Apple M1 Microarchitecture Research by Dougall Johnson

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

CMGE (zero, 2S)

Test 1: uops

Code:

  cmge v0.2s, v0.2s, #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
1004203715015116862510001000100026452112018203720371571318951000100010002037203711100110001073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000079116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371506116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038
100420371606116862510001000100026452112018203720371571318951000100010002037203711100110000073116111786100020382038203820382038

Test 2: Latency 1->2

Code:

  cmge v0.2s, v0.2s, #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)9fa8acc2c5cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150053619686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371501956119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150010319686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150093519686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715006119686251010010010000100100005002847521120018200372003718421318745101002001000020010000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000090866196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001032000026404163319786010000102003820038200382003820038
1002420037150000012061196862510010101000010100005028475211200182003720037184437187671001020100002010000200372003711100211091010100001000002006403163319786010000102003820038200382003820038
100242003715000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006403163319786010000102003820038200382003820038
100242003715000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006403163319786010000102003820038200382003820038
100242003715000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000306403163319786010000102003820038200382003820038
100242003715000000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000197306403163419786010000102003820038200382003820038
100242003715000012790605196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006403163319786010000102003820038200382003820038
100242003715000000061196862510010101000010100005028475210200182003720037184433187671001020100002010000200372003711100211091010100001000000006403163319786010000102003820038200382003820038
1002420037150000000103196862510010101000010100005028475211200182003720037184433187671001020100002210000200372003711100211091010100001000000006403173319786010000102003820038200382003820038
100242003715000000061196862510010101000010100005028475211200182003720037184433187671001020100002010000200372003711100211091010100001000000006403163319786010000102003820038200382003820038

Test 3: throughput

Count: 8

Code:

  cmge v0.2s, v8.2s, #0
  cmge v1.2s, v8.2s, #0
  cmge v2.2s, v8.2s, #0
  cmge v3.2s, v8.2s, #0
  cmge v4.2s, v8.2s, #0
  cmge v5.2s, v8.2s, #0
  cmge v6.2s, v8.2s, #0
  cmge v7.2s, v8.2s, #0
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)0307080a0b1e1f3f51inst 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
8020420057150000000292580108100800081008002050064013212001920038200389977699898012020080032200800322003820038118020110099100100800001000011151181161120035800001002003920039200392003920039
802042003815010101207125801081008000810080020500640132120028200492004899761099868012820080038200800382004820049118020110099100100800001000022251282232220046800001002005020050200502005020050
8020420049150000060642780116100800161008002850064019612002820049200489976999868012820080038200800382004820049118020110099100100800001000022251292232220045800001002004920049200502004920049
80204200481500000306427801161008001610080028500640196120028200482004999761099868012820080038200800382004820048118020110099100100800001000022251282232220045800001002005020050200492004920049
8020420049150000000642680116100800161008002850064019612002820048200499976999868012820080038200800382004820049118020110099100100800001000022251282232220046800001002004920049200492004920050
802042004915000001506426801161008001610080028500640196120028200482004899761099868012820080038200800382004920048118020110099100100800001000022251282232220045800001002004920049200502004920049
8020420048150000000642680116100800161008002850064019612002820048200499976999868012820080038200800382004820048118020110099100100800001000022251282232220045800001002004920049200492004920050
80204200481500000210064278011610080016100800285006401961200282004820048100091099868012820080038200800382004920048118020110099100100800001005622251282232220045800001002004920050200502004920050
80204200481500000120752780100100800001008000050064000012002820047200479971699938010020080000200800002004720047118020110099100100800001000011151203243320044800001002004820048200482004820048
80204200471500000300074027801001008000010080000500640000120028200472004799711599938010020080000200800002004720047118020110099100100800001000011151203243320044800001002004820048200482004820048

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308191e3f51inst 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)9fa0a1a8cfd5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150004839258001010800001080000506400000200192003820038100313100188001020800002080000200382003811800211091010800001000050201160112003580000102003920039200392003920039
800242003815000022925800101080000108000050640000020023200382003899963100188001020800002080000200382003811800211091010800001000050201160112003580000102003920039200392003920039
80024200381500003925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000050201160112003580000102003920039200392003920039
800242003815000213925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000050201160112003580000102003920039200392003920039
800242003815000123925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000050201160112003580000102003920039200392003920039
8002420038150001570425800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000050201160112003580000102003920039200392003920039
800242003815000273925800101080000108000050640000020019200382003899963100188020520800002080000200382003811800211091010800001000050201160112003580000102003920039200392003920039
80024200381500063925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000050201160112003580000102003920039200392003920039
800242003815000183925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000050201160112003580000102003920039200392003920039
800242003815000213925800101080000108000050640000020019200382003899963100188001020800002080000200382003811800211091010800001000050201160112003580000102003920039200392003920039