Apple M1 Microarchitecture Research by Dougall Johnson

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

FMUL (vector, 2D)

Test 1: uops

Code:

  fmul v0.2d, v0.2d, v1.2d
  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)0308090b18191e1f3a3f4e51inst 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)a0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100440373000000000613407251000100010005319081401840374037325833895100010002000403740371110011000000000073116113473100040384038403840384038
100440373000000000613407251000100010005319081401840374037325833895100010002000403740371110011000000000073116113473100040384038403840384038
100440373000000000613407251000100010005319081401840374037325833895100010002000403740371110011000222023520279240213499100040864085408541224086
1004408530100111718809023398451006100611485333041405340844084326283915101111632328408540851110011000040103583494124113531100040864086408540854084
100440853100011138008733398491006100611485319080405340844085326973914100011602436408440852110011000020003498473124213526100040744085408640864074
1004408531100111538808813407441006100611485333041405340844084326283906109611602000408540842110011000002103535279124123507100040384038408540844084
1004408531100111688818843407451006100611485333041405340854084326273915114811612322408440842110011000242003590294124113567100040384086408440854085
1004407331111111778819483398251006100611485333041405340374037327363915114811632320408540832110011000020123720294424113499100040854086408640854074
10044120301010014188015253398251000100611485333041405340374084327333895100010002000403740371110011000000000073116113473100040384038403840384038
100440373000000000613407251000100010005319081401840374037325833895100010002000403740371110011000000000073116113473100040384038403840384038

Test 2: Latency 1->2

Code:

  fmul v0.2d, v0.2d, v1.2d
  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)030b181e1f3f4e51inst 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)9fa1a8acc2c5cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204400373000000105394072510100100100001001000050057069080400184003740037381083387451010020010000200200004003740037111020110099100100100001000000071001161139479100001004003840038400384003840038
10204400373000000191394072510100100100001001000050057069080400184003740037381083387451010020010000200200004003740037111020110099100100100001000000071001161139479100001004003840038400384003840038
102044003730000001073940725101001001000010010000500570690804001840037400373810825387221010020010000200200004003740037111020110099100100100001000000071001161139534100001004003840038400384003840038
10204400372990000368394072510100100100001001000050057069080400184003740037381083387451010020010000200200004003740037111020110099100100100001004100071001161139479100001004003840038400384003840038
10204400373000000126394072510100100100001001000050057069080400184003740037381083387451010020010000200200004003740037111020110099100100100001000060071001161139479100001004003840038400384003840038
10204400862990001041072394072510100100100001001000050057069080400184003740037381083387451010020010000200200004013340037111020110099100100100001000100071001161139479100001004003840038400384003840038
10204400372990000126394072510100100100001001000050057069081400184003740037381083387451010020010000200200004003740037111020110099100100100001000000071001161139479100001004003840038400384003840038
10204400373000000935394072510100100100001001000050057069081400184003740037381083387451010020010000200200004003740037111020110099100100100001000000071001161139479100001004003840038400384003840038
10204400373000000172394072510100100100001001000050057069080400184003740037381083387451010020410000200200004003740037111020110099100100100001000000071001161139479100001004003840038400384003840038
1020440037300000084394072510100100100001001000050057069080400184003740037381083387451010020010000200200004003740037111020110099100100100001000000071001161139748100001004003840038400384003840038

