Apple M1 Microarchitecture Research by Dougall Johnson

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

FCADD (vector, 4S)

Test 1: uops

Code:

  fcadd v0.4s, v0.4s, v1.4s, #90
  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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220126254825100010001000398313130183037303724153289510001000200030373037111001100000073316222630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000200030373037111001100000373216222630100030383038303830383038
10043037220265254825100010001000398313030183037303724153289510001000200030373037111001100001073216222630100030383038303830383038
10043037230197254825100010001000398313030183037303724153289510001000200030373037111001100000073216222630100030383038303830383038
10043037230107254825100010001000398313030183037303724153289510001000200030373037111001100001073216222630100030383038303830383038
10043037230229254825100010001000398313130183037303724153289510001000200030373037111001100000073216222630100030383038303830383038
1004303723061254825100010001000398313030183037303724153289510001000200030373037111001100000073216222630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100000073216222630100030383038303830383038
1004303722061254825100010001000398313130183037303724153289510001000200030373037111001100022073216222630100030383038303830383038
1004303723061254825100010001000398313130183037303724153289510001000200030373037111001100000073216222630100030383038303830383038

Test 2: Latency 1->2

Code:

  fcadd v0.4s, v0.4s, v1.4s, #90
  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)030b1e3f4e51inst 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)9fa0a6a8a9accfd0d5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000000710011611296340100001003003830038300383003830038
1020430037224006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010002002813710011611296340100001003003830038300383003830038
1020430037225106129548251010010010000105100005814277313030018300373003728265032874510100200101812002000030037300371110201100991001001000010000000710011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000000710011611296340100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000000710011611296340100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773130300183003730037282650328745101002001000020020000300373003711102011009910010010000100000037100116112963420100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000100710011611296340100001003003830038300383003830038
10204300372240061295482510100100100001001000050042773130300183003730037282650328745101002001000020020000300373003711102011009910010010000100201012710011611296340100001003003830038300383003830038
1020430037225006129548441010010010000100100005004277313030018300373007028265032874510100200100002002000030037300371110201100991001001000010000000710011611296340100001003003830038300383003830038
1020430037225036129548251010010010000100100005004277313130018300373003728265032874510100200100002002000030037300371110201100991001001000010000000710011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03091e3f4e51inst 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
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001003640316222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001003640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001009640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100111640216222963010000103003830038300383003830038
10024300372250061295392510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001003640216222963010000103003830038300383003830038
10024300372250061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001009640216222963010000103003830038300383003830038
10024300372240061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001003640216222963010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100117640216222963010000103003830038300383003830038
100243003722600612954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010509668216222963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  fcadd v0.4s, v1.4s, v0.4s, #90
  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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250612954825101001001000010010000500427731303001830037300372826503287451010020010000200200003003730037111020110099100100100001008107101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282650328745101002001000020020000300373003711102011009910010010000100037101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282650328745101002001000020020000300373003711102011009910010010000100037101161129702100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282650328745101002001000020020000300373003711102011009910010010000100037101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826503287451010020010000200200003003730037111020110099100100100001000787101161129634100001003003830038300383003830038
1020430037224061295482510100100100001001000050042773131300183008430037282650328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830085
1020430132225061295482510100100100001001000050042773130300183003730037282650328745101002001000020020000300373003721102011009910010010000100037101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773131300183003730037282650328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042777811300183003730037282650328745101002001000020020000300373003711102011009910010010000100037101161129634100001003003830038300383003830038
1020430037225061295482510100100100001001000050042773130300183003730037282650328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b1e1f3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010106402162229630010000103003830038300383003830227
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000104066402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000105536402162229630010000103003830038300383003830038
100243007022500061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010036402162229630010000103003830038300853003830038
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000103596402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000104766402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000105906402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000104696402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731330018300373003728287328767100102010000202000030037300371110021109101010000105406402162229630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  fcadd v0.4s, v8.4s, v9.4s, #90
  fcadd v1.4s, v8.4s, v9.4s, #90
  fcadd v2.4s, v8.4s, v9.4s, #90
  fcadd v3.4s, v8.4s, v9.4s, #90
  fcadd v4.4s, v8.4s, v9.4s, #90
  fcadd v5.4s, v8.4s, v9.4s, #90
  fcadd v6.4s, v8.4s, v9.4s, #90
  fcadd v7.4s, v8.4s, v9.4s, #90
  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)0308181e1f3f51inst 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)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)9fa8accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005715000006112580100100800001008000050064000010200202003920039997339997801002008000020016000020039200391180201100991001008000010001115110003161120036800001002004020040200402004020040
802042003915000004125801001008000010080000500640000102002020039200399973399978010020080000200160000200392003911802011009910010080000100005110001161120036800001002004020040200402004020040
802042003915000004125801001008000010080000500640000102002020039200399973399978010020080000200160000200392003911802011009910010080000100005110001161120036800001002004320040200402004020040
802042003915000004125801001008000010080000556640000102002020039200399973399978010020080106200160000200392003911802011009910010080000100005110001161120036800001002004020040200402004020040
802042003915000006425801001008000010080000500640000002002020039200399973399978010020080000200160000200392003911802011009910010080000100005110001161120036800001002004020040200402004020040
802042003915000004125801001008000010080000500640000002002020039200399973399978010020080000200160000200392003911802011009910010080000100005110001161220036800001002004020040200402004020040
802042003915000004125801001008000010080000500640000002002020039200399973399978010020080000200160000200392003911802011009910010080000100065110001161120036800001002004020040200402004020040
802042003915000004125801001008000010080000500640000002002020039200399973399978010020080000200160000200392003911802011009910010080000100005110001161120036800001002004020040200402004020040
8020420039150001204125801001008000010080000500640000102002020039200399973399978010020080000200160000200392003911802011009910010080000100105110001161120036800001002004020040200402004020040
802042003915000004125801001008000010080000500640000002002020039200399973399978010020080000200160000200392003911802011009910010080000100205110001161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03071e1f3f51inst 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)61696d6edispatch 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
800242003915100040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000502017161772003680000102004020040200402004020040
800242003915000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001006502017161772003680000102004020040200402004020040
800242003915000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000502071617172003680000102004020040200402004020040
80024200391500004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050207167172003680000102004020040200402004020040
800242003915000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000502017161772003680000102004020040200402004020040
800242003915000027225800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050207167172003680000102004020040200402004020040
8002420039150000402580010108000010800005064000002002020039200399996310019800102080000201600002003920039118002110910108000010435020171617172003680000102004020040200402004020040
80024200391500004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050207161772003680000102004020040200402004020040
800242003915000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000502017167172003680000102004020040200402004020040
80024200391501004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050207167172003680000102004020040200402004020040