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, 8H)

Test 1: uops

Code:

  fabd v0.8h, v0.8h, v1.8h
  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)033f4e51inst 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
10043037226125482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037236125482510081000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037226125482510001000100039831313018303730372415328951000100020003037303711100110000373216222630100030383038308630383038
10043037236125482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037236125482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037226125482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
10043037236125482510001000100039831313018303730372415328951000100020003037303711100110000073216222630100030383038303830383038
100430372325125482510001000100039831313018303730372415328951000100020003037303711100110000973216222630100030383038303830383038
100430372361254825100010001000398313130183037303724153289510001000200030373037111001100009073216222630100030383038303830383038
10043037226125482510001000100039831313018303730372415328951000100020003037303711100110002073216222630100030383038303830383038

Test 2: Latency 1->2

Code:

  fabd v0.8h, v0.8h, v1.8h
  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)0308090b1e1f3f4e51inst 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)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000007102161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265628745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129705100001003003830038300383003830038
102043003722500000210429548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004282669030018300373003728265328745101002001000020020000300373003711102011009910010010000100000037101161129634100001003003830038300383003830038
10204300372250000010329548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129688100001003003830038300383003830038
10204300372250002106129548251010010010000100100005004277313030018300373003728265328745107252001000020020000300373003711102011009910010010000100000037101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000067101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b191e3f4e51inst 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)9fa0a6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250013261295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722510061295482510010101001610100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000060640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100001770640216222963010000103003830038300383003830038
100243003722500061295482510010101000710100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722500082295482510010101000010100005042773130300183008430084282873287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000100640216222963010000103003830038300383003830038
10024300372250006129548441001010100001110000504277313030018300373003728287102876710010201000020200003003730037111002110910101000010000150640216222970210000103003830038300853008530038
100243003722401061295482510010101000010100005042773130300183003730037282873287671016020100002020000300373003711100211091010100001000027902640216222963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  fabd v0.8h, v1.8h, v0.8h
  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)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)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)9fa0a1a6a7a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000030071011611296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000000030071011611296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000030071011611296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731303001830037300372826532874510100200101642002033230085300371110201100991001001000010000000060071011611296340100001003003830038300383003830038
10204300372240000000612954825101001001000010010000500427731303005430037300372826532874510100200100002002000030037300371110201100991001001000010000000090071011611296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000030071011611296340100001003003830038300383003830038
102043003722500000003762954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000001090071011611296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000030071011611296340100001003003830038300383003830038
10204300372240000000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000030071011611296340100001003003830038300383003830038
10204300372250000000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000000000071011611296340100001003003830038300383003830038

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)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)9fa1a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722400061295482510010101000010100005042773131300180300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
1002430037225000251295482510010101000010100005042773131300180300373003728287328767100102010000202000030037300371110021109101010000100100640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300180300373003728305328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
10024300372250007262954825100101010000101000050427731313001803003730037282873287671001020100002020000300373003711100211091010100001002500640216222963010000103003830038300383003830038
10024300372250006129548251001010100001010000614277313130018030037300372828732876710010201000020200003003730037111002110910101000010001050640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300180300373003728287328767100102010000202000030037300371110021109101010000100400640216222963010000103003830038300383003830038
100243003722400061295482510010101000010100005042773131300180300373003728302328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300180300373003728287328767100102010000202000030037300371110021109101010000100100640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300180300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300180300373003728287328767100102010000202000030037300371110021109101010000100000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  fabd v0.8h, v8.8h, v9.8h
  fabd v1.8h, v8.8h, v9.8h
  fabd v2.8h, v8.8h, v9.8h
  fabd v3.8h, v8.8h, v9.8h
  fabd v4.8h, v8.8h, v9.8h
  fabd v5.8h, v8.8h, v9.8h
  fabd v6.8h, v8.8h, v9.8h
  fabd v7.8h, v8.8h, v9.8h
  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)0308090b18191e3a3f51inst 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)9fa0a1a6a7a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015002000003025801081008000810080020500640132200202003920039997769990801202008003220016006420039200391180201100991001008000010000000000111511801600200360800001002004020040200402004020040
802042003915000000003025801081008000810080020500640132200202003920039997339997801002008000020016000020039200391180201100991001008000010000002000000511011611200360800001002004020040200402004020040
802042003915000000004125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000002000000511011611200360800001002004020040200402004020040
8020420039150000001504125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000004000000511011611200360800001002004020040200402004020040
802042003915000000004125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000000000000511011611200360800001002004020040200402004020040
802042003915000000004125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000000000000511011611200360800001002004020040200402004020040
8020420039150000000041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100000050150000511011622200360800001002004020040200402004020040
802042003915000000004125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000001000000511011611200360800001002004020040200402004020040
802042003915000000004125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000000030000511011611200360800001002004020040200402004020040
802042003915000000004125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000001030000511011611200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e3f51inst 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)9fa8accdcfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050206160642003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050202160242003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010112050206170342003680000102004020040200402004020040
80024200391501040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001010050204160242003680000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050204160242003680000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050204160422003680000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050204160242003680000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050202160422003680000102004020040200402004020247
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000050202160242003680000102004020040200402004020040
80024200391500040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001010050204160422003680000102004020040200402004020040