Apple M1 Microarchitecture Research by Dougall Johnson

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

FRSQRTS (vector, 2D)

Test 1: uops

Code:

  frsqrts v0.2d, v0.2d, v1.2d
  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)03091e3f4e51inst 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
1004403730006134072510001000100053190814018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
1004403730006134072510001000100053190814018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
1004403731006134072510001000100053190814018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
1004403730006134072510001000100053190814018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
10044037300061340725100010001000531908140184037403732583389510001000200040374037111001100002473116113473100040384038403840384038
10044037300061340725100010001000531908140184037403732583389510001000200040374037111001100001273116113473100040384038403840384038
1004403730006134072510001000100053190814018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
1004403730006134072510001000100053190814018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
10044037300061340725100010001000531908140184037403732583389510001000200040374037111001100005473116113473100040384038403840384038
1004403730006134072510001000100053190814018403740373258338951000100020004037403711100110000073116113473100040384038403840384038

Test 2: Latency 1->2

Code:

  frsqrts v0.2d, v0.2d, v1.2d
  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)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)60696b6d6edispatch 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)9fa8acc5cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102044003730006139407251010010010000100100005005706908140018040037400373810833874510100200100002002000040037400371110201100991001001000010000007101161139479100001004008540038400384003840038
102044003730006139407251010010010000100100005005706908140018040037400373810833874510100200101652042000040037400371110201100991001001000010000107101161139479100001004003840038400384003840038
1020440084300186139407251010010010000100100005005706908140018340037400373810833874510100200100002002000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
102044003729906139407251010010010000100100005005706908140018040037400373810833874510100200100002002000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018040037400373810833874510100200100002002000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
1020440037300072639407251010010010000100100005005706908140018040037400373810833874510100200100002002000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018040037400373810833874510100200100002002000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
1020440037300010339407251010010010000100100005005706908140018040037400373810833874510100200100002002000040037400371110201100991001001000010000007101161139483100001004003840038400384003840038
102044003730008239407251010010010000100100005005706908140018040037400373810833874510100200100002002000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018040037400373810833874510100200100002002000040037400371110201100991001001000010000007101161139479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

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)9fa0a1a8a9accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400372990000072639407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100000006402162239473010000104003840038400384003840038
1002440037300000006139407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100000306402162239473010000104003840038400384003840038
1002440037300000006139407251001010100001010000505706908140018400374003738130338767100102010161202000040037400371110021109101010000100000006402162239473210000104003840038400384003840038
1002440037300000006139407251001010100001010000505706908140018400854003738130338767100102010000202000040037400371110021109101010000100000006402162239473010000104003840038400384003840038
1002440037300000006139407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100000006402162239473010000104003840038400384003840038
1002440037300000006139407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100000006402162239473010000104003840038400384003840038
10024400373000000089739407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100000006402162239473010000104003840038400384003840038
1002440037300000006139407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100000016402162239473010000104003840038400864003840038
10024400373000000010339407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100000006402162239473010000104003840085400384003840038
1002440037299000906139407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100000006402162339473010000104003840038400384003840038

Test 3: Latency 1->3

Code:

  frsqrts v0.2d, v1.2d, v0.2d
  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)030b18191e1f3f4e51inst 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
102044003730000021061394072510100100100001001000050057069081400184003740037381083387451010020010000200200004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
10204400373000006061394072510100100100001001000050057069081400184003740037381083387451010020010000200200004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
102044003730010018061394072510100100100001001000056457069081400184003740037381083387451010020010000200200004003740037111020110099100100100001003007101161139479100001004003840038400384003840038
102044003729900018132613940725101001001000010010000500570690814001840037400373810833874510100200100002002000040230400371110201100991001001000010001207101161139479100001004003840038400384003840038
10204400372990000061394072510100100100001001000050057069081400184003740037381083387451010020010000200200004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
102044003729900000685394072510100100100001001000050057069081400184003740037381083387451010020010000200200004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
10204400373000000061394072510100100100001001000050057069081400184003740037381083387451010020010000200200004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
10204400373000000061394072510100100100001001000050057069081400184003740037381083387451010020010000200200004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
102044003730000030061394072510100100100001001000050057069081400184003740226381083387451010020010000200200004003740037111020110099100100100001000007101161139479100001004003840038400384003840038
102044003730000084061394072510100100100001001000050057069081400184003740037381083387451010020010000200200004003740037111020110099100100100001000007101161139479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)03191e1f3f4e51inst 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
10024400373000007263940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037300000613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037300000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037299000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037300000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037300000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038
10024400373000300613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037300000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037300000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000640216223947310000104003840038400384003840038
1002440037300000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000640216223954410000104003840038400384003840038

