Apple M1 Microarchitecture Research by Dougall Johnson

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

CMGT (register, D)

Test 1: uops

Code:

  cmgt d0, d0, d1
  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)03181e3f4e51inst 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)a1cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100420371500611687251000100010002646801201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371500611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371503611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371500611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371603611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371503611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371500611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371603611687251000100010002646800201820372037157231895100010002000203720371110011000073116221787100020382038203820382038
1004203715002631687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038
100420371500611687251000100010002646800201820372037157231895100010002000203720371110011000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmgt d0, d0, d1
  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)0308090b1e3f4e51inst 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)696d6edispatch 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)9fa0a1a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000038531968725101001181000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007103161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100203007101161119791100001002003820038200382003820038
10204200371501100611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
102042003715000007261968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768020018200372003718422318766101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500010611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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
1002420037150000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000010006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196672510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000606402162219785010000102003820038200382003820038
10024200371500000000631196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000010006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000030006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037149000000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000306403322219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmgt d0, d1, d0
  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)696d6edispatch 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
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007102161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720084184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000517101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000637101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038

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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100069640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100066640216221978510000102003820038200382003820038
1002420037150002521968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150002511968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010030640216221981010000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100573640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100066640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmgt d0, d8, d9
  cmgt d1, d8, d9
  cmgt d2, d8, d9
  cmgt d3, d8, d9
  cmgt d4, d8, d9
  cmgt d5, d8, d9
  cmgt d6, d8, d9
  cmgt d7, d8, d9
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 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)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)9fa0a1a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150004025801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100000066511021611200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000012001920038200389973039996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
8020420038150004025801001008000010080000500640000020019200382003899730310048801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
802042003815090402580100100800001008000050064000012007120038200389973039996801002008000020016000020038200892180201100991001008000010004100511011611200350800001002003920039200392003920039
8020420038150120822580100100800001008000050064000002001920038201009973039996801002008000020016000020038200962180201100991001008000010000000511011611200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001920038200389982039996801002008009920016000020038200381180201100991001008000010010000511011611200350800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001920038200389973039996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039
8020420038150004025801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100005403511011611200350800001002003920039200392003920039
8020420038150304025801001008000010080000500640000020019200382008999730399968021520080000200160198200972009121802011009910010080000100003205110116112007821800001002003920039200392003920039
802042003815000402580100100800001008000050064000002001920038200389973039996801002008000020016000020038200381180201100991001008000010000000511011611200350800001002003920039200392003920039

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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500017125800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100005020516552003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100015020416442003580000102003920039200392003920039
80024200381500027025800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100005020216442003580000102003920039200392003920039
8002420038150003925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100005020516552003580000102003920039200392003920039
80024200381500020925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000101905020416442008580000102003920039200392003920039
80024200381500028925800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000101005020416342003580000102003920039200392003920039
80024200381500022625800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100005020416442003580000102003920039200392003920039
80024200381500020525800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100005020316442003580000102003920039200392003920039
8002420038150908325800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100005020416442003580000102003920039200392003920039
80024200381500022825800101080000108000050640000120019200382003899963100188001020800002016000020038200381180021109101080000100005020416342003580000102003920039200392003920039