Apple M1 Microarchitecture Research by Dougall Johnson

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

UZP2 (vector, 8H)

Test 1: uops

Code:

  uzp2 v0.8h, v0.8h, v1.8h
  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
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073316111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203716010316872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000373116111787100020382038203820382038
100420371606116872510001000100026468012018207320371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  uzp2 v0.8h, v0.8h, v1.8h
  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)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)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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037155121261968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007102161119791100001002003820038200382003820038
1020420037156212511968725101001001000010010000500284768020018200372003718422318745101002001000020020328200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715601451968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371550611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371560611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037156241241968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715501031968725101001001000010010000500284768020018200372003718422318745101002041000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371550611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715501281968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715501701968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038

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)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)9fa0a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000685216221978510000102003820038200382003820038
10024200371506611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715003481968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100090640216221978510000102003820038200382003820038
10024200371500611968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100030640216221978510000102003820038200382003820038
100242003715001471968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715001031968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100400640216221978510000102003820038200382003820038
100242003715004531968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715003641968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150011681968725100101010000101000050284768020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715006119687251001010100001010000502847680200182007020037184443187671001020100002020000200372003711100211091010100001000120640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  uzp2 v0.8h, v1.8h, v0.8h
  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)03080b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000030071011611197910100001002003820038200382003820038
102042003715500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003715600000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002008520038200382003820038
102042003715500000082196872510100100100001001000064828476801200182003720037184223187451010021210000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003715500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003715500000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037155000012061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003715500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200203362013520037111020110099100100100001000000000071011611197910100001002003820038200382003820038
102042003715500000061196872510100100100001001000050028476801200182003720037184223187631010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038
1020420037155000000593196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030708090b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371550000000001051968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006403163719785010000102003820038200382003820038
10024200371550000000007691968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006403167319785010000102003820038200382003820038
1002420037155000000000821968725100101010000101000050284768012001820037200371844431878610010201000020200002003720037111002110910101000010000000006403166319785010000102003820038200382003820038
1002420037156000000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006403167319785010000102003820038200382003820038
10024200371550000000001101968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006403167319785010000102003820038200382003820038
1002420037155000000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006403167319785010000102003820038200382003820038
1002420037156000000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006403167319785010000102003820038200382003820038
10024200371550000000003811968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006403167319785010000102003820038200382003820038
1002420037155000000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000000006403167319785010000102003820038200382003820038
1002420037155000000000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000020006403167319785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  uzp2 v0.8h, v8.8h, v9.8h
  uzp2 v1.8h, v8.8h, v9.8h
  uzp2 v2.8h, v8.8h, v9.8h
  uzp2 v3.8h, v8.8h, v9.8h
  uzp2 v4.8h, v8.8h, v9.8h
  uzp2 v5.8h, v8.8h, v9.8h
  uzp2 v6.8h, v8.8h, v9.8h
  uzp2 v7.8h, v8.8h, v9.8h
  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)03081e1f3f51inst 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)9fa0a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200601560007125801081008000810080020500640132020019200382003899776998980120200800322001600642003820038118020110099100100800001000100111511801600200350800001002003920039200392003920039
80204200381550002925801081008000810080020500640132020019200382003899776998980120200800322001600642003820038118020110099100100800001000000111511801600200350800001002003920039200392003920039
80204200381550004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000100000511011611200350800001002003920039200392003920039
80204200381560006125801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000020000511011611200350800001002003920039200392003920039
80204200381550004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381550004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381550004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
8020420038155000197825801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381550004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039
80204200381550004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03090a0b18191e1f3f51inst 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)9fa0a1a7a8a9acc2cficache miss (d3)d5d6d9daddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420047155000000039258001010800001080000506400001520019200382003899963100188001020800002016000020038200381180021109101080000100000000502002161202120035080000102003920039200392003920039
800242003815500000006025800101080000108000050640000102001920038200389996310018800102080000201600002003820038118002110910108000010000000050200116802120035080000102003920039200392003920039
8002420038155000000039258001010800001080000506400000020019200382003899962610018800102080000201600002003820038118002110910108000010000000050200116801120035080000102003920039200392003920039
800242003815500000003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010000000050200116812920035080000102003920039200392003920039
800242003815500000003925800101080000108000050640000102001920038200389996310018801122080000201600002003820038118002110910108000010000000050200116003120035080000102003920039200392003920039
800242003815500000003925800101080000108000050640000102001920038200389996310018800102080000201600002003820038118002110910108000010000000050200116003120035080000102003920039200392003920039
800242003815500000003925800101080000108000050640000102001920038200389996310018800102080000201600002003820038118002110910108000010000000050200116001120035080000102003920039200392003920039
800242003815500000003925800101080000108000050640000102001920038200389996310018800102080000201600002003820038118002110910108000010000000050200216001120035080000102003920039200392003920039
8002420038156000000012425800101080000108000050640000102001920038200389996310018800102080000201600002003820038118002110910108000010000000050200116001120035080000102003920039200392003920039
8002420038156000000012925800101080000108000050640000102001920038200389996310018800102080000201600002003820038118002110910108000010000000050200116001120035080000102003920039200392003920039