Apple M1 Microarchitecture Research by Dougall Johnson

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

CMHS (register, 2S)

Test 1: uops

Code:

  cmhs v0.2s, v0.2s, v1.2s
  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
1004203716061168725100010001000264680120182037203715723189510001000200020372037111001100027073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000673116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000673116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  cmhs v0.2s, v0.2s, v1.2s
  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)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)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)9fa0a1a6a7a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204200371500000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000002000071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768012001820083200371842231874510100200100002002000020037200371110201100991001001000010000000030071011611197910100001002003820038200382003820038
10204200371500000600611968725101001001000010010000500284768012001820037200371842281874510100200100002002000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
10204200371500000300611968725101001001000010010000500284768012001820182200371842231874510100200101652002000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000000071011611197910100001002003820085200382003820038
10204200371500000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038
10204200371500000000611968725101001001000010010000500284768012001820037200371842231874510100200100002002000020037200371110201100991001001000010000000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03071e3f4e51inst 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)9faccdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100242003715009611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768002005420037200371844431876710010201000020200002003720037111002110910101000010006402162219823010000102003820038200382003820038
1002420037150009351968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715006611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102008520038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
10024200371500336611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038
100242003715000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010006402162219785010000102003820038200382003820038

Test 3: Latency 1->3

Code:

  cmhs v0.2s, v1.2s, v0.2s
  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)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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715006119687251010010010000100100005002847680020018200372003718422031874510100200100002002000020037200371110201100991001001000010005471011611197910100001002003820038200382003820038
10204200371501861196872510100100100001001000050028476800200182003720037184220318745101002001000020020000200372003711102011009910010010000100012071011611197910100001002003820038200382003820038
10204200371500611968725101251251000010010000626284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680020018200372003718422031874510100200100002002000020037200371110201100991001001000010008171011611197910100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
102042003715001051968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500611968725101001001000010010000626284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500611968725101001001000010010000626284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038
10204200371500611968725101001001000010010000500284768002001820037200371842203187451010020010000200200002003720037111020110099100100100001000071011611197910100001002003820038200382003820038

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)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)9fa0a1a7a8a9acc2cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000016402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000003006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000018045006402162219785010000102003820038200382003820038
1002420037150000000061196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000000141006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100000027006402162219785010000102003820038200382003820038
10024200371500000000611968725100101010000101000050285024612001820037200371844431876710010201000020200002003720037111002110910101000010000000006402162219785010000102003820038200382003820038
100242003715000000006119687251001010100001010000502847680120018200372003718444318767100102010000202000020037200371110021109101010000100008027006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  cmhs v0.2s, v8.2s, v9.2s
  cmhs v1.2s, v8.2s, v9.2s
  cmhs v2.2s, v8.2s, v9.2s
  cmhs v3.2s, v8.2s, v9.2s
  cmhs v4.2s, v8.2s, v9.2s
  cmhs v5.2s, v8.2s, v9.2s
  cmhs v6.2s, v8.2s, v9.2s
  cmhs v7.2s, v8.2s, v9.2s
  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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420049150940258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051102161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100383051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100246051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
8020420038150519402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100300051101161120035800001002003920039200392003920039
80204200381500402580100100800001008000050064000012001920038200389973399968010020080000200160000200382003811802011009910010080000100333051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161120035800001002003920039200392003920039
8020420038150040258010010080000100800005006400001200192003820038997339996801002008000020016000020038200381180201100991001008000010000051101161320035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090b18191e1f3f51inst 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)9fa0a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420048150000000039258001010800001080000556400000120019200382003899963100188001020800002016000020038200381180021109101080000100103050209164320035080000102003920039200392003920039
8002420038150000000039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100700050203164320035080000102003920039200392003920039
8002420038150000000039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100000050203163420035080000102003920039200392003920039
80024200381500000000392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001002703050203164320035080000102003920039200392003920039
80024200381500000000392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001003303050204164320035080000102003920039200392003920039
8002420038150000000039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100000050203163420035080000102003920039200392003920039
80024200381500000000229258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100000050203163420035080000102003920039200392003920039
80024200381500000000392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001004103050204164320035080000102003920039200392003920039
8002420038150000000039258001010800001080000506400000020019200382003899963100188001020800002016000020038200381180021109101080000100000050204164320035080000102003920039200392003920039
800242003815000000150392580010108000010800005064000000200192003820038999631001880010208000020160000200382003811800211091010800001002503050204164420035080000102003920039200392003920039