Apple M1 Microarchitecture Research by Dougall Johnson

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

UZP1 (vector, 4S)

Test 1: uops

Code:

  uzp1 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)03081e3f4e51inst 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)a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203716001511687251000100010002646800201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
1004203716001031687251000100010002646800201820372037157231895100010002000203720371110011000000373116111787100020382038203820382038
100420371500611687251000100010002646800201820372037157231895100010002000203720371110011000000373116111787100020382038203820382038
1004203717006116872510001000100026468002018203720371572318951000100020002037203711100110000100373116111787100020382038203820382038
1004203715001031687251000100010002646800201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
100420371600611687251000100010002646800201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
100420371500611687251000100010002646800201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
100420371600611687251000100010002646800201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
100420371500611687251000100010002646800201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
100420371600611687251000100010002646800201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  uzp1 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)030b181e3f4e51inst 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037155000611968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371550001711968725101001001000010010000500284768012001802003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371550001251968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371550001451968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371550001661968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715600011101968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037155000821968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371550001371968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371550001241968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371560001681968725101001001000010010000500284768002001802003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03050818191e1f3f4e51inst 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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000186402162219785010000102003820038200382003820083
100242003715000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000216402162219785010000102003820038200382003820038
100242003715000000082196872510010101000010100005028476800200182003720037184443187671001020101622020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
1002420037150000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000666402162219785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200842003711100211091010100001000206402162219785010000102003820038200382003820038
100242003715000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000006402242219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uzp1 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)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)72scheduler 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)9fa0a1a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371550000120061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037155000000061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100000003071011611197910100001002003820038200382003820038
10204200371560000000126196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100000003071011611197910100001002003820038200382003820038
10204200371550000120061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371550000000578196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037156000000061196872510100100100001001000050028476801200182003720037184220318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
1020420037156000000061196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100000000071011611197910100001002003820038200382003820038
10204200371550000000103196872510100100100001001000050028476801200182003720037184220318745104272041000020020000200372003711102011009910010010000100000100071011621198590100001002003820038200382003820038
10204200371551177933616049131963219310225141100721501076075128566610203062037120376184483271887211201222108262222265620372203718110201100991001001000010000000158000867294232009728100001002042120372204112037120372
10204204191561078669704244561961015910244136100961451121670328579041202702037420372184430311883911210217109902202198420361203607110201100991001001000010022000122100871125212007024100001002032720322203742022820325

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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037155000000515196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003716100000082196872510010101000010100005028476800200182003720037184443187671001020100002020324200852003711100211091010100001000640216221978510000102003820038200382003820038
100242003715500000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037155000000273196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037155000000105196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715500000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037155000000103196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037156000000103196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
100242003715500000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038
1002420037155000000444196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uzp1 v0.4s, v8.4s, v9.4s
  uzp1 v1.4s, v8.4s, v9.4s
  uzp1 v2.4s, v8.4s, v9.4s
  uzp1 v3.4s, v8.4s, v9.4s
  uzp1 v4.4s, v8.4s, v9.4s
  uzp1 v5.4s, v8.4s, v9.4s
  uzp1 v6.4s, v8.4s, v9.4s
  uzp1 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)0307080a0b18191e1f3a3f5051inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420048155000000000400258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000000000511031632200350800001002003920039200392003920039
80205200381550000003300400258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000000030511021623200350800001002003920039200392003920039
80204200381550000001200400258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011633200350800001002003920039200392003920039
802042003815600000054007050258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000000000511031643200350800001002003920039200392003920039
8020420038155000000630040025801001008000010080000500640000120019020038200389973399968010020080000200160000200382003811802011009910010080000100000144700511021633200350800001002003920039200392003920039
80204200381550000005100400258010010080000100800005006407561200190200382003899733999680100200800002001600002003820038118020110099100100800001000000000511031633200350800001002003920039200392003920039
802042003815600000016200400258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000000000511031622200350800001002003920039200392003920039
802042003815500000021000400258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000000000511031632200350800001002003920039200392003920039
80204200381550000005700400258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000000000511031633200350800001002003920039200392003920039
802042003815500000054000400258010010080000100800005006400001200190200382003899733999680100200800002001600002003820038118020110099100100800001000000000511021622200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b1e1f3f51inst 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)5f6066696d6edispatch 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)9fa9acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391550000609258001010800001080000506400001102001920038200389996310018800102080000201600002003820038118002110910108000010000502081610102003580000102003920039200392003920039
800242003815600003925800101080000108000050640000010200192003820038999631001880010208000020160000200382003811800211091010800001000050207168102003580000102003920039200392003920039
80024200381550021039258001010800001080000506400000002001920038200389996310018800102080000201600002003820038118002110910108000010000502091610102003580000102003920039200392003920039
80024200381560030039258001010800001080000506400000002001920038200389996310018800102080000201600002003820038118002110910108000010000502091611112003580000102003920039200392003920039
80024200381550054039258001010800001080000506400000002001920038200389996310018800102080000201600002003820038118002110910108000010030502011169102003580000102003920039200392003920039
80024200381550023403925800101080000108000050640000000200192003820038999631001880010208000020160000200382003811800211091010800001000050209169112003580000102003920039200392003920039
80024200381550072039258001010800001080000506400000002001920038200389996310018800102080000201600002003820038118002110910108000010000502010161062003580000102003920039200392003920039
80024200381550036039258001010800001080000506400000002001920038200389996310018800102080000201600002003820038118002110910108000010000502010168102003580000102003920039200392003920039
8002420038155005403925800101080000108000050640000000200192003820038999631001880010208000020160000200382003811800211091010800001000050207169112003580000102003920039200392003920039
80024200381550033039258001010800001080000506400000002001920038200389996310018800102080000201600002003820038118002110910108000010000502011169112003580000102003920039200392003920039