Apple M1 Microarchitecture Research by Dougall Johnson

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

FABD (vector, 2D)

Test 1: uops

Code:

  fabd 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)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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723061254825100010001000398313130183037303724153289510001000200030843084111001100000073116112630100030383038303830383038
1004303722061254825100010001000398313030183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303723082254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
10043037230128254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313030183037303724163289510001000200030373037111001100000373116112630100030383038303830383038
1004303723082254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303722061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000200030373037111001100000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  fabd 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): 3.0037

retire (01)cycle (02)0318191e3f4e51inst 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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
1020430037225001861295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042777233001830037300372826532874510100200100002002000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
1020530037224000612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100487101161129634100001003003830038300383003830038
102043003722400061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010007101161129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010007101171129634100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e3f4e51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250012612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001001650640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001001440640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001001620640516222963010000103003830038300383003830038
10024300372250006129548431001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010100640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001011740640216222963010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001001560640217222963010000103003830038300383003830038
10024300372240006129548251001010100001010000504277313030018300373003728287032876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250036129548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500276129548251001010100001010000504277313130018300373003728287032876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  fabd 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): 3.0037

retire (01)cycle (02)030b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000082295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001002000000071011611296340100001003003830038300383003830038
102043003722500012108585295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038
10204300372250000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000001000071011611296340100001003003830038300383003830038
102043003722510015082295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000000000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e1f3f4e51inst 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)9fa0a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037224001032954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722400612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037224088612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722400612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  fabd v0.2d, v8.2d, v9.2d
  fabd v1.2d, v8.2d, v9.2d
  fabd v2.2d, v8.2d, v9.2d
  fabd v3.2d, v8.2d, v9.2d
  fabd v4.2d, v8.2d, v9.2d
  fabd v5.2d, v8.2d, v9.2d
  fabd v6.2d, v8.2d, v9.2d
  fabd 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)031e3a3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000351102161120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039218020110099100100800001000051101161120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001001051101161120036800001002004020040200402004020040
8020420039150001362580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915090412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051101161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e3f51inst 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)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)9fa8accdcfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500040258001010800001080000506400000020020200392003999960310019800102080000201600002003920039118002110910108000010000502000416422003680000102004020040200402004020040
80024200391500040258001010800001080000506400000020020200392003999960310019800102080000201600002003920039118002110910108000010000502000416242003680000102004020040200402004020040
80024200391501040258001010800001080000506400000020020200392003999960310019800102080000201600002003920039118002110910108000010000502000216422003680000102004020040200402004020040
80024200391500040258001010800001080000506400000020020200392003999960310019800102080000201600002003920039118002110910108000010000502000416422003680000102004020040200402004020040
80024200391500040258001010800001080000506400000020020200392003999960310019800102080000201600002003920039118002110910108000010000502000216422003680000102004020040200402004020040
80024200391500040258001010800001080000506400000520020200392003999960310019800102080000201600002003920039118002110910108000010000502002416242003680000102004020040200402004020040
80024200391500040258001010800001080000506400001020020200392003999960310019800102080000201600002003920039118002110910108000010000502050216422003680000102004020040200402004020040
8002420039150047740258001010800001080000506400001020020200392003999960310019800102080000201600002003920039118002110910108000010000502000416242003680000102004020040200402004020040
80024200391500040258001010800001080000506400000020020200392003999960310019800102080000201600002003920039118002110910108000010000502052416622003680000102004020040200402004020040
80024200391500040258001010800001080000506400001020020200392003999960310019800102080000201600002003920039118002110910108000010000502050216432003680000102004020040200402004020040