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

FMINNMP (vector, 2D)

Test 1: uops

Code:

  fminnmp 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 cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)f5f6f7f8fd
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012054203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371507816872510001012100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037151566116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715010316872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110001073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fminnmp 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)03l2 tlb miss data (0b)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)60696b6d6emap 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
10204200371500061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100107101161119791100001002003820038200382003820038
10204200371510082196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100107101161119791100001002003820038200382003820038
10204200371500961196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000620196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002018320038200862003820038
10204200371500061196872510100100100001001000050028476800200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200180200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000727101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire uop (01)cycle (02)03mmu table walk data (08)l2 tlb miss data (0b)18191e1f3f4e51schedule 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)l1d cache writeback (a8)a9acc2cfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
100242003715000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006403164419785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006404164319785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000020006403164419785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006403164419785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006403163419785010000102003820038200382003820038
100242003714900000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006404163419785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000060006404164419785010000102003820038200382003820038
100242003715000000082196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006403163419785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006404164319785010000102003820038200382003820038
100242003715001000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006404164319785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fminnmp 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)03181e3f4e51schedule 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? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
10204200371500066196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010004271021622197910100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000371021622197910100001002003820038200382003820038
102042003715002461196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000710216221979126100001002003820038201362003820038
10204200371500246119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
10204200371500024419687251010010010000100100005002847680200182003720037184223187451010020410000200200002003720037111020110099100100100001000071021622197910100001002008520038200382003820038
1020420037150006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
10204200371500023219687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
1020420037150008219687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001001071021622197910100001002003820038200382003820038

1000 unrolls and 10 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)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 cache writeback (a8)accdcfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)? int retires (ef)f5f6f7f8fd
1002420037150018719687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150021019687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010001640216221978510000102003820038200382003820038
1002420037150033019687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715008219687251001010100001010000502847680120018200372003718444731876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150014519687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010100640216221978510000102003820038200382003820038
1002420037150014519687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010200640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010100640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150053619687251001010100001010000502847680120018200372003718444031876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fminnmp v0.2d, v8.2d, v9.2d
  fminnmp v1.2d, v8.2d, v9.2d
  fminnmp v2.2d, v8.2d, v9.2d
  fminnmp v3.2d, v8.2d, v9.2d
  fminnmp v4.2d, v8.2d, v9.2d
  fminnmp v5.2d, v8.2d, v9.2d
  fminnmp v6.2d, v8.2d, v9.2d
  fminnmp 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)0318191e1f3f51schedule 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)a9acc2cfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
8020420059150000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010001000511021611200350800001002003920039200392003920039
80204200381500000231258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611201160800001002003920039200392003920039
8020420038150000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
8020420038150000082258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000517811611200351800001002003920039200392003920039
8020420038150000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000016530511011611200350800001002003920039200392003920039
8020420038150000040258010010080000100800005006400001200192003820038997339996801002008009720016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
8020420038150000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392024020039
80204200381500100168258010010080000100800006026400001200192003820038997339996801002008000020016000020038200381180201100991001008000010001000511014011200350800001002003920039200392003920039
8020420038150000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511021611200350800001002003920039200392003920039
8020420038150000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000002511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire uop (01)cycle (02)03mmu table walk data (08)l2 tlb miss data (0b)18191e1f3a3f51schedule 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)l1d cache writeback (a8)a9acc2branch mispred nonspec (cb)cfd0d5map dispatch bubble (d6)dbddfetch restart (de)e0? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
8002420047151000000019025800101080000108000050640000020019200382003899963100188001020800002016000020038200381180021109101080000100000000050200131604920035080000102003920039200392003920039
800242003815000000003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000000050200121605420035080000102003920039200392003920039
8002420038150000012001682580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000103005020051604520035080000102007420039200392003920039
80024200381550000000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000006015020051605520035080000102003920039200392003920039
80024200381500000000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000000005020091606720035080000102003920039200392003920039
80024200381500000000392580010108000010800005064000002001920038200389996310018800102080000201600002003820038118002110910108000010000003005020011160101020035080000102003920039200392003920039
80024200381500000000392580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000005020051604420035080000102003920039200392003920039
800242003815000000003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000030050200616051120035080000102003920039200392003920039
80024200381500000000602580010108000010800005064000012001920038200389996310018800102080000201600002003820038118002110910108000010000000005020061606520035080000102003920039200392003920039
8002420038150000000020725800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100000030050200716010520035080000102003920039200392003920039