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, D)

Test 1: uops

Code:

  cmle d0, d0, #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)03091e3f4e51inst 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
1004203715008116862510001000100026452102018203720371571318951000100010002037203711100110000073116111810100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715096116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110006073116111786100020382038203820382038
10042037161061168625100010001000264521120182037203715713189510001000100020372037111001100002473116111786100020382038203820382038
1004203715006116862510001000100026452112018203720371571318951000100010002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmle d0, d0, #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)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)6061696d6edispatch 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)9faccfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000611968625101001001000010010000500284752100200182003720037184210318745101002001000020010000200372003711102011009910010010000100071001161119791100001002003820038200382003820038
102042003715010611968625101001001000010010000500284752100200182003720037184210318745101002001000020010000200372003711102011009910010010000100071001161119791100001002003820038200382003820038
1020420037150007261968625101001001000010010000500284752100200182003720037184210318745101002001000020010000200372003711102011009910010010000100071001161119791100001002003820038200382003820038
1020420037150001031968625101001001000010010000500284752100200182003720037184210318745101002001000020010000200372003711102011009910010010000100071001161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752100200182003720037184210318745101002001000020010000200372003711102011009910010010000100071001161119791100001002003820038200382003820038
1020420037150007141968625101001001000010010000500284752100200182003720037184210318745101002001000020010000200372003711102011009910010010000100071001161119791100001002003820038200382003820038
1020420037150007261968625101001001000010010000500284752100200182003720037184210318745101002001000020010000200372003711102011009910010010000100071001161119791100001002003820038200382003820038
1020420037150006471968625101001001000010010000500284752100200182003720037184210318745101002001000020010000200372003711102011009910010010000100071001161119791100001002003820038200382003820038
10204200371500010401968625101001001000010010000500284752100200182003720037184210318745101002001000020010000200372003711102011009910010010000100071001161119791100001002003820038200382003820038
102042003715000611968625101001001000010010000500284752100200182003720037184210318745101002001000020010000200372003711102011009910010010000100071001161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03081e1f3f4e51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150000821968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010003640216221978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
100242003715000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000270640216221978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
10024200371500007261968625100101010000101000050284752112001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038
1002420037150000611968625100101010000101000050284752102001820037200371844331876710010201000020100002003720037111002110910101000010000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmle d0, d8, #0
  cmle d1, d8, #0
  cmle d2, d8, #0
  cmle d3, d8, #0
  cmle d4, d8, #0
  cmle d5, d8, #0
  cmle d6, d8, #0
  cmle d7, d8, #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)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)cdcfd6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420049150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100111511816020035800001002003920039200392003920039
80204200381500522580108100800081008002050064013202001920038200389977269989801202008003220080032200382003811802011009910010080000100111511816020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100111511816020035800001002003920039200392003920039
8020420038149029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100111511816020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100111511816020035800001002003920039200392003920039
8020420038150052258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100111511816020035800001002003920039200392003920039
8020420038151029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100111511816020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100111511816020035800001002003920039200392003920039
8020420038150029258010810080008100800205006401320200192003820038997769989801202008003220080032200382003811802011009910010080000100111511816120035800001002003920039200392003920039
8020420038150029258010810080008100800205006401321200192003820038997769989801202008003220080032200382003811802011009910010080000100111511816020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e1f3f51inst 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)9fa8c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200501500039258001010800001080000506400000200192003820038999631001880010208000020800002003820038118002110910108000010005020716772003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010015020816552003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020616752003580000102003920039200392003920039
800242003815000392580010108000010800005064000012001920038200381000931001880010208000020800002003820038118002110910108000010005020516552003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020516772003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020716882003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020616552003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020716552003580000102003920039200392003920039
80024200381490039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020616652003580000102003920039200392003920039
80024200381500039258001010800001080000506400001200192003820038999631001880010208000020800002003820038118002110910108000010005020716762008480000102003920039200392003920039