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, 4S)

Test 1: uops

Code:

  neg v0.4s, v0.4s
  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)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
100420371606116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371566116862510001000100026452102018203720371571318951000100010002037203711100110000973116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100001273116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000373116111786100020382038203820382038
100420371606116862510001000100026452102018203720371571318951000100010002037203711100110000073117111786100020382038203820382038
10042037151261168625100010001000264521020182037203715713189510001000100020372037111001100003673116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100001273116111786100020382038203820382038
1004203715061168625100010001000264521020182037203715713189510001000100020372037111001100002173116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  neg v0.4s, 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)031e1f3a3f4e51inst 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)9fa0a1a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000056719686251010010010000100100005002847521200182003720037184210318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521200182003720037184210318745101002001000020010000200372003711102011009910010010000100001307101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521200182003720037184210318745101002001000020010000200372003711102011009910010010000100000307101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521200182003720037184210318745101002001000020010000200372003711102011009910010010000100001007101161119791100001002003820038200382003820038
102042003715000012419686251010010010000100100005002847521200182003720037184210318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715000014719686251010010010000100100005002847521200182003720037184210318745101002001000020010000200372003711102011009910010010000100003214407101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521200182003720037184210318745101002001000020010000200372003711102011009910010010000100003917707101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521200182003720037184210318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521200182003720037184210318745101002001000020010000200372003711102011009910010010000100000307101161119791100001002003820038200382003820038
10204200371500006119686251010010010000100100005002847521200182003720037184210318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0318191e3f4e51inst 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)9fa1a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500002351968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100100640216221978610000102003820038200382003820038
1002420037155000109719686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001002030640216221978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
10024200371500006119686251001010100001010000502847521200182003720037184433187671001020100002010000200372003711100211091010100001003400640216221978610000102003820038200382003820038
1002420037150110611968625100101010000101000050284752120018200832008318447318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752120018200372003718443318767100102010000201000020037200371110021109101010000100000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  neg v0.4s, v8.4s
  neg v1.4s, v8.4s
  neg v2.4s, v8.4s
  neg v3.4s, v8.4s
  neg v4.4s, v8.4s
  neg v5.4s, v8.4s
  neg v6.4s, v8.4s
  neg v7.4s, v8.4s
  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)030b18191e3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200571500000292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000011151182160020035800001002003920039200392003920039
80204200381500120292580108100800081008002050064013212001920038200389977699898012020080032202800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815500007352580108100800081008002050064013212001920038200389977699898020820080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500000762580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038149000010962580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
80204200381500000712580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
8020420038150000198732580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815000002925801081008000810080020500640132120019200382003899776998980120200800322008003220038200381180201100991001008000010060311151180160020035800001002003920039200392003920039
802042003815000024292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151180160020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e1f3a3f51inst 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
8002420040150000632258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020116112003580000102003920039200392003920039
800242003815000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020116112003580000102003920039200392003920039
8002420038150000609258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020116112003580000102009720039200392003920039
8002420038150000515258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020116112003580000102003920039200392003920039
800242003815000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020116112003580000102003920039200392003920039
800242003815000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020116112003580000102003920039200392003920039
80024200381500014162580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100125020116112003580000102003920039200392003920039
800242003815000039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020116112003580000102003920039200392003920039
800242003815000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010305020116112003580000102003920039200392003920039
8002420038150000812580010108000010800005064000012001920038200389996221001880010208000020800002003820038118002110910108000010005020116112003580000102003920039200392003920039