Apple M1 Microarchitecture Research by Dougall Johnson

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

FRECPS (vector, 4S)

Test 1: uops

Code:

  frecps v0.4s, v0.4s, v1.4s
  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)03070a1e3a3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch 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)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100440373011926834072510001000100053190840184037403732583389510001000200040374037111001100077416443473100040384038403840384038
100440373011026834072510001000100053190840184037403732583389510001000200040374037111001100077416443473100040384038403840384038
100440373011026834072510001000100053190840184037403732583389510001000200040374037111001100077416443473100040384038403840384038
100440373011026834072510001000100053190840184037403732583389510001000200040374037111001100077416443473100040384038403840384038
100440373011926834072510001000100053190840184037403732583389510001000200040374037111001100077416443473100040384038403840384038
100440373111026834072510001000100053190840184037403732583389510001000200040374037111001100077416443473100040384038403840384038
1004403730113926834072510001000100053190840184037403732583389510001000200040374037111001100077416443473100040384038403840384038
100440373011026834072510001000100053190840184037403732583389510001000200040374037111001100077416443473100040384038403840384038
100440373011028934072510001000100053190840184037403732583389510001000200040374037111001100077416443473100040384038403840384038
100440373011026834072510001000100053190840184037403732583389510001000200040374037111001100077416443473100040384038403840384038

Test 2: Latency 1->2

Code:

  frecps v0.4s, v0.4s, v1.4s
  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)696b6d6edispatch 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)9fa0a6a7a8acc5cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204400373000000613940725101001001000010010000500570690840018040037400373810803387451010020010000200200004003740037111020110099100100100001000000600071011611394790100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069084001804003740037381080338745101002001000020020000400374003711102011009910010010000100000012000710116113947919100001004003840136401344003840038
102044003729910931047263940725101001001000010010000500570690840018040037400373810803387451010020010000200203344008540037111020110099100100100001001007430071011611394790100001004003840038400384003840038
10204400373000000613940725101001001000010010000500570690840018040037400373810803387451010020010000200200004003740037111020110099100100100001000007390071011611394790100001004003840038400384003840038
102044003730000006139407251010010010000100100005005706908400180400374003738108033874510100200100002002000040037400371110201100991001001000010000001200071011611394790100001004003840038400384003840038
1020440037299001201033940725101001001000010010000522570690840053040037400373810803387631010020810000200200004003740037211020110099100100100001000303290071011611394790100001004003840038400384003840038
1020440037300000010339407251010010010000100100005005706908400180400374003738108033874510100200100002002000040037400371110201100991001001000010000001410071011611394790100001004003840038400384003840038
102044003730000120613940725101001001000010010000500570690840018040037400373810803387451010020010000200200004003740037111020110099100100100001000001180071011611394790100001004003840038400384003840038
1020440037300340082394072510100100100001001000066457069084001804003740037381080338745101002001000020020000400374003711102011009910010010000100000090071011611394790100001004003840038400384003840038
1020440037300000061394072510100100100001001000050057069084001804003740037381080338745101002001000020020000400374003711102011009910010010000100000090071011611394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)03090b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024400373000000006139407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100000009006402162239473010000104003840038400384003840038
10024400373000000007263940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000000306402162239473010000104003840038400834003840038
1002440037300000000613940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000000006402162239473010000104003840038400384003840038
10024400373000000006139407251001010100001010000505706908040018400374003738130338767100102010000202000040037400371110021109101010000100000520306402162239473010000104003840038400384003840038
10024400373000000006139407251001010100001010000505706908140018400374003738130338767100102010000202000040037400371110021109101010000100001930306402162239473010000104003840038400384003840038
1002440037300000000613940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000000006402162239473010000104003840038400384003840038
10024400373000000007263940725100101010000101000050570690804001840037400373813033876710010201000020200004003740037111002110910101000010000000006402162239473010000104003840038400384003840038
100244003729900000061394072510010101000010100005057069080400184003740037381303387671001020100002020000400374003711100211091010100001000000013506402162239473010000104003840038400384003840038
1002440037300000000823940725100101010000101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010000000306402162239473010000104003840038400384003840038
10024400373000000006139407251001010100001010115505706908140018400374003738130338767100102010000202000040037400371110021109101010000100000710006402162239473010000104003840038400384003840038

Test 3: Latency 1->3

Code:

