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, 4H)

Test 1: uops

Code:

  zip2 v0.4h, v0.4h, v1.4h
  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
10042037161215616872510001000100026468012018203720371572318951000100020002037203711100110000073116221787100020382038203820382038
1004203716012416872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000373116211787100020382038203820382038
100420371608416872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116211787100020382038203820382038
1004203716349116872510001000100026468012018203720371572318951000100020002037203711100110000073116121787100020382038203820382038
100420371536116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  zip2 v0.4h, v0.4h, v1.4h
  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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371550000030006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037161000000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371550000075006119687251010010010000100100005002847680120018203682035818444431887311044224106142202232420369203698110201100991001001000010020210139102869273121993426100001002035720371204172037420418
10204203701580028794261613968196101521022414810096146112127422857944120270203712040718446361887911364225111672282265620408204235110201100991001001000010000210120930850272142004134100001002037020326203722032620370
10204203271581107784361604338196431571022213510072147110647112856661020270203742037318445271887311205221111612122199820323203228110201100991001001000010004214138780867273222003924100001002037220374203742013420371
10204203721560107794261602287196101551022412910084146110647012856541120270203232041818443371887111206218109952162232020420203227110201100991001001000010020010139080870173112004334100001002037120373203692037220366
102042037015800077855704144211961016010230141100841401015269828563641202702037220369184442518873112012041000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037155000006006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037155000000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037161000000006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000071011711197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308181e1f3f4e51inst 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)9fa1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150005706119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150001506119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100001006402162219785010000102003820038200382003820038
1002420037150007206119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
100242003715000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
100242003715000006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500024034619687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150003606119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150002106119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
10024200371500020108219687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038
1002420037150002106119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  zip2 v0.4h, v1.4h, v0.4h
  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)03080b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715500000008219687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000000071021611197910100001002003820038200382003820038
10204200371550000336006119687251010010010000100100005002847680020054200372003718422318745101002121033320420000200372003711102011009910010010000100000000000071011611197910100001002003820038200382003820038
1020420037155000012006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000000071011611197910100001002003820038200382003820038
102042003715500000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000000071011611197910100001002003820038200382003820038
102042003715500000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000300071011611197910100001002003820038200382003820038
102042003715500000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000000071011611197910100001002003820038200382003820086
102042003716000046006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000000071011611197910100001002003820038200382003820038
1020420037155000015006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000000000071011611197910100001002003820038200382003820038
1020420037156000012006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000000071011611197910100001002003820038200382003820038
102042003715600000006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030a18191e3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371550000103196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
1002420037156000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
1002420037155000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
10024200371550000536196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
1002420037155000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
1002420037155000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
10024200371560001561196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
10024200371560003961196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640616331978510000102003820038200382003820038
1002420037155200061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038
1002420037155200061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640316331978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  zip2 v0.4h, v8.4h, v9.4h
  zip2 v1.4h, v8.4h, v9.4h
  zip2 v2.4h, v8.4h, v9.4h
  zip2 v3.4h, v8.4h, v9.4h
  zip2 v4.4h, v8.4h, v9.4h
  zip2 v5.4h, v8.4h, v9.4h
  zip2 v6.4h, v8.4h, v9.4h
  zip2 v7.4h, v8.4h, v9.4h
  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)03080b1e3f51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200601550008225801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051103161120035800001002003920039200392003920039
802042003815600040258010010080084100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010016051101161120035800001002003920039200392003920039
802042003815500040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010005751101161120035800001002003920039200392003920039
802042003815500023025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381550004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815500040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010001551101161120035800001002003920039200392003920039
802042003815500040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010003951101161120035800001002003920039200392003920039
802042003815500040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010004251101161120035800001002003920039200392003920039
80204200381561004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000951101161120035800001002003920039200392003920039
802042003815500040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010007251101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e3f51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391560012639258001010800001080000506400002001920038200389996310018800102080000201600002003820038118002110910108000010000502091681720035080000102003920039200392003920039
800242003815500039258001010800001080000506400002001920089200389996310018800102080000201600002003820038118002110910108000010400502061681720035080000102003920039200392003920039
800242003815500039258001010800001080000506400002001920038200389996310018801082080000201600002003820038118002110910108000010000502061618720035080000102003920039202422003920039
8002420038155000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100035020171617720035080000102003920039200392003920039
80024200381550003925800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001000050201416171720035080000102003920039200392003920039
8002420038155000832580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100005020171617820035080000102003920039200392003920091
8002420038155000394480010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100005020171681720035080000102003920039200392003920039
8002420038155000602580010108000010800005064000020019200382003899963100188011020800002016000020038200381180021109101080000100005020171681720035080000102003920039200392003920039
8002420038156000392580010108000010800005064000020019200382003899963100188011020800002016000020038200381180021109101080000100005020171661720035080000102003920039200392003920039
8002420038156000392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100005020171671420035080000102003920039200392003920039