Apple M1 Microarchitecture Research by Dougall Johnson

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

CMGT (zero, 16B)

Test 1: uops

Code:

  cmgt v0.16b, v0.16b, #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)03191e3a3f4e51inst 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)a0a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004203715000611686251000100010002645211201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203715000821686251000100010002645211201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203716000611686251000100010002645211201820372037157131895100010001000203720371110011000000073116211786100020382038203820382038
1004203715090611686251000100010002645210201820372037157131895100010001000203720371110011000000073116211786100020382038203820382038
1004203715000611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203715000821686251000100010002645211201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203715000611686251000100010002645210201820852037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203715000611686251000100010002645210201820372037157131895100010001000203720371110011000000073116111786100020382038203820382038
1004203715000611686251000100010002645210201820372037157131895100010001000203720371110011000000373116111786100020382074203820382038
1004203715100611686251000100010002645210201820372037157131895100010001000203720371110011000000073116211786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmgt v0.16b, v0.16b, #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)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)9fa0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000710116111979100100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000030710116111979100100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100023400710125211979120100001002008520038200382008620038
1020420037150306119675251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000710116111979100100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000030710116111979100100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000710116111979100100001002003820038200382003820038
1020420037150156119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000710116111979100100001002003820038200382003820038
1020420037150246119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000710116111979100100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000000710116111979100100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521020018200372003718421318745101002001000020010000200372003711102011009910010010000100000000710116111979100100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e1f3f4e51inst 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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371509061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001010640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001009640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671016320100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
100242003715042061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
1002420037150357061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038
10024200371500061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221984810000102003820038200382003820038
100242003715012061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000640216221978610000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmgt v0.16b, v8.16b, #0
  cmgt v1.16b, v8.16b, #0
  cmgt v2.16b, v8.16b, #0
  cmgt v3.16b, v8.16b, #0
  cmgt v4.16b, v8.16b, #0
  cmgt v5.16b, v8.16b, #0
  cmgt v6.16b, v8.16b, #0
  cmgt v7.16b, v8.16b, #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)03070a1e1f3f51inst 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)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915011120292580108100800081008002050064075612001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
80204200381501100292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
802042003815011005042580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161220035800001002003920039200392003920039
8020420038150110045032580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
802042003815011002002580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181162120035800001002003920039200392003920039
80204200381501100292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
80204200381501100292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
80204200381501100292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
80204200381501100292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161220035800001002003920039200392003920039
80204200381501100292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039

1000 unrolls and 10 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)6061696d6edispatch 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)9fa8acbranch mispredict (cb)cfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115000392580010108000010800005064000010200192003820038999631001880010208000020800002003820038118002110910108000010000502000161612122003580000102003920039200392003920039
800242003815000392580010108000010800005064000010200192003820038999631001880010208000020800002003820038118002110910108000010000502000121610122003580000102003920039200392003920039
800242003815000392580010108000010800005064000010200192003820038999631001880010208000020800002003820038118002110910108000010000502000111611122003580000102003920039200392003920039
800242003815000392580010108000010800005064000010200192003820038999631001880010208000020800002003820038118002110910108000010000502000141613122003580000102003920039200392003920039
80024200381500039258001010800761080000506400001020019200382003899963100188001020800002080000200382003811800211091010800001000050200091612142003580000102003920039200392003920039
80024200381500039258001010800001080000506400001020019200382003899963100188001020800002080000200382003811800211091010800001000050200012161392003580000102003920039200392003920039
80024200381500039258001010800001080000506400001020019200382003899963100188001020800002080000200382003811800211091010800001000050200012169142003580000102003920039200392003920039
80024200381500339258001010800001080000506400001020019200382003899963100188001020800002080000200382003811800211091010800001000050200012161482003580000102003920039200392003920039
800242003815000392580010108000010800005064000010200192003820038999631001880010208000020800002003820038118002110910108000010000502000141613122003580000102003920039200392003920039
80024200381500039258001010800001080000506400001020019200382003899963100188001020800002080000200382003811800211091010800001000050200081612102003580000102003920039200392003920039