Apple M1 Microarchitecture Research by Dougall Johnson

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

FADD (scalar, S)

Test 1: uops

Code:

  fadd 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
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372308225482510001000100039831303018303730372415328951000100020003037303711100110001073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  fadd 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): 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)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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071021622296340100001003003830038300383003830038
10204300372250057612954825101001001000010010000626427731303001830037300372826532876310253200100002002000030037300371110201100991001001000010002171021622296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071021622296340100001003003830038300383003830038
102043003722400098295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071021622296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071021622296340100001003003830038300383003830038
102043003722500061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071021622296340100001003003830038300383003830038
102043003722500061295482510125100100001251000050042773130300183008530037282653287441010020010000200200003003730037111020110099100100100001000071031722296340100001003003830038300383003830038
102043003722500061295482510125100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071021622296340100001003003830038300383003830038
1020430037225002461295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071021622296340100001003003830038300383003830038
102043003722400061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001000071021622296340100001003003830038300383003830038

1000 unrolls and 10 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)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)9fa0a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000006129548251001010100001010000504277313030018030037300372830232876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010001006402162229630010000103003830038300383003830038
100243003722500000008929548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010001006402162229630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773130300180300373003728287328767100102010000202000030037300371110021109101010000100033036402162229630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018030037300372828732876710010201000020203403003730037111002110910101000010001006402162229630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010002006402162229630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018030037300372828732876710010201000020200003003730037111002110910101000010000006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  fadd 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): 3.0037

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)9fa1a8a9acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100030007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722596129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003721102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100010907101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830228
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038

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)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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500612954825100101010000101000050427731313001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037224006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100024640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103022630038300383003830038
100243003722400612954825100101010000101000050427867013001830037300372828732876710010201000020200003003730037111002110910101000010000640216222990410000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100012640216222969210000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225001162954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103008630038300383003830038
100243003722500612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  fadd s0, s8, s9
  fadd s1, s8, s9
  fadd s2, s8, s9
  fadd s3, s8, s9
  fadd s4, s8, s9
  fadd s5, s8, s9
  fadd s6, s8, s9
  fadd 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)0307080a1e3a3f51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420059150101024825801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001007005114101610920036800001002004020198200402004020040
802042003915010162482580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100040511411169920036800001002004020040200402004020040
802042003915010102482580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511491691120036800001002004020040200402004020040
802042003915010102482580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100006651149169920036800001002004020040200402004020040
8020420039150101024825801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000005114916111120036800001002004020040200402004020040
8020420039150101024825801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001002005114416111120036800001002004020040200402004020040
802042009815010102482580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511491691020036800001002004020040200402004020040
80204200391501010248258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000051149169420036800001002004020040200402004020040
802042003915010102482580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100001055114916111120036800001002004020040200402004020040
80204200391501010248258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000051144169920036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e1f3f5051inst 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)9fa8a9acc2c5cfd2icache miss (d3)d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150000040025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100000050200691611720036080000102004020040200402004020040
800242003915000004002580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000005020066169920075080000102004020040200402004020040
80024200391500000400258001010800001080000506400001200202003920099999631001980010208000020160000200392003911800211091010800001000000502007916111320036080000102004020040200402004020040
80024200391500000549025800101080084108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100000050200611166920036080000102004020040200402004020040
80024200391500000746025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100000050200671691320036080000102004020040200402004020040
8002420039150000074302580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010000005020069167920036080000102004020040200402004020040
8002420039150000030502580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010005102050200691613820085180000102004020040200402004020040
800242003915011004002580010108000010800005064000002006820039200399996310019800102080000201601962011220099218002110910108000010000205020061116111120036080000102004020040200402004020040
8002420039150001204002580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000005020069166920036080000102004020040200402004020040
80024200391500000400258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000000502006716111220036080000102004020040200402004020040