Apple M1 Microarchitecture Research by Dougall Johnson

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

CMHI (register, 16B)

Test 1: uops

Code:

  cmhi v0.16b, v0.16b, v1.16b
  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)60696b6d6edispatch 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
1004203716061168725100010001000264680020180203720371572318951000100020002037203711100110000073216111787100020382038203820382038
1004203715061168725100010001000264680020180203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715061168725100010001000264680020180203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715061168725100010001000264680020180203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715061168725100010001000264680020180203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715061168725100010001000264680020180203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037150156168725100010001000264680020180203720371572318951000100020002037203711100110000073116111787100020382038203820382038
10042037151261168725100010001000264680020180203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715061168725100010001000264680020183203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715061168725100010001000264680020180203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmhi v0.16b, v0.16b, v1.16b
  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)9fa1a8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371501561196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071005162219791100001002003820038200382003820038
10204200371509536196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071002162219791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071002162219791100001002003820038200382003820038
10204200371502161196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071002162219791100001002003820038200382003820038
10204200371502761196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071002162219791100001002003820038200382003820038
102042003715014761196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071002162219791100001002003820038200382003820038
10204200371500251196872510100100100001001000050028476802001820037200371842231880110100200100002002000020037200371110201100991001001000010000071002162219791100001002003820038200382008520038
102042003715021961196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071002162219791100001002003820038200382003820038
10204200371504561196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071002162219791100001002003820038200382003820038
1020420037150061196872510100100100001001000050028476802001820037200371842231874510100200100002002000020037200371110201100991001001000010000071002162219791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000420061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000240061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000251196872510010101000010100005028476802009020037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102008620038200382008520038
1002420037150000000061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820179
10024200371500000000103196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219895010000102003820038200382003820038
1002420037150000090061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000150061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000030006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101002410100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000330061196872510010101000010100005028476802001820037200371844431876710010201000020200002003720037111002110910101000010090000006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmhi v0.16b, v1.16b, v0.16b
  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)03181e1f3a3f4e51inst 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)9fa0a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150078006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150060072619687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150033006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500537006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150018006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150021006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150021006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150024006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
10204200371500273006119687251010010010000100100005002847680120018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038
1020420037150024006119687251010010010000100100005002847680020018200372003718422318745101002001000020020000200372003711102011009910010010000100000007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03181e1f3f4e51inst 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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
10024200371490006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
10024200371502006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
100242003715001506119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
10024200371500006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038
10024200371500306119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100640216221978510000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmhi v0.16b, v8.16b, v9.16b
  cmhi v1.16b, v8.16b, v9.16b
  cmhi v2.16b, v8.16b, v9.16b
  cmhi v3.16b, v8.16b, v9.16b
  cmhi v4.16b, v8.16b, v9.16b
  cmhi v5.16b, v8.16b, v9.16b
  cmhi v6.16b, v8.16b, v9.16b
  cmhi v7.16b, v8.16b, v9.16b
  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)9fcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200591501564025801001008000010080000500640000200192003820038997339996801002008000020216019220038200381180201100991001008000010051102161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010051101161120035800001002003920039200392003920039
8020420038150244025801001008000010080000500640000200192003820038997339996801002008000020016000020038200381180201100991001008000010051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030708090a18191e1f3a3f51inst 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)9fa0a1a6a8a9acc2cfd0d2icache miss (d3)d5d6d9dadbddinst fetch restart (de)e0? int output thing (e9)eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200481500000009003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010000100050200001816000652003500080000102003920039200392003920039
80024200381500000202100392580010118009312800965064000000200192003820097999631001880010208000020160000200382003811800211091010800001000020305056000123500010102008300080000102003920039200392003920039
8002420038150000000000392580010108000010800005064000001200192003820038999631001880010208000020160000200382003811800211091010800001000000005020000616000752003500080000102003920039200392003920039
8002420038150000000000392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000010305020000616000572003500080000102003920039200392003920039
80024200381500000000001342580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000010305020000516000462003500080000102003920039200392003920039
80024200381500000002768803925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010000000050200001116000772003500080000102003920039200392003920039
8002420038150000000180039258001010800001080000506400000120019200382003899963100188001020800002016000020038200381180021109101080000100000000502000012160001152003500080000102003920039200392003920039
80024200381500000000004525800101080000108000062640000002001920038200389996310018800102080000201600002003820038118002110910108000010000000050200001316000662003500080000102003920039200392003920039
80024200381500000001800602580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000000005020000616000652003500080000102003920039200392003920039
80024200381500000000003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010000000050200016160001142003500080000102003920039200392003920039