Test 4: throughput

Count: 8

Code:

  frsqrts v0.2d, v8.2d, v9.2d
  frsqrts v1.2d, v8.2d, v9.2d
  frsqrts v2.2d, v8.2d, v9.2d
  frsqrts v3.2d, v8.2d, v9.2d
  frsqrts v4.2d, v8.2d, v9.2d
  frsqrts v5.2d, v8.2d, v9.2d
  frsqrts v6.2d, v8.2d, v9.2d
  frsqrts v7.2d, v8.2d, v9.2d
  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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420060150514225801001008000010080000500640000200212004020040997339998801002008000020016000020040200401180201100991001008000010000051102161120037800001002004120041200412004120041
8020420040150274225801001008000010080000500640000200212004020040997339998801002008000020016000020040200401180201100991001008000010000051104161120037800001002004120041200412004120041
8020420040150364225801001008000010080000500640000200212004020040997339998801002008000020016000020040200401180201100991001008000010000051101161120037800001002004120041200412004120041
802042004015004225801001008000010080000500640000200212004020040997339998801002008000020016000020040200401180201100991001008000010000051101161120037800001002004120041200412004120041
802042004015004225801001008000010080000500640000200212004020040997339998801002008000020016000020040200401180201100991001008000010000051101161120037800001002004120041200412004120041
8020420040150013725801001008000010080000500640000200212004020040997339998801002008000020016000020040200401180201100991001008000010000051101161120037800001002004120041200412004120041
802042004015004225801001008000010080000500640000200212004020040997339998801002008000020016000020040200401180201100991001008000010000051101161120037800001002004120041200412004120041
802042004015004225801001008000010080000500640000200212004020040997339998801002008000020016000020040200401180201100991001008000010000051101161120037800001002004120041200412004120041
8020420040150214225801001008000010080000500640000200212004020040997339998801002008000020016000020040200401180201100991001008000010000051101161120037800001002004120041200412004120041
802042004015004225801001008000010080000500640000200212004020040997339998801002008000020016000020040200401180201100991001008000010000051101161120037800001002004120041200412004120041

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)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)9fa6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420049150003004125800101080000108000050640000120021200402004099963100208001020800002016000020040200401180021109101080000100000050202116652003780000102004120041200412004120041
80024200401500000412580010108000010800005064000002002120040200409996310020800102080000201600002004020040118002110910108000010000005020716772003780000102004120041200412004120041
80024200401500000412580010108000010800005064000002002120040200409996310020800102080000201600002004020040118002110910108000010010005020716652003780000102004120041200412004120041
800242004015000004161800101080302108010750640000020021200402004099963100208001020800002016000020040200401180021109101080000100000050201116742003780000102004120041200412004120041
80024200401500000412580010108000010800005064000002002120040200409996310020800102080000201600002004020040118002110910108000010000005020516642003780000102004120041200412004120041
800242004015000004125800101080000108000050640000020021200402004099963100208001020800002016000020040200401180021109101080000100000050205164122003780000102004120041200412004120041
800242004015000004125800101080000108000050640000020021200402004099962610020800102080000201600002004020040118002110910108000010000005020516542003780000102004120041200412004120041
800242004015000150412580010108000010800005064000002002120040200409996310020800102080000201600002004020040118002110910108000010000005020616572003780000102004120041200412004120041
800242004015000002312580010108000010800005064000002002120040200409996310020800102080000201600002004020040118002110910108000010000005020616742003780000102004120041200412004120041
80024200401500000412580010108000010800005064000002002120040200409996310020800102080000201600002004020040118002110910108000010000005020516642003780000102004120041200412004120041