000010003007101161139479100001004003840038400384003840038
10204400372990000006139407251010010010000100100005005706908140018400374003738108033874510100200100002002000040037400371110201100991001001000010002007101161139479100001004003840038400384003840038
10204400373000000006139407251010010010000100100005005706908040018400374003738108033874510100200100002002000040037400371110201100991001001000010002007101161139479100001004003840038400384003840038
10204400373000000006139407251010010010000100100005005706908040018400374003738108033874510100200101652002000040037400371110201100991001001000010001007101161139479100001004003840038400384003840038
10204400373000000006139407251010010010000100100005005706908140018400374003738108033874510100200100002002000040037400371110201100991001001000010002007101161139479100001004003840038400384003840038
10204400373000000006139407251010010010000100100005005706908140018400374003738108033874510100200100002002000040037400371110201100991001001000010002007101161139479100001004003840038400384003840038

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)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)9fa1a8acc5cfd5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400373000166394072510010101000010100005057069080400184003740037381433387671001020100002020000400374003711100211091010100001000006404162339473010000104003840038400384003840038
1002440037300061394072510010101000010100005057069080400184003740037381303387671001020100002020000400374003711100211091010100001001006404163439473010000104003840038400384003840038
1002440037300961394072510010101000010100005057069080400184003740037381303387671001020100002020000400374003711100211091010100001000006404163439473010000104003840038400384003840038
10024400373000726394072510010101000010100005057069080400184003740037381303387671001020100002020000400374003711100211091010100001000006404163439473010000104003840038400384003840038
1002440037300061394072510010101000010100005057069081400184003740037381303387671001020100002020000400844003711100211091010100001000006404164439473010000104003840038400384003840038
10024400373000145394072510010101000010100005057069080400184003740037381303387671001020100002020000400374003711100211091010100001000006403163439473010000104003840038400384003840038
1002440037300061394072510010101000010100005057069080400184003740037381303387671001020100002020000400374003711100211091010100001000006403163439473010000104003840038400384003840038
10024400373000536394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000006404163439473010000104003840038400384003840038
1002440037299061394072510010101000010100005057069080400184003740037381303387671001020100002020000400374003711100211091010100001000006404164439473310000104003840038400384003840038
10024400373000170394072510010101000010100005057069080400184003740037381303387671001020100002020000400374003711100211091010100001000006404164439473010000104003840038400384003840038

Test 4: throughput

Count: 8

Code:

  fnmul s0, s8, s9
  fnmul s1, s8, s9
  fnmul s2, s8, s9
  fnmul s3, s8, s9
  fnmul s4, s8, s9
  fnmul s5, s8, s9
  fnmul s6, s8, s9
  fnmul s7, s8, s9
  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)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)60696b6d6edispatch 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)9fa8cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420049150086258010010080000100800005006400000200210200402004099733999880100200800002001600002004020040118020110099100100800001000511061611200370800001002004120041200412004120041
80204202001500105258010010080000100800005006400000200210200402004099733999880100200800002001600002004020040118020110099100100800001000511011611200370800001002004120041200412004120041
80204200401500147258010010080000100800005006400000200210200402004099733999880100200800002001600002004020040118020110099100100800001000511011611200370800001002004120041200412004120041
80204200401500127258010010080000100800005006400000200213200402004099733999880100200800002001600002004020040118020110099100100800001000511011611200370800001002004120041200412004120041
80204200401500151258010010080000100800005006400000200210200402004099733999880100200800002001600002004020040118020110099100100800001000511011611200370800001002004120041200412004120041
80204200401500842580100100800001008000050064000002002102004020040997339998801002008000020016000020040200401180201100991001008000010005110116112003714800001002004120041200412004120041
8020420040150063258010010080000100800005006400000200210200402004099733999880100200800002001600002004020040118020110099100100800001000511011611200370800001002004120041200412004120041
80204200401500524258010010080000100800005006400000200210200402004099733999880100200800002001600002004020040118020110099100100800001000511011611200370800001002004120041200412009320041
80204200401500126258010010080000100800005006400000200210200402004099733999880100200800002001600002004020040118020110099100100800001000511011611200370800001002004120041200412004120041
8020420040150063258010010080000100800005006400000200210200402004099733999880100200800002001600002004020040118020110099100100800001000511011611200370800001002004120041200412004120041

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e3f51inst 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)9fa0a8accfitlb miss (d4)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004915000041258001010800001080000506400000020021200402004099963100208001020800002016000020040200401180021109101080000100005020051600444200370080000102004120041200412004120041
800242004015000041258001010800001080000506400000020021200402004099963100208001020800002016000020040200401180021109101080000100005020021600442200370080000102004120041200412004120041
800242004015001041258001010800001080000506400000020021200402004099963100208001020800002016028020040200401180021109101080000100035020031600242200370080000102004120041200412004120041
8002420040150000169258001010800001080000506400000020021200402004099963100208001020800002016000020040200401180021109101080000100005020041600344200370080000102004120041200412004120041
800242004015000041258001010800001080000506400000020021200402004099963100208001020800002016000020040200401180021109101080000100005020041600342200370080000102004120041200412004120041
8002420040150000127258001010800001080000506400000020021200402004099963100208001020800002016021420040200401180021109101080000100005020031600324200370080000102004120041200412004120041
800242004015000083438001010800001080000506400000020021200402004099963100208001020800002016000020040200401180021109101080000100005020021600353200373080000102004120041200412004120041
800242004015000041258001010800001080000506400000020021201042004099963100208001020800002016000020040200401180021109101080000100005020041600364200780080000102004120041200412004120041
8002420040150000192258001010800001080000506400000020021200402004099963100208001020800002016000020040200401180021109101080000100005020041600344200370080000102004120041200412004120041
80024200401500012169258001010800001080000506400001120021200402004099963100208001020800002016000020040200401180021109101080000100005020041600344200370080000102004120041200412004120041