  frecps v0.4s, v1.4s, v0.4s
  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)9fa1a6a7a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102044003730006139407251010010010000132100005005706908140018040037400373810833874510100200100002002000040037400371110201100991001001000010002010007102172239479100001004003840038400384003840038
1020440037299061394072510100100100001001000050057069081400180400374003738108338745101002001000020020000400374003711102011009910010010000100000403007102162239479100001004003840038400384003840076
102044003730006139407251010010010000100100005005706908140018040037400373810833874510100200100002002000040037400371110201100991001001000010000000007102162239479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018040037400373810833874510100200100002002000040037400371110201100991001001000010000000007102162239479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018040037400373810833874510100200100002002000040037400371110201100991001001000010000000007102162239479100001004003840038400384003840038
102044003730006139407251010010010012100100005005706908140018040037400373810833874510100200100002002000040037400371110201100991001001000010000010007102162239479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018040037400373810833874510100200100002002000040037400371110201100991001001000010000000007102162239479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018040037400373810833874510100200100002002000040084400371110201100991001001000010000009007102162239479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018040037400373810833874510100200100002002000040037400371110201100991001001000010000010007102162239479100001004003840038400384003840038
102044003730006139407251010010010000100100005005706908140018040037400373810833874510100200100002002000040037400371110201100991001001000010000000007102162239479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)03080b18191e3a3f4e51inst 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)9fa6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003730000000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001001006402162239473010000104003840038400384003840038
1002440037300000000613940725100101010024101000050570690814001840037400373813033876710010201000020200004003740037111002110910101000010054006402162239473010000104003840038400384003840038
100244003730000000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000006402162239473010000104003840038400384003840038
100244003730000000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001001006402162239473010000104003840038400384003840038
100244003730000000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000006402162239473010000104003840038400384003840038
100244003730000000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001002006402162239473010000104003840038400384003840038
100244003730000000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000006402162239473010000104003840038400384003840038
100244003730000000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000006402162239473010000104003840038400384003840038
100244003730000000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000006402162239473010000104003840038400384003840038
100244003730000000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000006402162239473010000104003840038400384003840038

Test 4: throughput

Count: 8

Code:

  frecps v0.4s, v8.4s, v9.4s
  frecps v1.4s, v8.4s, v9.4s
  frecps v2.4s, v8.4s, v9.4s
  frecps v3.4s, v8.4s, v9.4s
  frecps v4.4s, v8.4s, v9.4s
  frecps v5.4s, v8.4s, v9.4s
  frecps v6.4s, v8.4s, v9.4s
  frecps v7.4s, v8.4s, v9.4s
  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)03083f51inst 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)9fa8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420094150010725801001008000010080000500640000200212004020040997339998801002008000020016000020040200401180201100991001008000010000051102161120037800001002004120041200412004120041
802042004015004225801001008000010080000500640000200212004020040997339998801002008000020016000020040200401180201100991001008000010000051101161120037800001002004120041200412004120041
802042004015004225801001008000010080000500640000200212004020040997339998801002008000020016000020040200401180201100991001008000010010051101161120037800001002004120041200412004120041
802042004015004225801001008000010080000500640000200212004020040998339998801002008000020016021220040200401180201100991001008000010013251271371120037800001002004120041200412004120041
802042010015014225801001008000010080000500640000200212004020040997339998801002008000020016000020040200401180201100991001008000010010051101161120037800001002004120041200412004120041
8020420040150042225801001008000010080000500640000200212004020040997339998801002008000020016000020040200401180201100991001008000010000051101161120037800001002004120041200412004120041
802042004015004225801001008000010080000500640000200212004020040997339998801002008000020016000020040200401180201100991001008000010000051101161120037800001002004120041200412004120041
802042004015004225801001008000010080313500640000200212004020040997339998801002008000020016000020040200401180201100991001008000010016051101161120037800001002009220041200412004120041
802042004015004225801001008000010080000500640000200212004020040997339998801002008010620016000020040200401180201100991001008000010000051101161120037800001002004120041200412004120041
80204200401500102125801001008000010080000500640000200212004020040997339998801002008000020016000020040200401180201100991001008000010000051101161120037800001002004120041200412004120041

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3a3f51inst 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)9fa8acc2cfd0icache miss (d3)d5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420049150004125800101080000108000050640000120021200402004099963100208001020800002016000020040200401180021109101080000100005020066164220037080000102004120041200412009220041
8002420040150004125800101080000108000050640000120021200402004099963100208001020800002016000020040200401180021109101080000100005020054163520037080000102004120041200412004120041
8002420040150014125800101080000108000050640000120021200402004099963100208001020800002016000020040200401180021109101080000100005020054162720037080000102004120041200412004120041
8002420040150004125800101080000108000050640000120021200402004099963100208001020800002016000020040200401180021109101080000100005020054165720037080000102004120041200412004120041
8002420040150004125800101080000108000050640000120021200402004099963100208001020800002016000020040200401180021109101080000100605020054162520037080000102004120041200412004120041
80024200401500068925800101080000108000050640000120021200402004099963100208001020800002016000020040200401180021109101080000100005020054165220037080000102004120041200412004120041
8002420040150006425800101080000108000050640000120021200402004099963100208001020800002016000020040200401180021109101080000100005020054164220037080000102004120041200412004120041
80024200401500041258001010800001080000506400001200212004020040999631002080010208000020160000200402004011800211091010800001003305020054164220037080000102004120041200412004120041
80024200401506304125800101080000108000050640000120021200402004099963100208001020800002016000020040200401180021109101080000100005020054164420037080000102004120041200412004120041
80024200401500010625800101080000108000050640000120021200402004099963100208001020800002016000020040200401180021109101080000100005020054164220037080000102004120041200412004120041