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, 16B)

Test 1: uops

Code:

  zip2 v0.16b, v0.16b, v1.16b
  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)60696d6edispatch 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
100420371536116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000973116111787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371609016872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000198573116111787100020382038203820382038
1004203716010316872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371608416872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715126116872510001000100026468002018203720371572318951000100020002037203711100110001073116111787100020382038203820382038
1004203715010316872510001000100026468012018203720371572318951000100020002037203711100110001073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  zip2 v0.16b, v0.16b, v1.16b
  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)0318191e1f3f4e51inst 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)696d6edispatch 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)9fa0a1a6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371550060061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000010071011611197910100001002003820038200382003820038
10204200371550051061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037155000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382008720038
10204200371553112061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037155000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037155000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037155000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371560000145196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371550030346196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371550036081196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038

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)6061696d6edispatch 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)9fa8accfd0d5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715033361196872510010101000010100005028476800320018200372003718444318767100102010000202000020037200371110021109101010000100064002160221978510000102003820038200382003820038
100242003715036961196872510010101000010100005028476800020018200372003718444318803100102010000202000020037200371110021109101010000100064002160221978510000102003820038200382003820038
1002420037149396536196872510010101000010100005028476800020018200372003718444318767100102010000202000020037200371110021109101010000100064002160221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801020018200372003718444318767100102010000202000020037200371110021109101010000100064002160221978510000102003820038200382003820038
10024200371501561196872510010101000010100005028476801020018200372003718444318767100102010000202000020037200371110021109101010000100064032160221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476801020018200372003718444318767100102010000202000020037200371110021109101010000100064002160221978510000102003820038200382003820038
1002420037150061196872510010101000010100005028476800020018200372003718444318767100102010000202000020037200371110021109101010000100064002160221978510000102003820038200382003820038
10024200371491861196872510010101000010100005028476800020018200372003718444318767100102010000202000020037200371110021109101010000100064002160221978510000102003820038200382003820038
10024200371502461196872510010101000010100005028476800020018200372003718444318767100102010000202000020037200371110021109101010000100064002160221978510000102003820038200382003820038
1002420084150961196872510010101000010100005028476800020018200372003718444318767100102010000202000020037200371110021109101010000100064002160221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  zip2 v0.16b, v1.16b, v0.16b
  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)030408090b18191e1f3a3f4e51inst 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)9fa0a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037155000000000611968725101001001000010010000500284768002001820037200371842971874010100200100082002001620037200371110201100991001001000010000000071011611197910100001002018320230201352017920181
10204201801561011000001031968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037155000000000821968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000100071011611197910100001002003820038200382003820038
1020420037155000000600891968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
10204200371550000002100611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000403071011611197910100001002003820038200382003820038
10204200371550000001200611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037155000000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037155000000000611968725101001001000010010000522284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
1020420037155000000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038
102042003715500000012007311968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371550000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371550000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371560000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371550000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371550000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
100242003715500000010319687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371550000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371560000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371550000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100001036402162219785010000102003820038200382003820038
10024200371550000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  zip2 v0.16b, v8.16b, v9.16b
  zip2 v1.16b, v8.16b, v9.16b
  zip2 v2.16b, v8.16b, v9.16b
  zip2 v3.16b, v8.16b, v9.16b
  zip2 v4.16b, v8.16b, v9.16b
  zip2 v5.16b, v8.16b, v9.16b
  zip2 v6.16b, v8.16b, v9.16b
  zip2 v7.16b, v8.16b, v9.16b
  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)030a1e3f51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581552040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010020051103162220035800001002003920039200392003920039
80204200381562040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102162220035800001002003920039200392003920039
80204200381552040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102162220035800001002003920039200392003920039
802042003815521240258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102162220035800001002003920039200392003920039
80204200381552040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102162220035800001002003920039200392008820039
8020420038155201825258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102162220035800001002003920039200392003920039
80204200381552040258010010080000100800005006400001200192003820038997339996801002008000020016039620038200381180201100991001008000010000051102162220035800001002003920039200392003920039
80204200381552040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010003051102162220035800001002003920039200392003920039
80204200381562040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102162220035800001002003920039200392003920039
80204200381552040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102162220035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3a3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0eaebec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481551203925800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010005020516662003500080000102003920039200392003920039
8002420038155003925800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010005020616562003500080000102003920039200392003920039
8002420038155003925800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010105020616652003500080000102003920039200392003920039
8002420038155003925800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010005020616672003500080000102003920039200392003920039
8002420038156003925800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010005020516552003500080000102003920039200392003920039
80024200381550060258001010800001080000506400000200190200382003899963100188001020800002016000020038200381180021109101080000105050207167820035006280000102003920039200392003920039
80024200381550051425800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010005020616572003500080000102003920039200392003920039
8002420038155003925800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010005020616772003500080000102003920039200392003920039
8002420038155006025800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010005020616662003500080000102003920039200392003920039
8002420038155003925800101080000108000050640000020019020038200389996310018800102080000201600002003820038118002110910108000010005020716562003500080000102003920039200392003920039