Apple M1 Microarchitecture Research by Dougall Johnson

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

CMLE (zero, 4S)

Test 1: uops

Code:

  cmle v0.4s, v0.4s, #0
  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)031e1f3f4e51inst 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
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037151206116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmle v0.4s, v0.4s, #0
  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)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)9fa8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150061196862510100100100001001000050028475211200182003720037184210318745101002001000020010000200372003711102011009910010010000100000710116111979100100001002003820038200382003820038
1020420037150061196864510100100100001001000050028475210200182003720037184210318745101002001000020010000200372003711102011009910010010000100000710116111979100100001002003820038200382003820038
1020420037149061196862510100100100001001000050028475210200182003720037184210318745101002001000020010000200372003711102011009910010010000100000710116111979100100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475211200182003720037184210318745101002001000020010000200372003711102011009910010010000100000710116111979100100001002003820038200382003820038
1020420037150661196862510100100100001001000050028475211200182003720037184217318745101002001000020010000200372003711102011009910010010000100000710116111979100100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475211200182003720037184210318745101002001000020010000200372003711102011009910010010000100000710116111979170100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475210200182003720037184210318745101002001000020010000200372003711102011009910010010000100000710116111979100100001002003820038200382003820038
1020420037150961196862510100100100001001000050028475211200182003720037184210318745101002001000020010000200372003711102011009910010010000100000710116111979100100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475211200182003720037184210318745101002001000020010000200372003711102011009910010010000100000710116111979100100001002003820038200382003820038
1020420037150061196862510100100100001001000050028475211200182003720037184210318745101002001000020010000200372003711102011009910010010000100000710116111979100100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)030b1e3f4e51inst 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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000006403163319786010000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001003006403163319786010000102003820038200382003820038
10024200371490061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001003006403163319786010000102003820038200382003820038
10024200371501061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001003006403163319786010000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000006403163319786010000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000006403163319786010000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000006403163319786010000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010172200372003711100211091010100001001006403163319786010000102003820038200382003820038
100242003715000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010046036403163319786010000102003820038200382003820038
1002420037150006119686251001010100001010000502847521120018200372003718443318767100102010000201000020037200371110021109101010000100201146403163319786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmle v0.4s, v8.4s, #0
  cmle v1.4s, v8.4s, #0
  cmle v2.4s, v8.4s, #0
  cmle v3.4s, v8.4s, #0
  cmle v4.4s, v8.4s, #0
  cmle v5.4s, v8.4s, #0
  cmle v6.4s, v8.4s, #0
  cmle v7.4s, v8.4s, #0
  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)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)9fa8acc5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200611500071258010810080008100800205006401321200192003820038997769989801202008003220080032200882003811802011009910010080000100001115118116020035800001002003920039200392003920039
80204200871500052258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
80204200381500050258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
80204200381500029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039
802042003815000416258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100001115118016020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191f3a3f51inst 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)9fa8a9acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150000081258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020216422003580000102003920039200392003920039
8002420038150000081258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020216322003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020216332003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020416442003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020216432003580000102003920039200392003920039
8002420038150000060258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020316332003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020216222003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020316222003580000102003920039200392003920039
80024200381500000703258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020216222003580000102003920039200392003920039
8002420038150000039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010000005020216222003580000102003920039200392003920039