Apple M1 Microarchitecture Research by Dougall Johnson

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

FCMEQ (scalar, H)

Test 1: uops

Code:

  fcmeq h0, h0, h1
  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
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715126116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
1004203715021216872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371508116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371506116872510001000100026468002018203720371572318951000100020002037203711100110000073116111787100020382038203820382038
100420371606116872510001000100026468012018203720371572318951000100020002037203711100110000073116111787100020382038203820382038

Test 2: Latency 1->2

Code:

  fcmeq h0, h0, h1
  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)9fa0a8acc5cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038
102042003715006119687251010010010000100100005002847680200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071011611197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)03191e3f4e51inst 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)9fa1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024200371500061196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100010640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100220640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100020640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200372110021109101010000100000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476801200182003720037184440318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371501061196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
100242003715000124196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038
10024200371500061196872510010101000010100005028476800200182003720037184440318767100102010000202000020037200371110021109101010000100000640216221978510000102003820038200382003820038

Test 3: Latency 1->3

Code:

  fcmeq h0, h1, h0
  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)030818191e1f3f4e51inst 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? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020420037150000001229196872510100100100001001000050028476800200182003720037184297187401010021010008200200162003720037111020110099100100100001000011171711611198010100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768002001820037200371842961874010100200100082002001620037200371110201100991001001000010006011171711611198010100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001002300071021622197910100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001008000071021622197910100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021621197910100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476800200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
10204200371500000061196872510100100100001001000050028476801200182003720037184223187451010020010000200200002003720037111020110099100100100001000000071021622197910100001002003820038200382003820038
102042003715000000611968725101001001000010010000500284768002001820037200371842231874510100200100002002000020037200371110201100991001001000010007800071021622197910100001002003820038200382003820038

1000 unrolls and 10 iterations

Result (median cycles for code): 2.0037

retire (01)cycle (02)031e1f3a3f4e51inst 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)9fa0a1a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002420037150000611968725100101010000101000050284768002001820037200371844431876710010201000020200002003720037111002110910101000010000846402162219785010000102003820038200382003820038
1002420037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000426402162219785010000102003820038200612003820038
1002420037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000666402162219785010000102003820038200382003820038
1002420037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000756402162219785010000102003820038200382003820038
10024200371500001451968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000816402162219785010000102003820038200382003820038
1002420037150000611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000666402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476801200182003720037184443187671001020101802020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
100242003715000061196872510010101000010100005028476800200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038
100242003715035400611968725100101010000101000050284768012001820037200371844431876710010201000020200002003720037111002110910101000010000756402162219785010000102003820038200382003820038
10024200371501561921103196872510010101000010100005028476801200182003720037184443187671001020100002020000200372003711100211091010100001000006402162219785010000102003820038200382003820038

Test 4: throughput

Count: 8

Code:

  fcmeq h0, h8, h9
  fcmeq h1, h8, h9
  fcmeq h2, h8, h9
  fcmeq h3, h8, h9
  fcmeq h4, h8, h9
  fcmeq h5, h8, h9
  fcmeq h6, h8, h9
  fcmeq h7, h8, h9
  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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150038625801001008000010080000500640000120019200382003899730399968010020080000200160000200382003811802011009910010080000100051104161120035800001002003920039200392003920039
8020420038150017225801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
8020420038150027525801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100051102161120035800001002003920039200392003920039
8020420038150010325801001008007610080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
802042003815004044803121008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100051101161120097800001002003920039200392003920039
802042003815008225801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
8020420038150014525801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
8020420038150012425801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039
802042003815004025801001008000010080000500640000020019200382003899730399968010020080000200160000200382003811802011009910010080000100051101161120035800001002003920039200392003920039

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03041e3f51inst 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)61696d6edispatch 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)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420047150101242580010108000010800005064000002001920038200389996031001880108208000020160000200382003811800211091010800001000502026163226200350080000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996031001880010208000020160000200382003811800211091010800001000502025161427200350080000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996031001880010208000020160000200382003811800211091010800001000502027162028200350080000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996031001880010208000020160000200382003811800211091010800001000502025163427200350080000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996031001880010208000020160000200382003811800211091010800001000502027163116200350080000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996031001880010208000020160000200382003811800211091010800001000502014162930200350080000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996031001880010208000020160000200382003811800211091010800001000502027163327200350080000102003920039200392003920039
800242003815000395080010108000010800005064000002001920038200389996031001880010208000020160000200382003811800211091010800001000502025163121200350080000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996031001880010208000020160000200382003811800211091010800001000502027163020200350080000102003920039200392003920039
800242003815000392580010108000010800005064000002001920038200389996031001880010208000020160000200382003811800211091010800001000502027161828200350080000102003920039200392003920039