Apple M1 Microarchitecture Research by Dougall Johnson

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

CMGE (register, 2D)

Test 1: uops

Code:

  cmge v0.2d, v0.2d, v1.2d
  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)0308091e3f4e51inst 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
10042037160006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037160006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037160006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150006116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150006116872510001000100026468002018203720371572318951000100020002037203721100110000073116111787100020382038203820382038
10042037150006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150006116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmge v0.2d, v0.2d, v1.2d
  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)03070a1e3f4e51inst 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
102042003715011068319687251010010010000100100005002847680120018200372003718429718740101002001000820020016200372003711102011009910010010000100001117171161119806100001002003820038200382003820038
102042003715011061196872510100100100001001000050028476801200182003720037184297187401010020010008200200162003720037111020110099100100100001003090007102162219791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318763101002001000020020000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038
102042003715000012619687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100030007102162219791100001002003820038200382003820038
102042003715000069519687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038
102042003715000018919687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038
102042003715000012419687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100311110007102162219791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680120018200372003718422818745101002001000020020000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038
10204200371500006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038
102042003715000012419687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007102162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03181e3f4e51inst 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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150001241968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003714900125519687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100430640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100353640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500025819687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100476640216221978510000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
1002420037150001871968725100101210000141015250284896302001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmge v0.2d, v1.2d, v0.2d
  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)031e3a3f4e51inst 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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150008219687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371500112619687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007100161119791100001002003820038200382003820038
10204200371500037919687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371500097196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000020037101161119791100001002003820038200382003820038
10204200371500019119687251010010010000100100005002847680200182003720037184227187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371500012419687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
1020420037150006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
10204200371500012619687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
1020420037149008419687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000007101161119791100001002003820038200382003820038
102042003715000611968725101001001000010010000500284768020018200372008518422318745101002001000020020000200372003711102011009910010010000100000530127101161119791100001002003820038200382003820038

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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150028419687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150010319687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100306402162219785010000102003820038200382003820038
1002420037149061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001024306402162219785010000102003820038200382003820038
10024200371500105319687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
100242003715006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001034606402162219785010000102003820038200382003820038
1002420037150031919687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038
1002420037150012819687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmge v0.2d, v8.2d, v9.2d
  cmge v1.2d, v8.2d, v9.2d
  cmge v2.2d, v8.2d, v9.2d
  cmge v3.2d, v8.2d, v9.2d
  cmge v4.2d, v8.2d, v9.2d
  cmge v5.2d, v8.2d, v9.2d
  cmge v6.2d, v8.2d, v9.2d
  cmge v7.2d, v8.2d, v9.2d
  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)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)9fa8cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915008225801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000511021611200350800001002003920039200392003920039
802042003815006125801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000511011611200350800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000511011611200350800001002003920039200392003920039
802042003815506125801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000511011611200350800001002003920039200392003920039
802042003815007025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000511011611200350800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000511011611200358800001002003920039200392003920039
802042003815008225801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000511011611200350800001002003920039200392003920039
802042003814904025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000511011611200350800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000511011611200350800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010000511011611200350800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090b18191e1f3a3f51inst 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)5f60696d6edispatch 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)9fa0a1a6a8acc2branch mispredict (cb)cficache miss (d3)d5d6d9dbddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150000000003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010000000050203716004320035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010000000050200416004420035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010000000050200416004320035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010000000050200416004420035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010000000050200416004320035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010000000050200416003420035080000102003920039200392008920039
80024200381500000033003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010000000050201416004320035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000112001920038200389996310018800102080000201600002003820038118002110910108000010000000050200416003420035080000102003920039200392003920039
80024200381500000000082625800101080000108000050640000012001920038200389996310018800102080000201600002003820038118002110910108000010000000050200416004320035080000102003920039200392003920039
8002420038150000000003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010000000050200216004320035080000102003920039200392003920039