Apple M1 Microarchitecture Research by Dougall Johnson

Firestorm: Overview | Base Instructions | SIMD and FP Instructions
Icestorm:  Overview | Base Instructions | SIMD and FP Instructions

ZIP1 (vector, 4S)

Test 1: uops

Code:

  zip1 v0.4s, v0.4s, v1.4s
  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 (01)cycle (02)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371506116872510001000100026468020182037203715723189510001000200020372037111001100013973216221787100020382038203820382038
10042037163611687251000100010002646802018203720371572318951000100020002037203711100110000215873216221787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371601051687251000100010002646802018203720371572318951000100020002037203711100110000373216221787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000373216221787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000373216221787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000673216221787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371606116872510001000100026468020182037203715723189510001000200020372037111001100005473216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  zip1 v0.4s, v0.4s, v1.4s
  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 (01)cycle (02)030b1e1f3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa1a8a9accfd1d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715509012519687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038
1020420037155000103196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000004871001161119791100001002003820038200382003820038
102042003715500021519687251010010010000100100005002847680020018200372003718422318763102742001000020020000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038
10204200371550006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038
102042003715500025119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038
10204200371550006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038
10204200371560006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038
10204200371550006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038
10204200371610006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038
10204200371550006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000071001161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037156120841968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785110000102003820038200382003820038
1002420037156240611968725100101010000101000050284768002001820037200371844431876710010201016820200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037155005361968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162319785010000102003820038200382003820038
100242003715500611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402163219853010000102003820038200382003820038
100242003715500851968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715500611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010106402162219785010000102003820038200382003820038
100242003715500841968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037155120611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
1002420037155004511968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010106402162319785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  zip1 v0.4s, v1.4s, v0.4s
  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 (01)cycle (02)0308090b18191e1f3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a8a9acbcc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371560000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371560000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003715500000000103196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371550000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371550000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371550000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371550000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371550000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371550000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
10204200371550000000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000030071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030818191e1f3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696b6d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acbranch mispredict (cb)cfd0d5d6ddinst fetch restart (de)dfe0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371560000006119687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010000646741622319785010000102003820038200382003820038
100242003715500012037219687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010000646721622319785010000102003820038200382003820038
100242003715500030037219687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010100646721622319785010000102003820038200382003820038
10024200371550000037219687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010000646721622319785010000102003820038200382003820038
10024200371550000037219687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010000646721622319785010000102003820038200382003820038
10024200371550000037219687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010000646721622319785010000102003820038200382003820038
100242003715500000373719687251001010100001010000502847680120018020037200371844431876710010201000020200002003720037111002110910101000010130646721622319785010000102003820038200382003820038
1002420037155000003105196872510010101000010100005028476800200180200372003718444318767100102010000202000020037200371110021109101010000103731646721622319785010000102003820038200382003820038
10024200371550000037219687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037211002110910101000010000646421622319785010000102003820038200382003820038
100242003715500000373719687251001010100001010000502847680020018020037200371844431876710010201000020200002003720037111002110910101000010000646421622319785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  zip1 v0.4s, v8.4s, v9.4s
  zip1 v1.4s, v8.4s, v9.4s
  zip1 v2.4s, v8.4s, v9.4s
  zip1 v3.4s, v8.4s, v9.4s
  zip1 v4.4s, v8.4s, v9.4s
  zip1 v5.4s, v8.4s, v9.4s
  zip1 v6.4s, v8.4s, v9.4s
  zip1 v7.4s, v8.4s, v9.4s
  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 (01)cycle (02)0308090b18191e1f3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200491550000042040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000010001511021611200350800001002003920039200392003920039
80204200381550000015061258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
8020420038155000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
8020420038155000003040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
80204200381550000015040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
80204200381560000000325258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
80204200381550000478040258020210080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
8020420038155000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
8020420038155000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039
8020420038156000000040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a1e1f3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048155005707042580010108000010800005064000002001920038200389996310018800102080000201600002003820088118002110910108000010005750202161220035080000102003920039200392003920039
80024200381550026703837258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000050201161120035080000102003920039200392003920039
8002420038155003270118258001010800001080000506400000200192003820038999631001880012208000020160000200382003811800211091010800001000050201161120035080000102003920039200392003920039
8002420038156000039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000050201161120035080000102003920039200392003920039
8002420038155016039258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000050201161120035080000102003920039200392003920039
800242003815500035239258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000050201161320076080000102003920039200392003920039
80024200381550018039258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000050201161120035080000102003920039200392003920039
800242003815500102044258001010800001280000606400000200192003820038999631001880012208000020160000200382003811800211091010800001000050201161120035080000102003920039200392003920039
800242003815500453067258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000050201161120035080000102003920039200392003920039
8002420038155008701016258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001010050201161120035080000102003920039200392003920039