Apple M1 Microarchitecture Research by Dougall Johnson

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

CMLT (zero, 8H)

Test 1: uops

Code:

  cmlt v0.8h, v0.8h, #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)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
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
10042037151626116862510001000100026452102018203720371571318951000100010002037203711100110003073116111786100020382038203820382038
100420371506116862510001000100026452102018203720371571318951000100010002037203711100110002073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmlt v0.8h, v0.8h, #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)0318191e1f3f4e51inst 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
10204200371500015610461196862510100100100121261000059428487850200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500000170196862510100100100001001000050028475210200182003720037184218187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
1020420037150000061196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715000001871968625101001001000010010000500284752102001820037200371842131874510100200100002001000020037200371110201100991001001000010057371011611197910100001002003820038200382003820038
10204200371500000465196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500030092196862510100100100001001000050028475210200182003720037184213187451010020010000200100002003720037111020110099100100100001000071011611197910100001002003820038200382003820038

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)9fa8cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500191196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001006402162219786010000102003820038200382003820038
10024200371500187196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001006402162219786010000102003820038200382003820038
10024200371500124196862510010101000010100005028475210200182003720037184433187861001020100002010000200372003711100211091010100001006402162219786010000102003820038200382003820038
10024200371500166196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001006402162219786010000102003820038200382003820038
1002420037150061196864510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001006402162219786010000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001016402162219786010000102003820038200382003820038
1002420037150061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001006402162219786210000102003820038200382003820038
10024200371500386196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001006402162219786010000102003820038200382003820038
1002420037150061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001006402162219786010000102003820038200382003820038
10024200371500145196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001006402162219786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmlt v0.8h, v8.8h, #0
  cmlt v1.8h, v8.8h, #0
  cmlt v2.8h, v8.8h, #0
  cmlt v3.8h, v8.8h, #0
  cmlt v4.8h, v8.8h, #0
  cmlt v5.8h, v8.8h, #0
  cmlt v6.8h, v8.8h, #0
  cmlt v7.8h, v8.8h, #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)9fa8acc2c5branch mispredict (cb)cdcfd5d6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200571500292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118116020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001006001115118016020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132120019200382003899776100248012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
802042003815001592580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039
80204200381500292580108100800081008002050064013202001920038200389977699898012020080032200800322003820038118020110099100100800001000001115118016020035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03041e3f51inst 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)9fa8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115010392580091108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100050260416552003580000102003920039200392003920039
800242003815000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100050200616762003580000102003920039200392003920039
8002420038150015392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100050200616662003580000102003920039200392003920039
800242003815000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100050200427762003580000102003920039200392003920039
8002420038150002432580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100050200516552003580000102003920039200392003920039
800242003815000392580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100050200616752003580000102003920039200392003920039
8002420038150001252580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100050200516552003580000102003920039200392003920039
800242003815000622580010108000010800005064000012001920038200389996310018800102080000208000020038200381180021109101080000100050200516662003580000102003920039200392003920039
800242003815000622580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050200516552003580000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996310018800102080000208000020038200381180021109101080000100050200616652003580000102003920039200392003920039