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, 8H)

Test 1: uops

Code:

  cmge v0.8h, v0.8h, v1.8h
  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)033f4e51inst 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
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037166116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037156116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmge v0.8h, v0.8h, v1.8h
  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)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)9fcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
10204200371500061196874310100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038
10204200371500061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b1e1f3f4e51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221982410000102003820038200382003820038
100242003715000001031968725100101010000121015250284768002001820037200371844431876710010201000020200002003720037111002110910101000010019980640216221978510000102003820038200382003820038
10024200371500024001031968725100101010000101000050284768012001820084200371844471878610010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010030640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640316221978510000102003820038200382003820038
1002420037150001201031968725100101010000101000050284768002001820085200371844431876710010201000020203382008420037111002110910101000010059682640216221978510000102003820038200382003820038
10024200371500100611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
10024200371500000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000640216221978510000102003820038200382003820038
100242003715000120611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010030640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmge v0.8h, v1.8h, v0.8h
  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
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422718745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715096119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680120065200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100007102162219791100001002003820038200382003820038

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)60696b6d6edispatch 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000000006119687251001010100001010000502847680120018020037200371844403187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680020018020037200371844403187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680120018020037200371844403187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680020018020037200371844473187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680120018020037200371844403187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680020018020037200371844403187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680020018020037200371844403187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000906119687251001010100001010000502847680020018020037200371844403187671001020100002020000200372003711100211091010100001000000007042162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680120018020037200371844403187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680020018020037200371844403187671001020100002020000200372003711100211091010100001000000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmge v0.8h, v8.8h, v9.8h
  cmge v1.8h, v8.8h, v9.8h
  cmge v2.8h, v8.8h, v9.8h
  cmge v3.8h, v8.8h, v9.8h
  cmge v4.8h, v8.8h, v9.8h
  cmge v5.8h, v8.8h, v9.8h
  cmge v6.8h, v8.8h, v9.8h
  cmge v7.8h, v8.8h, v9.8h
  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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015002925801081008000810080020500640132020019200382003899776998980120200800322001600642003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815002925801081008000810080020500640132020019200382003899776998980120200800322001600642003820038118020110099100100800001000011151180160020035800001002003920039200392003920039
802042003815006825801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000051101161120035800001002003920039200392003920039
8020420038150070525801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000051101161120035800001002003920039200392003920039
802042003815004025801001068000010080000500640000120019200382003899813999680314200800002001600002003820096218020110099100100800001000000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000020019200382003899733999680100200800002001600002003820038118020110099100100800001000000051101161120035800001002003920039200392003920039
802042003814904025801001008000010080000500640000120019200382003899733999680100200800002001600002003820038118020110099100100800001000000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030818191e3f51inst 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)9fa8accfd0d2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004015000006092580010108000010800005064000015200192003820038999631001880010208000020160000200382003811800211091010800001000502004216112003580000102003920039200392003920039
80024200381500009392580010108000010800005064000010200192003820038999631001880010208000020160000200382003811800211091010800001000502000116112003580000102003920039200392003920039
8002420038150000605142580010108000010800005064000010200192003820038999631001880010208000020160000200382003811800211091010800001000502000116112003580000102003920039200392003920039
800242003815000084392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001013502000116112003580000102003920039200392003920039
80024200381500010392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000502000116112003580000102003920039200392003920039
8002420038150001159392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000502053116112003580000102003920039200392003920039
80024200381500009392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000502000116112003580000102003920039200392003920039
800242003815000005142580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000502000116112003580000102003920039200392003920039
80024200381500009392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000502053116112003580000102003920039200392003920039
800242003815000069392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000502053116112003580000102003920039200392003920039