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, 2S)

Test 1: uops

Code:

  fabd v0.2s, v0.2s, v1.2s
  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
100430372206125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723012825482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723010725482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372208225482510001000100039831313018303730372415328951000100020003037303711100110001073116112630100030383038303830383038
100430372306125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037233876125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110001073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
100430372306125482510001000100039831303018303730372415328951000100020003037303711100110001073116112630100030383038303830383038
100430372206125482510001000100039831303018303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  fabd v0.2s, v0.2s, v1.2s
  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)03181e3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500612954825101141001000010010000500427731303001830085300372826532874510100200100002002000030037300372110201100991001001000010023671011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722400612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037301811110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010005371011611296348100001003003830038300383003830038
102043003722400612954825101001001000010010000500427867003001830037300372826532874510100200100002002000030085300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722400612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
102043003722500612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038
1020430037225030612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b181e3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000254295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300853003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216322963010000103003830038300383003830038
1002430037225000082295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
1002430037225000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372240010514295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250000726295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  fabd v0.2s, v1.2s, v0.2s
  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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037224000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250000012629548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
10204300372250000012129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101160129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722500001086129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038

1000 unrolls and 10 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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100640316222963010000103003830038300383003830038
100243003722542693529548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722508229548251001010100001010000504277313130064300373003728287328767100102010000202000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100640216222963010000103003830038300383003830038
10024300372254326129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100640216222963010000103003830038300383003830038
1002430037225756129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100640216222963010000103003830038300383003830038
10024300372253816129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100640216222963010000103003830038300383003830038
100243003722506129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100640216222963010000103003830038300383003830038
10024300372254326129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100640216222963010000103003830038300383003830038
10024300372253876129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  fabd v0.2s, v8.2s, v9.2s
  fabd v1.2s, v8.2s, v9.2s
  fabd v2.2s, v8.2s, v9.2s
  fabd v3.2s, v8.2s, v9.2s
  fabd v4.2s, v8.2s, v9.2s
  fabd v5.2s, v8.2s, v9.2s
  fabd v6.2s, v8.2s, v9.2s
  fabd v7.2s, v8.2s, v9.2s
  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)03081e3f51inst 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)9fa8acc5cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200571500198412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511002161120036800001002004020040200402004020040
80204200391500258412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511001161120036800001002004020040200402004020040
802042003915000412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511001161120036800001002004020040200402004020040
80204200391500258412580100100800001008000050064000002002020039200399982399978010020080000200160000200392003911802011009910010080000100000511001161120036800001002004020040200402004020040
80204200391500276412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511001161120036800001002004020040200402004020040
80204200391500312412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511001161120036800001002004020040200402004020040
80204200391500300412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100760511001161120036800001002004020040200402004020040
80204200391500276412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511001161120077800001002004020040200402004020040
80204200391490321412580100100800001008000050064000012002020039200399973399978010020080000200160000200392003911802011009910010080000100000511001161120036800001002004020040200402004020040
80204200391500291412580100100800001008000050064000002002020039200399973399978010020080000200160000200392003911802011009910010080000100000511001161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03181e1f3f51inst 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)9fa0a1a8accficache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815001204025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100000502001216222003680000102004020040200402004020040
8002420039150000402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000050200616222003680000102004020040200402004020040
8002420039150000402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010002050200216262003680000102004020040200402004020040
8002420039150060402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000050200216222003680000102004020040200402004020040
8002420039150000405880010128000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000050200616222003680000102004020040200402004020040
8002420039150000402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000050200216222003680000102004020040200402004020040
800242003915005040402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000050200616222003680000102004020040200402004020040
8002420039150000402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000050200616662003680000102004020040200402004020040
8002420039150000402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000050200216222003680000102004020040200402004020040
80024200391500004204980010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010000050200216222003680000102004020040200402004020040