Apple Microarchitecture Research by Dougall Johnson

M1/A14 P-core (Firestorm): Overview | Base Instructions | SIMD and FP Instructions
M1/A14 E-core (Icestorm):  Overview | Base Instructions | SIMD and FP Instructions

FCADD (vector, 2S)

Test 1: uops

Code:

  fcadd v0.2s, v0.2s, v1.2s, #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 uop (01)cycle (02)03mmu table walk instruction (07)1e3f4e51schedule uop (52)schedule simd uop (54)dispatch simd uop (57)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map simd uop (7e)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst simd alu (9a)l1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)f5f6f7f8fd
1004303723006125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037220025125482510001000100039831313018303730372415328951000100020003037303711100110002073116112630100030383038303830383038
1004303722006125482510001000100039831313018303730372415328951000100020003037303711100110000073116222627100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831313018303730372415328951000100020003037303711100110000073116222630100030383038303830383038
1004303722006125482510001000100039831313018303730372415328951000100020003037303711100110000073216112630100030383038303830383038
1004303722106125482510001000100039831313018303730372417328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  fcadd v0.2s, v0.2s, v1.2s, #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 uop (01)cycle (02)0318191e3a3f4e51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fl1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)? int retires (ef)f5f6f7f8fd
102043003722500906129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100137101161129634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100237101161129634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100337101161129634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100137101161129634100001003003830038300383003830038
102043003722512837181229548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100437101161129634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100197101161129634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100067101161129634100001003003830038300383003830038
1020430037224000061295482510100100100001001000050042773130300183003730037282653287451010020010000200200003003730037111020110099100100100001007157101161129634100001003003830038300383003830038
102043003722500006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100237101161129634100001003003830038300383003830038
102043003722400006129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100137101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire uop (01)cycle (02)03l1i tlb fill (04)3a3f4e51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fl1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)? int retires (ef)f5f6f7f8fd
1002430037224026229548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000101364461612102963010000103003830038300383003830038
100243003722502231295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001013644111612112963010000103003830038300383003830038
100243003722502622954825100101010000101000050427731303001830037300372828732876710010201000020200003003730037111002110910101000010223644111611112963010000103003830038300383003830038
10024301802250262295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001023644111610102963010000103003830038300383003830038
10024300372250262295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001043644111611102963010000103003830038300383003830038
1002430037224025524295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001016644101610112963010000103003830038300383003830038
10024300372250262295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001023644101611112963010000103003830038300383003830038
1002430037225026229548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000103015644816882963010000103003830038300383003830038
10024300372250262295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001020644111611102963010000103003830038300383003830038
10024300372250262295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001013644121611122963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  fcadd v0.2s, v1.2s, v0.2s, #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 uop (01)cycle (02)031e3f4e51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fl1d tlb access (a0)ld unit uop (a6)l1d cache writeback (a8)a9acc2branch cond mispred nonspec (c5)cfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)? int retires (ef)f5f6f7f8fd
10204300372250822954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000406007101161129634100001003003830038300383003830038
10204300372250892954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000100007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000100007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000100007101161129634100001003003830038300383003830038
102043003722501242954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010020140407101161129634100001003003830038300383003830038
102043003722512612954825101001041000810010000516427832903005430037300372826592874510100206100002002065630037300371110201100991001001000010000000007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000103007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000003007101161129634100001003003830038300383003830038
102043003722501032954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000203007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000200007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire uop (01)cycle (02)03mmu table walk data (08)1e1f3f4e51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fl1d tlb access (a0)l1d cache writeback (a8)a9accfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000036402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000028736402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722400061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722400082295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
100243003722500061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830084300383003830038
100243003722500061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  fcadd v0.2s, v8.2s, v9.2s, #90
  fcadd v1.2s, v8.2s, v9.2s, #90
  fcadd v2.2s, v8.2s, v9.2s, #90
  fcadd v3.2s, v8.2s, v9.2s, #90
  fcadd v4.2s, v8.2s, v9.2s, #90
  fcadd v5.2s, v8.2s, v9.2s, #90
  fcadd v6.2s, v8.2s, v9.2s, #90
  fcadd v7.2s, v8.2s, v9.2s, #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 uop (01)cycle (02)03mmu table walk data (08)181e3a3f51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fl1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)? int retires (ef)f5f6f7f8fd
80204200591500024246258010012480193100800005006407862002020039200399973399978010020080000200160206200392003911802011009910010080000100005114111610920036800001002004020040200402004020040
8020420039150004322462580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051149164920036800001002004020040200402004020040
80204200391500002462580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051149169420036800001002004020040200402004020040
80204200391500002462580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051144169920036800001002004020040200402004020040
80204200391500002462580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051149169920036800001002004020040200402004020040
8020420039150003332462580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051149167720036800001002004020040200402004020040
80204200391500002462580100100800001008000050064000020020200392008899733999780100200800002001600002003920039118020110099100100800001000051149169920036800001002004020040200402004020040
80204200391500202462580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051149167720036800001002004020040200402004020040
80204200391500002462580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000051149169920036800001002004020040200402004020040
80204200391500040824625801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000511441610920036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire uop (01)cycle (02)03mmu table walk instruction (07)mmu table walk data (08)l2 tlb miss data (0b)18191e1f3f51schedule uop (52)schedule int uop (53)schedule simd uop (54)dispatch int uop (56)dispatch simd uop (57)int uops in schedulers (59)ldst uops in schedulers (5b)60696d6emap stall dispatch (70)map rewind (75)map stall (76)dispatch uop (78)map int uop (7c)map simd uop (7e)map int uop inputs (7f)map simd uop inputs (81)8283flush restart other nonspec (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst branch cond (94)inst int alu (97)inst simd alu (9a)9fl1d tlb access (a0)l1d tlb miss (a1)ld unit uop (a6)st unit uop (a7)l1d cache writeback (a8)a9acc2cfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
800242004815000000004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100000903050204163520036080000102004020040200402004020040
800242003915000000004025800101080000108000050640000120020200392003999963100198001020800002016000020088200901180021109101080000100000009050205163520036080000102004020040200402004020040
800242003915000000004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100000500050205164420036080000102004020040200402004020040
800242003915001000004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100000700050204164520036080000102004020040200402004020040
8002420039150000001204025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100000700050204165520036080000102004020040200402004020040
800242003915000000004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100000400050203163520036080000102014420040200402004020040
800242003915000000004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100000300050204164420036080000102004020040200402004020040
800242003915000000004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100000300050203165320036080000102004020040200402004020040
800242003915000000004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100000500050205165320036080000102004020040200402004020040
800242003915000000004025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100000100050204164420036080000102004020040200402004020040