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, 2D)

Test 1: uops

Code:

  neg v0.2d, v0.2d
  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
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110001073116111786100020382038203820382038
100420371636116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  neg v0.2d, v0.2d
  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)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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500900196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101162119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500124196862510100100100001001000050028475210200182003720037184293187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001251000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500149196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500251196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001002479287101161119791100001002003820038200382003820038
10204200371500235196862510100100100001001000050028475211200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150082196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715005441968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000127101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0309181e1f3f4e51inst 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)9fa8a9cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000061196862510010101000010100005028475212001820037200371844303187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150000061196862510010101000010100005028475212001820037200371844303187671001020100002010000200372003711100211091010100001030640216221978610000102003820038200382003820038
10024200371550000155196862510010101000010100005028475212001820037200371844303187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150000061196862510010101000010100005028475212001820037200371844303187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150000061196862510010101000010100005028475212001820037200371844303187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150000061196862510010101000010100005028475212001820037200371844303187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500000166196862510010101000010100005028475212001820037200371844303187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150000061196862510010101000010100005028475212001820037200371844303187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500000103196862510010101000010100005028475212001820037200371844303187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150000061196862510010101000010100005028475212001820037200371844303187671001020100002010000200372003711100211091010100001020640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

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

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)031e3f51inst 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)9fa8c2c5branch mispredict (cb)cdcfd6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420057151029258010810080008100800205006401321200192003820038997706998980120200800322008003220038200381180201100991001008000010000111511816020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997706998980120200800322008003220038200381180201100991001008000010000111511816020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997706998980120200800322008003220038200381180201100991001008000010000111511816020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997706998980120200800322008003220038200381180201100991001008000010000111511816020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997706998980120200800322008003220038200381180201100991001008000010000111511816020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997706998980120200800322008003220038200381180201100991001008000010000111511816020035800001002003920039200392003920039
802042003815015149258010810080008100800205006401321200192003820038997706998980120200800322008003220038200381180201100991001008000010000111511816020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997706998980120200800322008003220038200381180201100991001008000010000111511816020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997706998980120200800322008003220038200381180201100991001008000010000111511816020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997706998980120200800322008003220038200381180201100991001008000010000111511816020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03191e3f51inst 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
80024200501500039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020416422003580000102003920039200392003920039
80024200381500039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020416342003580000102003920039200392003920039
80024200381500039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020416442003580000102003920039200392003920039
80024200381500039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020416422003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020416422003580000102003920039200392003920039
8002420038150102532580104108000010800005064000002001920038200381000531001880010208000020800962003820038118002110910108000010017405020416422003580000102003920039200392003920039
8002420038150014439258001010800001080000506400000200602003820295999471001680208208000020800972003820096118002110910108000010005020216342003580000102003920039200392003920039
80024200381500039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020416242003580000102003920088200392003920039
800242003815005439258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020416432003580000102003920039200392003920039
800242003815000146258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020416242003580000102003920039200392003920039