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

FMAXNM (vector, 2D)

Test 1: uops

Code:

  fmaxnm 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)031e3f4e51schedule 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 tlb miss (a1)l1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)f5f6f7f8fd
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680120182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203716061168725100010001000264680020182037203715723189510001000200020372037111001100000373116111787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
10042037150611687251000100010002646800201820372037157231895100010002000203720371110011000016073116111787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203716061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fmaxnm 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): 2.0037

retire uop (01)cycle (02)030f1e3f4e51schedule 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)9fbranch mispred nonspec (cb)cfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)? int retires (ef)f5f6f7f8fd
10204200371500174611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715010611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
1020420037150007261968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
1020420037150078611968725101001001000010010000500284768012001820037200371842531874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
1020420037150036611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
1020420037150099611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire uop (01)cycle (02)030918191e1f3f4e51schedule 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 tlb access (a0)l1d tlb miss (a1)st unit uop (a7)l1d cache writeback (a8)a9acc2branch mispred nonspec (cb)cdcfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
100242003715000090611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000000006403163319785010000102003820038200382003820038
1002420037150000480611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000000006403163319785010000102003820038200382003820038
1002420037150000180611967625100101010000101000050284896320054201322003718444318767101622010000202032420037200371110021109101010000100001002006403163319785010000102003820038200382003820038
10024200371500003001031968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000000006403163319785010000102003820038200382003820038
1002420037150000570611968725100221010012101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000000006403163319785010000102003820038200382003820038
1002420037150000240611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000000006403163319785010000102003820038200382003820038
1002420037150000210611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000000006403163319785010000102003820038200382003820038
100242003715000060611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000000006403163319785010000102003820038200382003820038
100242003715000000611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000000006403163319785010000102003820038200382003820038
1002420037150000150611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000000006403163319785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fmaxnm 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): 2.0037

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)l1d tlb miss (a1)l1d cache writeback (a8)acbranch cond mispred nonspec (c5)cfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)? int retires (ef)f5f6f7f8fd
10204200371501266119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007102161119791100001002003820038200382003820038
102042003714906119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745105852041000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715006119687441010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150246119687251010010010000100100005002847680020018200372008518422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire uop (01)cycle (02)03mmu table walk instruction (07)1e3f4e5051schedule 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? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
1002420037150006119687025100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150006119687025100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150006119687025100101010000101000050284768012001820037200371845631876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150036119687025100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500246119687025100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010036402162219785010000102003820038200382003820038
1002420037150006119687025100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500186119687025100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010106402162219785310000102003820038200382003820038
1002420037150006119687025100101010012101000050284896302009020037200371844431876710314201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150006119687025100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037150006119687025100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fmaxnm v0.2d, v8.2d, v9.2d
  fmaxnm v1.2d, v8.2d, v9.2d
  fmaxnm v2.2d, v8.2d, v9.2d
  fmaxnm v3.2d, v8.2d, v9.2d
  fmaxnm v4.2d, v8.2d, v9.2d
  fmaxnm v5.2d, v8.2d, v9.2d
  fmaxnm v6.2d, v8.2d, v9.2d
  fmaxnm 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)030f1e3f51schedule 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)accdcfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)? int retires (ef)f5f6f7f8fd
80204200491502040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010063051101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100526051101161120035800001002003920039200392003920039
8020420038150034025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001002487051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100215051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815000402580100100800001008038950064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100303051101161120035800001002003920039200392003920039
80204200381500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire uop (01)cycle (02)03l1i tlb fill (04)181e3f51schedule 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)acbranch cond mispred nonspec (c5)cfl1i tlb miss demand (d4)d5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)ea? simd retires (ee)? int retires (ef)f5f6f7f8fd
8002420047150103115258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000050211171614182003522080000102003920039200392003920039
800242003815010010925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100005021117161717200352080000102003920039200392003920039
8002420038150100298258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001009005021117161417200352080000102003920039200392003920039
80024200381501001072580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010015005021117161714200352080000102003920039200392003920039
800242003815010010025800101080000108000071640000120019200382003899963100188001020800002016000020038200381180021109101080000100005021117161316200352080000102003920039200392003920039
800242003815010011325800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100005021117161717200352080000102003920039200392003920039
800242003815010010025800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100005021114161714200352080000102003920039200392003920039
800242003815010010825800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100005021118161417200352080000102003920039200392003920039
800242003815010010025800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100005021117161717200352080000102008820039200392003920039
80024200381501009925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100005021117161718200352080000102003920039200392003920039