Apple M1 Microarchitecture Research by Dougall Johnson

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

NEG (vector, 2S)

Test 1: uops

Code:

  neg v0.2s, v0.2s
  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)0308181e1f3f4e51inst 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)a0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150000611686251000100010002645212018203720371571318951000100010002037203711100110000000000073116111786100020382038203820382038
10042037150000611686251000100010002645212018203720371571318951000100010002037203711100110000000000073116111786100020382038203820382038
10042037150000611686251000100010002645212018203720371571318951000100010002037203711100110000000000073116111786100020382038203820382038
10042037150000611686251000100010002645212018203720371571318951000100010002037203711100110000000000073116111786100020382038203820382038
10042037150000611686251000100010002645212018203720371571318951000100010002037203711100110000000003073116111786100020382038203820382038
10042037150000611686251000100010002645212018203720371571318951000100010002037203711100110000000000073116111786100020382038203820382038
10042037150000821686251000100010002645212018203720371571318951000100010002037203711100110000000000073116111786100020382038203820382038
100420371500630611686251000100010002645212018203720371571318951000100010002037203711100110000000000073116111786100020382038203820382038
10042037150030611686251000100010002645212018203720371571318951000100010002037203711100110000000100073116111786100020382038203820382038
10042037150000611686251000100010002645212018203720371571318951000100010002037203711100110000000000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  neg v0.2s, 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)030e3f4e51inst 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)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)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150061196862510100100100001001000050028475212001820037200371842103187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
10204200371500441196862510100100100001001000050028475212001820037200371842103187451010020010000200100002003720037111020110099100100100001000000073911611197910100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475212001820037200371842103187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475212001820037200371842103187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475212001820037200371842103187451010020010000200100002003720037111020110099100100100001002003371011611197910100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475212001820037200371842103187451010020010000200100002003720037111020110099100100100001000001071011611197910100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475212001820037200371842103187451010020410000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475212001820037200371842103187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475212001820037200371842103187451010020010000200100002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475212001820037200371842103187451010020010000200100002003720037111020110099100100100001000000671011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b181e1f3a3f4e51inst 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)9fa0a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000000061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
10024200371500000000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100031006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010001036402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010001006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038
1002420037150000000061196862510010101000010100005028475212001820037200371844331876710010201000020100002003720037111002110910101000010000006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  neg v0.2s, v8.2s
  neg v1.2s, v8.2s
  neg v2.2s, v8.2s
  neg v3.2s, v8.2s
  neg v4.2s, v8.2s
  neg v5.2s, v8.2s
  neg v6.2s, v8.2s
  neg v7.2s, v8.2s
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)0307191e3f51inst 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)9fa8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420047150000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000105011151180160020035800001002003920039200392003920039
8020420038150000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000117011151180160020035800001002003920039200392003920039
802042008815000272925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
802042003815000029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100087011151180160020035800001002003920039200392003920039
802042003814900029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100084011151180160020035800001002003920039200392003920039
80204200381500002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
802042003815000029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100060011151180160020035800001002003920039200392003920039
80204200381500002925801081008000810080020500640132020019200382003899776998980120200800322008003220038200381180201100991001008000010000011151180160020035800001002003920039200392003920039
802042003815000029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100096011151180160020035800001002003920039200392003920039
802042003815000029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100099011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03070a1e1f3a3f51inst 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)9fa6a8accfd0d2d5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150113302872580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100065024002316022222003580000102003920039200392003920039
800242003815011002452580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100005024002216021222003580000102003920039200392003920039
800242003815011002452580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100205024002316022222003580000102003920039200392003920039
80024200381501100250258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010026905024002216023212003580000102003920039200392003920039
800242003815011002452580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100261445024001916022182003580000102003920039200392003920039
8002420038150110021102580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100005024001816020162003580000102003920039200392003920039
80024200381501100210952580010108007610800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100005024002216023222003580000102003920039200392003920039
8002420038150110021102580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100005024002316018232003580000102003920039200392003920039
8002420038150111502452580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100005024001816022182003580000102003920039200392003920039
800242003815011002452580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100065024001716022182003580000102003920039200392003920039