Apple M1 Microarchitecture Research by Dougall Johnson

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

ZIP2 (vector, 2S)

Test 1: uops

Code:

  zip2 v0.2s, v0.2s, v1.2s
  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
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000094216221787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037160611687251000100010002646802021203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371618611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
100420371612611687251000100010002646802018203720371572318951000100020002037203711100110000373216221787100020382038203820382038
100420371661031687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037160611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038
10042037150611687251000100010002646802018203720371572318951000100020002037203711100110000073216221787100020382038203820382038

Test 2: Latency 1->2

Code:

  zip2 v0.2s, v0.2s, v1.2s
  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)031e1f3f4e51inst 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)9fa1a6a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371550061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371550061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371550061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715612061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715500103196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000003071011611197910100001002003820038200382003820038
102042003715512061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000003071011611197910100001002003820038200382003820038
10204200371550061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000010071011611197910100001002003820038200382003820038
102042003715500251196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371550082196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715500124196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000010071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150186119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006403162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715008419687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003716306119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715008219687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150216119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200851110021109101010000100006402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  zip2 v0.2s, v1.2s, v0.2s
  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)030e1e3f4e51inst 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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037155096119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037155006119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000037101161119791100001002003820038200382003820038
1020420037155006119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000037101161119791100001002003820038200382003820038
1020420037155006119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000407101161119791100001002003820038200382003820038
10204200371550246119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037156006119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037155006119687251010010010000100100005002847680120018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
10204200371550060619687441010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000037101161119791100001002003820038200382003820038
1020420037156006119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
1020420037155006119687251010010010000100100005002847680020018020037200371842231874510100200100002002000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030f1e243f4e51inst 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)inst ldst (9b)9fa1a6a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037155000821968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000001000200640216221978510000102003820038200382003820038
1002420037155000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000001000200640216221978510000102003820038200382003820038
1002420037156000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000001000130640216221978510000102003820038200382003820038
1002420037155000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000001002000640216221978510000102003820038200382003820038
1002420037155000536196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100005601000400640216221978510000102003820038200382003820038
1002420037156000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000001000000640216221978510000102003820038200382003820038
1002420037156000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000001000000640216221978510000102003820038200382003820038
1002420037155000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000001000000640216221978510000102003820038200382003820038
10024200371563002791968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000001000000640216221978510000102003820038200382003820038
1002420037155000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000001000000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  zip2 v0.2s, v8.2s, v9.2s
  zip2 v1.2s, v8.2s, v9.2s
  zip2 v2.2s, v8.2s, v9.2s
  zip2 v3.2s, v8.2s, v9.2s
  zip2 v4.2s, v8.2s, v9.2s
  zip2 v5.2s, v8.2s, v9.2s
  zip2 v6.2s, v8.2s, v9.2s
  zip2 v7.2s, v8.2s, v9.2s
  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)031e3f51inst 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)9fa0a6a8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200381559103258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511021611200350800001002003920039200392003920039
8020420038156040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920098200392003920039
8020420038155040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
8020420038156040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011612200350800001002003920039200392003920039
8020420038161040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
8020420038155040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011612200350800001002003920039200392003920039
80204200381550170258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920089200392009120039
802042003815821211258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
802042003815501472580100100800001008000050064000002001920038200389973331018080706202807792021605862044420451918020110099100100800001002303733052251101122031523800001002046020444204472045420039
80204200381550230258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e1f3f51inst 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)9fa0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039155000090791258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001040000050204161120035080000102003920039200392003920039
8002420038155000000506258001010800001080000506400001200192003820038999681009980305208028920160000201842019041800211091010800001000000050201161120035080000102003920039200392003920039
800242003815500000084258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000050202162220035080000102003920039200392003920039
800242003815600000076258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000000050201161120035080000102003920039200392003920039
800242003815500000085258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000050201161120035080000102003920039200392003920039
8002420038155000000613258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000050201161120035080000102003920039200392003920039
800242003815500000076258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000050202161120035080000102003920039200392003920039
800242003815500000076258001010800001080000506400000200192003820038999631001880010208000020160000200382003811800211091010800001000000050201161120035080000102003920039200392003920039
800242003815600000076258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000000050201161120035280000102003920039200392003920039
800242003815600000076258001010800001080000506400001200192003820038999631001880010208000020160000200382003811800211091010800001000000050201161120035080000102003920039200392003920039