Apple M1 Microarchitecture Research by Dougall Johnson

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

FRSQRTS (scalar, D)

Test 1: uops

Code:

  frsqrts d0, d0, d1
  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)03080918191e3f4e51inst 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)a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10044037310000061340725100010001000531908140184037403732583389510001000200040374037111001100000073316333473100040384038403840384038
10044037300000061340725100010001000531908140184037403732583389510001000200040374037111001100000073316333473100040384038403840384038
100440373000008761340725100010001000531908140184037403732583389510001000200040374037111001100000073316333473100040384038403840384038
10044037300000061340725100010001000531908140184037403732583389510001000200040374037111001100000073316333473100040384038403840384038
10044037300000061340725100010001000531908140184037403732583389510001000200040374037111001100010073316333473100040384038403840384038
10044037300000061340725100010001000531908140184037403732583389510001000200040374037111001100010073316333473100040384038403840384038
10044037300000061340725100010001000531908140184037403732583389510001000200040374037211001100000073316333473100040384038403840384038
10044037300000061340725100010001000531908140184037403732583389510001000200040374037111001100000073316333473100040384085403840384038
10044037300000061340725100010001000531908140184037403732583389510001000200040374037111001100000073316333473100040384038403840384038
10044037300000082340725100010001000531908040184037403732583389510001000200040374037111001100009073316333473100040384038403840384038

Test 2: Latency 1->2

Code:

  frsqrts d0, d0, d1
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)031e1f3f4e51inst 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)9fa6a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037300006139407251010010010000100100005005706908040018400374003738108338745101002001000020020000400374003711102011009910010010000100000071011611394790100001004003840038400384003840038
1020440037299006139407251010010010000100100005005706908040018400374003738108338745101002001000020020000400374003711102011009910010010000100000071011611394790100001004003840038400384003840038
1020440085300006139407251010010010000100100005005706908040018400374003738108338745101002001000020020000400374003711102011009910010010000100000071011611394790100001004003840038400384003840038
10204400373000072639407251010010010000121100005005706908040018400374003738108338745101002001000020020000400374003711102011009910010010000100000071011611394790100001004003840038400384003840038
1020440037299006139371671013110010000117100005325706908040018400374003738108338745101002001000020020000400374003711102011009910010010000100313271011611394790100001004003840038400384003840038
1020440037300006139407251010010010000100100005005706908040018400374003738108338745101002001000020020000400374003711102011009910010010000100010071011611394790100001004003840038400384003840038
1020440037300006139407251010010010000100100005005706908040018400374003738108338745101002001000020020000400374003711102011009910010010000100000071011611394790100001004003840038400384003840038
102044003730029719210339398661010010010000119100006655706908040053400844003738112338745102512001000020020000400374003711102011009910010010000100010071011611394790100001004003840038400384003840038
10204400373001206139407251010010010000100100005005706908040018400374003738108338745101002001000020020000400374003711102011009910010010000100000071011611394790100001004003840038400384003840038
1020440037299006139407251010010010000100100005005706908040018400374022938108338745101002001000020020000400374003711102011009910010010000100003071011611394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)030b191e1f3f4e51inst 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)9fa8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400373000030061394072510010101000010100005057069080400184003740037381303387671001020100002020000400374003711100211091010100001000006403163339473010000104003840038400384003840038
1002440037300000061394072510010101000010100005057069080400184003740037381303387671001020100002020000400374003711100211091010100001000006403163339473010000104003840038400384003840038
1002440037299000061394072510010101000010100005057069080400184003740037381303387671001020106432020000400374003711100211091010100001000006603163339473010000104003840038400384003840038
1002440037300000061394072510010101000010100005057069080400184003740037381303387671001020100002020000400374003711100211091010100001000006403163339473010000104003840038400384003840038
1002440037300000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000006403163339473010000104003840038400384003840038
1002440037299000076394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000006403163339473010000104003840038400384003840038
1002440037299000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000006403163339473010000104003840038400384003840038
1002440037300000061394072510010101000010100005057069080400184003740037381303387671001020100002020000400374003711100211091010100001000006403163339473010000104003840038400384003840038
10024400373000000232394072510010101000010100005057069080400184003740037381303387671001020100002020000400374003711100211091010100001000006403163339473010000104003840038400384003840038
1002440037300000061394072510010101000010100005057069080400184003740037381303387671001020100002020000400374003711100211091010100001000006403173339473010000104003840038400384003840038

Test 3: Latency 1->3

Code:

  frsqrts d0, d1, d0
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)0318191e1f3f4e51inst 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)9fa8acbranch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020440037300000061394072510100100100001001000050057069084001840037400373810833874510100200100002002000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
1020440037300000061394072510100100100001001014850057069084001840037400373810833874510100200100002002000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
10204400373000000536394072510100100100001001000050057069084001840037400373810833874510100200100002002000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069084001840037400373810833874510100200100002002000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069084001840037400373810833874510100200100002002000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069084001840037400373810833874510100200100002002000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069084001840037400373810833874510100200100002002000040037400371110201100991001001000010010007101161139479100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069084001840037400373810833874510100200100002002000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
10204400373000012061394072510100100100001001000050057069084012340037400373810833874510100200100002002000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
102044003730000180843394072510100100100001001000050057069084001840037400373810833874510100200100002002000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