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)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)9fa0a1a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002440037300019739407251001010100001010000505706908400184003740037381303387671001020100002020000400374003711100211091010100001000000640216223947310000104003840038400384003840038
100244003730006139407251001010100001010000505706908400184003740037381303387671001020100002020000400374003711100211091010100001000000640216123951110000104003840038400384003840038
10024400373001512639407251001010100001010000505706908400184003740037381303387671001020100002020000400374003711100211091010100001000000640216223947310000104003840038400384003840038
1002440037299017039407251001010100001010000505706908400184003740037381303387671001020100002020000400374003711100211091010100001000030640216223947310000104003840038400384003840038
1002440037300054839407251001010100001010000505706908400184003740037381303387671001020100002020000400374003711100211091010100001000000640216223947310000104003840038400384003840038
100244003730006139407251001010100001010000505706908400184003740037381303387671001020100002020000400374003711100211091010100001000000640216223947310000104003840038400384003840038
100244003730006139407251001010100001010000505706908400184003740037381303387671001020100002020000400374003711100211091010100001000000640216223947310000104003840038400384003840038
1002440037300426139407251001010100001010000505706908400184003740037381303387671001020100002020000400374003711100211091010100001000000640216223947310000104003840038400384003840038
100244003729906139407251001010100001010000505706908400184003740037381303387671001020100002020000400374003711100211091010100001000000640216223947310000104003840038400384003840038
100244003730006139407251001010100001010000505706908400184003740037381303387671001020101722020000400374003711100211091010100001000000640216223947310000104003840038400384003840038

Test 3: Latency 1->3

Code:

  fmul v0.2d, v1.2d, v0.2d
  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)0308090b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cfd0d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102044003730000000002803940725101001001000010010000500570690804001804003740037381083387451010020010000200200004003740037111020110099100100100001000000000710011611394790100001004003840038400384003840038
10204400373000000000843940725101001001000010010000500570690804001804003740037381083387451010020010000200200004003740037111020110099100100100001000000000710011611394790100001004003840038400384003840038
102044003730000000001703940725101001001000010010000500570690804001804003740037381083387451010020010000200200004003740037111020110099100100100001000000000710011611394790100001004003840038400384003840038
10204400373000000000613940725101001001000010010000500570690804001804003740037381083387451010020010000200200004003740037111020110099100100100001000000000710011611394790100001004003840038400384003840038
10204400373000000000613940725101001001000010010000500570690804001804003740037381083387451010020010000200200004003740037111020110099100100100001000000000710011611394790100001004003840038400384003840038
10204400373000000000613940725101001001000010010000500570690804001804003740037381083387451010020010000200200004003740037111020110099100100100001000000000710011611394790100001004003840038400384003840038
10204400373000000000613940725101001001000010010000500570690804001804003740037381083387451010020010000200200004003740037111020110099100100100001000000000710011611394790100001004003840038400384003840038
10204400373000000000613940725101001001000010010000500570690804001804003740037381083387451010020010000200200004003740037111020110099100100100001000000000710011621394790100001004003840038400384003840038
10204400373000000000613940725101001001000010010000500570690804001804003740037381083387451010020010000200200004003740037111020110099100100100001000000000710011611394790100001004003840038400384003840038
10204400373000000000613940725101001001000010010000500570690804001804003740037381083387451010020010000200200004003740037111020110099100100100001000000000710011611394790100001004003840038400384003840038

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)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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003730021350394072510010101000010100005057069081400180400374003738130338767100102010000202000040037400371110021109101010000100006403162339473010000104003840038400384003840038
1002440037300084394072510010101000010100005057069081400180400374003738130338767100102010000202000040037400371110021109101010000100006402162239473010000104003840038400384003840038
1002440037299061394072510010101000010100005057069081400180400374003738130338767100102010000202000040037400371110021109101010000100006402162239473010000104003840038400384003840038
1002440037300061394072510010101000010100005057069081400180400374003738130338767100102010000202000040037400371110021109101010000100006402162239473010000104003840038400384003840038
1002440037299061394072510010101000010100005057069081400180400374003738130338767100102010000202000040037400371110021109101010000100016402162239473010000104003840038400384003840038
1002440037299061394072510010101000010100005057069081400180400374003738130338767100102010000202000040037400371110021109101010000100006402162239473010000104003840038400384003840038
1002440037300061394072510010101000010100005057069081400180400374003738130338767100102010000202000040037400371110021109101010000100006402162239473010000104003840038400384003840038
1002440084300061394072510010101000010100005057069081400180400374003738130338767100102010000202000040037400371110021109101010000100006402162239473010000104003840038400384003840038
10024400372990726394072510010101000010100005057069081400180400374003738130338767100102010000202000040037400371110021109101010000100006402162239473010000104003840038400384003840038
1002440037299061394072510010101000010100005057069081400180400374003738130338767100102010000202000040037400371110021109101010000100006402162239473010000104003840038400384003840038

