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

FSUB (vector, 2D)

Test 1: uops

Code:

  fsub v0.2d, v0.2d, v1.2d
  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)03181e3f4e51schedule uop (52)schedule simd uop (54)dispatch simd uop (57)ldst uops in schedulers (5b)696b6d6emap 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
1004303723006125482510001000100039831330180303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831330180303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303722008225482510001000100039831330180303730372415328951000100020003037303711100110000073116112630100030383038303830383038
10043037230010325482510001000100039831330180303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831330180303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831330180303730372415328951000100020003037303711100110000373116112630100030383038303830383038
1004303723006125482510001000100039831330180303730372415628951000100020003037303711100110002373116112630100030383038303830383038
1004303722006125482510001000100039831330180303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303722006125482510001000100039831330180303730372415328951000100020003037303711100110000073116112630100030383038303830383038
1004303723006125482510001000100039831330180303730372415328951000100020003037303711100110000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  fsub v0.2d, v0.2d, v1.2d
  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)03l2 tlb miss data (0b)191e3a3f4e51schedule 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)acbranch cond mispred nonspec (c5)branch mispred nonspec (cb)cdcfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)? int retires (ef)f5f6f7f8fd
1020430037225000061295482510100100100001001000050042773131300183003730037282727287411010020010008200200163003730037111020110099100100100001000001117180160029647100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282726287411010020010008200200163003730037111020110099100100100001000001117170160029647100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282727287411010020010008200200163003730037111020110099100100100001000001117180160029646100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282727287411010020010008200200163003730037111020110099100100100001000001117180160029647100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773130300183003730037282727287401010020010008200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
10204300372250000105295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000000007101161129634100001003003830038300383003830038
1020430037225000084295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000030007321161229634100001003003830038300383003830038
102043003722510120103295482510100100100001001059650042773130300183022830037282653287451073320010000200200003003730037111020110099100100100001000260007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire uop (01)cycle (02)03mmu table walk data (08)181e3f4e51schedule 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)simd prf full (72)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)accdcfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
1002430037225000612954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
10024300372250002322954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037224000612954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100221091010100001001006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001000006402322229630210000103003830038300383003830038
1002430037225000822954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
1002430037225000612954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038
10024300372250007262954825100101010000101000050427731303001830037300372828703287671001020100002020000300373003711100211091010100001000006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  fsub v0.2d, v1.2d, v0.2d
  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 cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)? int retires (ef)f5f6f7f8fd
1020430037225021429548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire uop (01)cycle (02)03mmu table walk instruction (07)1e3f4e51schedule 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 miss (a1)l1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
1002430037225007629548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006403163329630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006403163329630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006403163329630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006403163329630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100006403163329630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006403163329630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006403163329630010000103003830038300383003830038
10024300372250156129548251001010100001010000504277313030018300373003728287328767100122010000202000030037300371110021109101010000100006403163329630010000103003830038300383003830038
1002430037224006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006403163329630010000103003830038300383003830038
1002430037225006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100006403163329630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  fsub v0.2d, v8.2d, v9.2d
  fsub v1.2d, v8.2d, v9.2d
  fsub v2.2d, v8.2d, v9.2d
  fsub v3.2d, v8.2d, v9.2d
  fsub v4.2d, v8.2d, v9.2d
  fsub v5.2d, v8.2d, v9.2d
  fsub v6.2d, v8.2d, v9.2d
  fsub v7.2d, v8.2d, v9.2d
  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)03l2 tlb miss data (0b)3f51schedule 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)a9acc2cfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)? int retires (ef)f5f6f7f8fd
8020420057150041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000000051103161120036800001002004020040200402004020040
8020420039150041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000000051101161120036800001002004020040200402004020040
8020420039150041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000000051101161120036800001002004020040200402004020040
8020420039150041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000000051101161120036800001002004020040200402004020040
80204200391500798258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000000051101161120036800001002004020040200402004020040
8020420039150041258010010080000100800005006400000200202003920039997339997801002008000020016000020039200391180201100991001008000010000000051101161120036800001002004020040200402004020040
80204200391500844258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000000051101161120036800001002004020040200402004020040
8020420039150083258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000000051101161120036800001002004020040200402004020040
8020420039150041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000000051101161120036800001002004020040200402004020040
8020420039150041258010010080000100800005006400001200202003920039997339997801002008000020016000020039200391180201100991001008000010000000051101161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire uop (01)cycle (02)031e3f51schedule 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)accfd2l1i cache miss demand (d3)d5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)? int retires (ef)f5f6f7f8fd
800242003915008425800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050200618169172003680000102004020040200402004020040
80024200391500646258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000502006171613172003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000502006151616142003680000102004020040200402004020040
800242003915006325800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050200771617142003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000502007161618182003680000102004020040200402004020040
800242003915001300258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000502056141617132003680000102004020040200402004020040
8002420039150059325800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050200681617142003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000502006151610172003680000102004020040200402004020040
800242003915006225800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050200891616132003680000102004020040200402004020040
80024200391500711258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000502008161614162003680000102004020040200402004020040