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)9fa0a1a6a8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003730006139407251001010100001010000505706908040018400374003738153338767100102010000202000040037400371110021109101010000100004500640216223947310000104003840038400384003840038
10024400373000613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000000640216223947310000104003840038400384003840038
10024400372990613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000000640216223947310000104003840038400384003840038
1002440037300010203940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000000640216223947310000104003840038400384003840038
10024400373000823940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000000640216223947310000104003840038400384003840038
10024400373000613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000000640216223947310000104003840038400384003840038
10024400373000613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000000640216223947310000104003840038400384003840038
10024400373000613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000100640216223947310000104003840038400384003840038
10024400373000613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000000640216223947310000104003840038400384003840038
100244003730006139407251001010100041010000505706908040018400374008438130338767100102010000202000040037400371110021109101010000100000120640216223947310000104003840038400384003840038

Test 4: throughput

Count: 8

Code:

  frsqrts d0, d8, d9
  frsqrts d1, d8, d9
  frsqrts d2, d8, d9
  frsqrts d3, d8, d9
  frsqrts d4, d8, d9
  frsqrts d5, d8, d9
  frsqrts d6, d8, d9
  frsqrts d7, d8, d9
  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)0308090b18191e1f3a3f51inst 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
802042004015000000150042258010010080000100800005006400000200212004020040997339998801002008000020016000020040200401180201100991001008000010000000000511041611200370800001002004120041200412004120119
80204200401500000000042258010010080000100800005006400000200212004020040997339998801002008000020016000020040200401180201100991001008000010000000000511011611200370800001002004120041200412004120041
80204200401500000000042258010010080000100800005006400001200212004020040997339998801002008000020016000020040200401180201100991001008000010000000000511011611200370800001002004120041200412004120041
802042004015000000000213258010010080000100800005006400000200212004020040997339998801002008000020016000020040200401180201100991001008000010000000000511011611200370800001002004120041200412004120041
80204200401500000000042258010010080000100800005006400001200212004020040997339998801002008000020016000020040200401180201100991001008000010000000000511011611200370800001002004120041200412004120041
80204200401500000000042258010010080000100800005006400001200212004020040997339998801002008000020016000020040200401180201100991001008000010000000000511011611200370800001002004120041200412004120041
802042004015000000000707258010010080000100800005006400001200212004020040997339998801002008000020016000020040200401180201100991001008000010000000000511011611200370800001002004120041200412004120041
80204200401500000000042258010010080000100800005006400000200212004020040997339998801002008000020016000020040200401180201100991001008000010000000000511011611200370800001002004120041200412004120041
80204200401500000000042258010010080000100800005006400001200212004020040997339998801002008000020016000020040200401180201100991001008000010000000000511011611200370800001002004120041200412004120041
80204200401500000000042258010010080000100800005006400001200212004020040997339998801002008000020016000020040200401180201100991001008000010000000000511011611200370800001002004120041200412004120041

1000 unrolls and 10 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)9facbranch mispredict (cb)cfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004915004125800101080000108000050640000120021200402004099963100208001020800002016000020040200401180021109101080000100050207160462003780000102004120041200412004120041
800242004015004125800101080000108000050640000020021200402004099963100208001020800002016000020040200401180021109101080000100050205160562003780000102004120041200412004120041
800242004015004125800101080000108000050640000020021200402004099963100208001020800002016000020040200401180021109101080000100050206160652003780000102004120041200412004120041
800242004015004125800101080000108000050640000120021200402004099963100208001020800002016000020040200401180021109101080000100050206160652003780000102004120041200412004120041
8002420040150184125800101080000108000050640000120021200402004099963100208001020800002016000020040200401180021109101080000100050205160562003780000102004120041200412004120041
80024200401503184125800101080000108000050640000020021200402004099963100208001020800002016000020040200401180021109101080000100050207160662003780000102004120041200412004120041
800242004015004125800101080000108011650640000020021200402004099963100208001020800002016000020040200401180021109101080000100050205160762003780000102004120041200412004120041
800242004015004125800101080000108000050640000020021200922004099963100208001020800002016000020040200401180021109101080000100050206160772003780000102004120041200412004120041
800242004015004125800101080000108000050640000020021200402004099963100208001020800002016000020040200401180021109101080000100050205160562003780000102004120041200412004120041
800242004015004125800101080000108000050640000020021200402004099963100208001020800002016000020040200401180021109101080000100050205160652003780000102004120041200412004120041