Test 4: throughput

Count: 8

Code:

  fmul v0.2d, v8.2d, v9.2d
  fmul v1.2d, v8.2d, v9.2d
  fmul v2.2d, v8.2d, v9.2d
  fmul v3.2d, v8.2d, v9.2d
  fmul v4.2d, v8.2d, v9.2d
  fmul v5.2d, v8.2d, v9.2d
  fmul v6.2d, v8.2d, v9.2d
  fmul v7.2d, v8.2d, v9.2d
  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)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)9fa0a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200401500422580100100800001008000050064000002002120040200409973399988010020080000200160000200402004011802011009910010080000100000051102161120037800001002004120041200412004120041
80204200401500422580100100800001008000050064000002002120040200409973399988010020080000200160000200402004011802011009910010080000100000051101161120037800001002004120041200412004120041
80204200401500632580100100800001008000050064000012002120040200409973399988010020080000200160000200402004011802011009910010080000100000051101161120037800001002004120041200412004120041
80204200401500422580100100800001008000050064000002002120040200409973399988010020080000200160000200402004011802011009910010080000100000051101161120037800001002004120041200412004120041
802042004015004225801001008000010080000500640000020021200402004099733999880100200800002001600002004020040118020110099100100800001000002751101161120037800001002004120041200412004120041
80204200401500422580100100800001008000050064000002002120040200409973399988010020080000200160000200402004011802011009910010080000100000051101161120037800001002004120041200412004120041
80204200401500422580100100800001008000050064000012002120040200409973399988010020080000200160000200402004011802011009910010080000100000051101161220037800001002004120041200412004120041
80204200401500422580100100800001008000050064000012002120040200409973399988010020080000200160000200402004011802011009910010080000100000051101161120037800001002004120041200412004120041
80204200401500422580100100800001008000050064000012002120040200409973399988010020080000200160000200402004011802011009910010080000100000051101161120037800001002004120041200412004120041
802042004015004225801001008000010080000500640000120021200402004099733999880100200800002001600002004020040118020110099100100800001000150951101161120037800001002004120041200412004120041

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080918191e1f3f51inst 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)9fa8a9accfd2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420049150000000412580010108000010800005064000002002120040200409996310020800102080000201600002004020040118002110910108000010000502073163320037080000102004120041200412004120041
8002420040150000000412580010108000010800005064000012002120040200409996310020800102080000201600002004020040118002110910108000010000502013163220037080000102004120041200412004120041
8002420040150000000412580010108000010800005064000012002120040200409996310020800102080000201600002004020040118002110910108000010000502013163320037080000102004120041200412004120041
8002420040150000000412580010108000010800005064000012002120040200409996310020800102080000201600002004020040118002110910108000010000502003163320037080000102004120041200412004120041
800242004015000000046932580010108000010800005064000002002120040200409996310020800102080000201600002004020040118002110910108000010000502002163320037080000102004120041200412004120041
8002420040150000000622580010108000010800005064000002002120040200409996310020800102080000201600002004020040118002110910108000010000502013162320037080000102004120041200412004120041
8002420040150000030622580010108000010800005064000002002120040200409996310020800102080000201600002004020040118002110910108000010000502012163320037080000102004120041200412004120041
8002420040150000000412580010108000010800005064000002002120040200409996310020800102080000201600002004020040118002110910108000010000502003162320037080000102004120041200412004120041
8002420040150000000412580010108000010800005064000002002120040200409996310020800102080000201600002004020040118002110910108000010003502003162320037080000102004120041200412004120041
8002420040150000000832580010108000010801055064000002002120040201039996310048801172080000201600002004020040118002110910108000010040502003162320037280000102004120041200412004120103