Apple M1 Microarchitecture Research by Dougall Johnson

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

FABS (scalar, S)

Test 1: uops

Code:

  fabs s0, s0
  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
100420371606116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112054203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110002373116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018208520841574318951000100010002037203711100110001073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  fabs s0, s0
  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)030b191e1f3f4e51inst 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)60696b6d6edispatch 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)9fa1a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000006119686251010010010000100100005002847521120018020037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521120018020037200371842131874510100200100002001000020037200371110201100991001001000010000307101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018020037200371842131874510100200100002001000020037200371110201100991001001000010001007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521020018020037200371842131874510100200100002001000020037200371110201100991001001000010001007331161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521120018020037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521120018320037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521120018020037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000006119686451010010010000100100005002847521120018020037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038
102042003715000006119686251010010010000100100005002847521120018020037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820085
102042003715000006119686251010010010000100100005002847521020018020037200371842131874510100200100002001000020037200371110201100991001001000010000007101161119791100001002003820038200382003820038

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)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)9faccdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372008411100211091010100001000640216221978610000102003820038200382003820038
10024200371502461196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037149061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  fabs s0, s8
  fabs s1, s8
  fabs s2, s8
  fabs s3, s8
  fabs s4, s8
  fabs s5, s8
  fabs s6, s8
  fabs s7, s8
  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)030b1e3f51inst 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)cdcfd6inst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420059150002925801081008000810080020500642452200192003820038997769989801202008003220080032200382003811802011009910010080000100131115118160200350800001002003920039201172003920039
80204200381500021925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100601115118160200350800001002003920039200392003920039
80204200381500122925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118160200350800001002003920039200392003920039
80204200381500029258010810080008100800205006401322001920038200389988699898012020080032200800322003820038118020110099100100800001000691115118160200350800001002003920039200392003920039
8020420038150002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100701115118160200350800001002003920039200392003920039
8020420038150002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100101115118160200350800001002003920039200392003920039
8020420038150002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118160200350800001002003920039200392003920039
8020420038150002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100341441115118160200350800001002003920039200392003920039
802042003815000136258010810080008100800205006401322001920038200389977699898012020080032200800322003820038118020110099100100800001003631115118160200350800001002003920039200392003920039
8020420038150002925801081008000810080020500640132200192003820038997769989801202008003220080032200382003811802011009910010080000100231115118160200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030708090a18191e1f3a3f51inst 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)9fa0a1a6a8a9acc2cfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200401500000000003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010000400050201160112003580000102003920039200392003920039
80024200381500000000008845801051080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010000200250201160112003580000102003920039200392003920039
80024200381500000000003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010000000050201160112003580000102003920039200392003920039
800242003815000000000039258001010800001080000506400002001920038200389996310018800102080289208000020038200381180021109101080000100002900050201160112012480000102003920039200912003920039
800242003815000100000081258001010800001080000506400002001920038200909996310018800102080197208000020038200381180021109101080000100003606050201160112003580000102003920039200392003920039
800242003815000000000010225800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010000000050201160112003580000102003920039200392003920039
80024200381500000000003925800101080000108000050640000200192003820038999631001880010208000020800002003820038118002110910108000010000003050201160112003580000102003920039200392003920039
800242003815001000100039258001010800001080000506400002001920038200389996310018801072080000208000020038200383180021109101080000100003203050201160112003580000102003920039200392003920039
800242003815000000000039258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100003503050201160112003580000102003920039200392003920039
800242003815000000000039258001010800001080000506400002001920038200389996310018800102080000208000020038200381180021109101080000100003203050201160112003580000102003920039200392003920039