Apple M1 Microarchitecture Research by Dougall Johnson

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

UADDLP (vector, 2S)

Test 1: uops

Code:

  uaddlp v0.2s, v0.4h
  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)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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371600611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371510611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1005203715012611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371500611686251000100010002645212018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  uaddlp v0.2s, v0.4h
  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)030818191e3a3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500002250611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161319791100001002003820038200382003820038
1020420037150000006451968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000000611968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101163119791100001002008520038200382003820038
102042013215111000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037201801110201100991001001000010000007101161119791100001002003820038200382003820038
102042003714900000611968625101001001000010010000500284752112001820037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002018220038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e3a3f4e51inst 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)9facc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500094196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000660216221978610000102003820038200382003820038
100242003715000525196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715039061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001060640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  uaddlp v0.2s, v8.4h
  uaddlp v1.2s, v8.4h
  uaddlp v2.2s, v8.4h
  uaddlp v3.2s, v8.4h
  uaddlp v4.2s, v8.4h
  uaddlp v5.2s, v8.4h
  uaddlp v6.2s, v8.4h
  uaddlp v7.2s, v8.4h
  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)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)9fc5branch mispredict (cb)cdcfd6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420061150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100111511816020035800001002003920039200392003920039
80204200381500599258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100111511816020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100111511816020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100111511816020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100111511816020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100111511816020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100111511816020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100111511816020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100111511816020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100111511816020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0304181e3a3f51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004015000752442580010108000010800005064000002001920044200389996310018800102080000208000020038200381180021109101080000100050241616161920035080000102003920039200392003920039
8002420038150004112442580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050241616161020035080000102003920039200392003920039
80024200381501002442580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050241516141020035080000102003920039200392003920039
80024200381500002442580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050241516131620035080000102003920039200392003920039
800242003815000152614258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005024161691520035080000102003920039200392003920039
80024200381500002442580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050241416141820035080000102003920039200392003920039
800242003815010122442580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050241516141820035080000102003920039200392003920039
8002420038150003244258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005024916141620035080000102003920039200392003920039
80024200381500002602580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050241616161620035080000102003920039200392003920039
80024200381501092442580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050241416161420035080000102003920039200392003920039