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

ADDP (vector, 2D)

Test 1: uops

Code:

  addp 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)03l2 tlb miss data (0b)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)cfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)f5f6f7f8fd
100420371600611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371500611687251000100010002646801201820372037157231895100010002000203720371110011000173116111787100020382038203820382038
100420371500611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371500611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371600611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371500611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371500611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371600611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371600611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371500611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  addp 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)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)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)accdcfd5map dispatch bubble (d6)ddfetch restart (de)e0? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
102042003715066631196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500631196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011610197910100001002003820038200382003820038
102042003715012661196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197912100001002003820038200382003820038
10204200371500346196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

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)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)acbranch cond mispred nonspec (c5)cfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)? int retires (ef)f5f6f7f8fd
1002420037150606119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000661316561982810000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640616651978510000102003820038200382003820038
1002420037150034619687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640516551978510000102003820038200382003820038
100242003715008219687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640516651978510000102003820038200382003820038
100242003715066119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640516561978510000102003820038200382003820038
1002420037150023719687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640616651978510000102003820038200382003820038
1002420037150336119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640416641978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640416661978510000102003820038200382003820038
1002420037150934619687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640616461978510000102003820038200382003820038
1002420037150186119687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000640616651978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  addp 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)696d6emap 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? int output thing (e9)? simd retires (ee)? int retires (ef)f5f6f7f8fd
10204200371500611968725101001001000010010000500284768020018200372003718422031874510100200100002002000020037200371110201100991001001000010006071011611197910100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422031874510100200100002002000020037200371110201100991001001000010009071011611197910100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422031874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715009351968725101001001000010010000500284768020018200372003718422031874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422031874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184220318745101002001000020020000200372003711102011009910010010000100018071011611197910100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020022200372003718422031874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422031874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500711968725101001001000010010000500284768020018200372003718422031874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768020018200372003718422031874510100200100002002000020037200371110201100991001001000010000071011611197910100001002003820038200382003820038

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)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
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010459640416551978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001013640616461978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010340640616651978510000102003820038200382003820038
100242003715017461196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640516551978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640516461978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001020640616561978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001013640616651978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001023640516461978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640516551978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000107159640616561978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  addp v0.2d, v8.2d, v9.2d
  addp v1.2d, v8.2d, v9.2d
  addp v2.2d, v8.2d, v9.2d
  addp v3.2d, v8.2d, v9.2d
  addp v4.2d, v8.2d, v9.2d
  addp v5.2d, v8.2d, v9.2d
  addp v6.2d, v8.2d, v9.2d
  addp 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)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)accdcfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)? int retires (ef)f5f6f7f8fd
8020420058150040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010023051101161120035800001002003920039200392003920039
80204200381500515258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010083051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010053051101161120035800001002003920039200392003920039
80204200381500612580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100012051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100146051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010010051101161120035800001002003920039200392003920039
802042003815007052580100100800001008000050064000002001920038200389973399968010020080000200160000200382003811802011009910010080000100290051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010013051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039

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)5f60696d6emap 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)9fld unit uop (a6)l1d cache writeback (a8)accfd5map dispatch bubble (d6)ddfetch restart (de)e0? simd retires (ee)? int retires (ef)f5f6f7f8fd
8002420047150039258001010800001080000506400000020019200382003899960310018800102080000201600002003820038118002110910108000010003502011161392003580000102003920039200392003920039
8002420038150039258001010800001080000506400000120019200382003899960310018800102080000201600002003820038118002110910108000010019120503812161282003580000102003920039200392003920190
80024200381500392580010108000010800005064000001200192003820038999603100188001020800002016000020038200381180021109101080000100105020121612122003580000102003920039201002003920039
80024200381510392580010108000010800005064000000200192003820038999603100188001020800002016000020038200381180021109101080000100005020141612122003580000102003920039200392003920039
80024200381500392580010108000010800005064000001200192003820038999603100188001020800002016000020038200381180021109101080000100735020131613132003580000102003920039200392003920039
800242003815003925800101080000108000050640000002001920038200389996031001880010208000020160000200382003811800211091010800001000050208169122003580000102003920039200392003920039
8002420038150039258001010800001080000506400000120019200382003899960310018800102080000201600002003820038118002110910108000010060502081612122003580000102003920039200392003920039
80024200381500392580010108009510800965064000000200192003820038999603100188001020800002016000020038200381180021109101080000100335020121613132003580000102014020039200392003920091
80024200381500392580010108000010800005064000001200192003820038999603100188001020800002016000020038200381180021109101080000100605020121612122003580000102003920039200392003920039
80024200381500210258001010800001080000506400000120019200382003899960310018800102080000201600002003820038118002110910108000010011115037131613132003580000102003920039200392003920039