Apple M1 Microarchitecture Research by Dougall Johnson

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

CMEQ (register, 8B)

Test 1: uops

Code:

  cmeq v0.8b, v0.8b, v1.8b
  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)0308090b18191e1f3f4e51inst 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)a0a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10042037150000000611687251000100010002646800201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
10042037160000000611687251000100010002646801201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
10042037150000000611687251000100010002646800201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
10042037150000090611687251000100010002646800201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
10042037160000000611687251000100010002646801201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
10042037160000000611687251000100010002646800201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
10042037150000000611687251000100010002646801201820372037157231895100010002336208420371110011000000073116111787100020382038203820382038
10042037150000000611687251000100010002646801201820372037157231895100010002000203720371110011000000073116111787100020382038203820382038
10042037160000000611687251000100010002646801201820372037157271895100010002000203720371110011000000073116111787100020382038203820382038
10042037170000000611687251000100010002646800201820372037157231895100010002000203720371110011000009073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmeq v0.8b, v0.8b, v1.8b
  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)030708191e3a3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500003011721968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010011997714617421979125100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
1020420037150000001031968725101001001000010010000500284768002001820037200371842231874510100202101682002000020037200371110201100991001001000010000710417221979125100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
102042003715000000103196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
10204200371500009061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
10204200371501000061196872510100100100001251000062628476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820085200382003820038
10204200371500000061196872510100100100001001000062628476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000071021622197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03081e3f4e51inst 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)9fa0a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150008419687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371500023219687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150096119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150008219687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100010640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680020018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
1002420037150108419687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmeq v0.8b, v1.8b, v0.8b
  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)9faccfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715003641968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715001261968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715007261968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038
102042003715001281968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010007101161119791100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)0307080b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715000000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003714900100900611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715000000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000100006402162219785010000102003820038200382003820038
1002420037150000102971040611968725100101010000101000050284768012001820037200371844431876710162201033620200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715000000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715000000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715000000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024201801500000000015541967625100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000100006403242219785210000102003820038200382008620085
100242003715000000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000026100611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmeq v0.8b, v8.8b, v9.8b
  cmeq v1.8b, v8.8b, v9.8b
  cmeq v2.8b, v8.8b, v9.8b
  cmeq v3.8b, v8.8b, v9.8b
  cmeq v4.8b, v8.8b, v9.8b
  cmeq v5.8b, v8.8b, v9.8b
  cmeq v6.8b, v8.8b, v9.8b
  cmeq v7.8b, v8.8b, v9.8b
  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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815033940258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000051102161120035800001002003920039200392003920039
8020420038150063258010010080000100800975006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000051101162120035800001002003920039200392003920039
80204200381501240258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200192003820038997303999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
80204200381503640258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150340258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815038740258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039
802042003815039340258010010080000100800005006400000200192003820038997303999680100200800002001600002003820038118020110099100100800001000051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0318191e1f3f51inst 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)9fa6a7a8accfd0d2itlb miss (d4)d5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915000390392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000005020000161613920035080000102003920039200392003920039
800242003815000003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010000125020000121681220035080000102003920039200392003920039
800242003815000003925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010000050200001216121220035080000102003920039200392003920039
8002420038150002403925800101080000108000050640000002001920038200389996310018800102080000201600002003820038118002110910108000010000470502000081681220035080000102003920039200392008920039
800242003815000243039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100000502000081691220035080000102003920039200392003920039
800242003815000390394480010108009410800005064000000200192003820087999631001880110208009920160000200382003811800211091010800001022005020000141691220074080000102003920089200392003920039
80024200381500096039258001010800001080000506400000520019200382003899963100188001020800002016000020038200381180021109101080000100000502000081681220035080000102003920039200392003920039
800242003815000240392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001000035020510131612820035080000102003920039200902003920039
8002420038150002703925800101080000108000050640000002001920038200381001331001880010208000020160000200382003811800211091010800001000005020510121612820035080000102003920039200392003920039
80024200381500021012725800101080000108000050640000102001920038200389996310018800102080000201600002003820038118002110910108000010001405020510121613920035080000102003920039200392003920039