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, 4H)

Test 1: uops

Code:

  cmgt v0.4h, v0.4h, v1.4h
  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
100420371606116872510001000100026468002018203720371571318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000075216111787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100015073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715061168725100010001000264680020182037203715723189510001000200020372037111001100012073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmgt v0.4h, v0.4h, v1.4h
  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)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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
10204200371500000536196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010046307101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010052307101161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
102042003715000006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000007101161119791100001002003820038200382003820038
1020420037150000061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010023007101161119791100001002003820038200382003820038
10204200371500000611968725101001001000010010000500284768020018200372003718422318745101002001000020020000200372003711102011009910010010000100011407101161119791100001002003820038200382003820038

1000 unrolls and 10 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)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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150048611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640416431978510000102003820038200382003820038
1002420037150092511968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640316431978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640316341978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640416441978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640416441978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640416441978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216441978510000102003820038200382003820038
1002420037150005641968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640416341978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012006520037200371844431876710010201000020200002003720037111002110910101000010000640316341978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640416321978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmgt v0.4h, v1.4h, v0.4h
  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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010012115100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715096119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007101161119791100001002003820038200382003820038

1000 unrolls and 10 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)9fa1a6a8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000606402162219785010000102003820038200382003820038
1002420037150000072619687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100001206402162219785010000102003820038200382003820038
10024200371500000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010001006402162219785010000102003820038200382003820038
10024200371500000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
10024200371500000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219851010000102003820038200382003820038
10024200371500000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
100242003715000005361968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000006402162219785010000102003820038200382003820038
100242003715000002161968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010201006402162219785010000102003820038200382003820038
10024200371500000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010400306402162219824010000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010031006402162219785110000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmgt v0.4h, v8.4h, v9.4h
  cmgt v1.4h, v8.4h, v9.4h
  cmgt v2.4h, v8.4h, v9.4h
  cmgt v3.4h, v8.4h, v9.4h
  cmgt v4.4h, v8.4h, v9.4h
  cmgt v5.4h, v8.4h, v9.4h
  cmgt v6.4h, v8.4h, v9.4h
  cmgt v7.4h, v8.4h, v9.4h
  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)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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420038150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051103161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010013051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010030051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000108051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010010051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039

1000 unrolls and 10 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)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)9fa8accfd5d6daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100050206160652003580000102003920039200392003920039
80024200381500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100050205160642003580000102003920039200392003920039
80024200381500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100050207160552003580000102003920039200392003920039
80024200381500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100050205160442003580000102003920039200392003920039
80024200381500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100950205160562003580000102003920039200392003920039
800242003815006092580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100050205160662003580000102003920039200392003920039
800242003815093950800101080000108000050640000200192003820038999631001880010208000020160000200382003811800211091010800001006650205160562003580000102003920039200392003920039
80024200381500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100050204160572003580000102003920039200392003920039
80024200871500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000100050206160552003580000102003920039200392003920039
80024200381500392580010108000010800005064000020019200382003899963100188001020800002016000020038200381180021109101080000101050204160452003580000102003920100200392003920039