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, 2S)

Test 1: uops

Code:

  frsqrts 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
100440373106134072510001000100053190814018403740373258338951000100020004037403711100110000073216113473100040384038403840384038
100440373036134072510001000100053190804018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
100440373008434072510001000100053190814018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
100440373106134072510001000100053190814018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
100440373006134072510001000100053190804018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
100440373106134072510001000100053190814018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
100440373066134072510001000100053190804018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
100440373006134072510001000100053190804018403740373258338951000100020004037403711100110000073116113473100040384038403840384038
100440373006134072510001000100053190814018403740373258338951000100020004037403711100110000373116113473100040384038403840384038
100440373006134072510001000100053190814018403740373258338951000100020004037403711100110000073116113473100040384038403840384038

Test 2: Latency 1->2

Code:

  frsqrts 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): 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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102044003730007263940725101001001000010010000500570690840018400374003738108338745101002001000020020000400374003711102011009910010010000100007102162239479100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690840158400374003738108338745101002001000020020000400374003711102011009910010010000100007102162239479100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690840018400374003738108338745101002001000020020000400374003711102011009910010010000100007102162239479100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690840018400374003738108338745101002001000020020000400374003711102011009910010010000100007102162239479100001004003840038400384003840038
10204400372990613940725101001001000010010000500570690840018400374003738108338745101002001000020020000400374003711102011009910010010000100007102162239479100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690840018400374003738108338745101002001000020020000400374003711102011009910010010000100007102162239479100001004003840038400384003840038
10204400372990613940725101001001000010010000500570690840018400374003738108338745101002001000020020000400374003711102011009910010010000100007102162239479100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690840018400374003738108338745101002001000020020000400374003711102011009910010010000100007102162239479100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690840018400374003738108338745101002001000020020000400374003711102011009910010010000100207102162239479100001004003840038400384003840038
10204400373000613940725101001001000010010000500570690840018400774003738108338745101002001000020020000400374003711102011009910010010000100007102162239479100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)030818191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003730000000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000000006402162239473010000104003840038400384003840038
100244003729900000061394072510010101000010100005057069080400184003740037381303387671001020100002020000400374003711100211091010100001000000006402162239473010000104003840038400384003840038
100244003730000000061394072510010101000010100005057069080401584003740037381303387671001020100002020000400374003711100211091010100001000000006402162239473010000104003840038400854003840038
100244003730000000061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000000006402162239473010000104003840038400384003840038
100244003730000000061394072510010101000010100005057069080400184003740037381303387671001020100002020000400374003711100211091010100001000000006402162239473010000104003840038400384003840038
100244003731000090061394072510010101000012100005057069080400184003740037381303387671001020101722020000400374003721100211091010100001000000006402162239473010000104003840038400384003840038
100244003731000018008939407251001010100001010000505706908040018400374003738130283887511048201097222222644036840368811002110910101000010403022134007883654439711310000104003840038400384003840038
1002440037311000900823940725100101010000141000050572086804001840366400373813052387671001024100002021936403684003711100211091010100001000010306822162239914010000104003840038400384050940038
100244003731000090061394072510010101000010100005057069081400184003740037381303387671001020100002020000400374003711100211091010100001000000306402162239473010000104003840038400384003840085
10024400373140991188704061393982510010101000010100005057069080400184003740037381303387671001020100002020000400374003711100211091010100001000200006402162239473010000104003840038400384003840038

Test 3: Latency 1->3

Code:

  frsqrts 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): 4.0037

retire (01)cycle (02)0307080b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204400373001000000072639407251010010010000100100005005706908040018400374003738108338745101002001000020020000400374003711102011009910010010000100000000071021622394790100001004003840038400384003840038
1020440037300000000006139407251010010010000100100005005706908040018400374003738108338745101002001000020020000400374003711102011009910010010000100000000071021622394790100001004003840038400384018140038
1020440037299000000006139407251010010010000100100005005706908040018400374003738108338745101002001000020020000400374003711102011009910010010000100000000071021622394790100001004003840038400384003840038
1020440037300000000006139407251010010010000100100005005706908040018400374003738108338745101002001000020020000400374003711102011009910010010000100000000071021622394790100001004003840038400384003840038
1020440037300000000006139407251010010010000100100005005706908040018400374003738108338745101002001000020020000400374003711102011009910010010000100000100071021622394790100001004003840038400384003840038
1020440037299000000006139407251010010010000100100005005706908040018400374003738108338745101002001000020020000400374003711102011009910010010000100000000071021622394790100001004003840038400384003840038
1020440037300000000006139407251010010010000100100005005706908040018400374003738108338745101002001000020020000400374003711102011009910010010000100000000071021622394790100001004003840038400384003840038
1020440037299000000006139407251010010010000100100005005706908040018400374003738108338745101002001000020020664400374003711102011009910010010000100000300071041622394790100001004003840038400384003840038
10204400373000000000025139407251010010010000100100005005708304140018400374003738108338745101002001000020020000400374003711102011009910010010000100000000071021622394790100001004003840038400384003840038
1020440037299000000006139407251010010010000100100005005706908040018400374003738108338745101002001000020020662400374003711102011009910010010000100000000071021622394790100001004003840038400384003840038

1000 unrolls and 10 iterations

Result (median cycles for code): 4.0037

retire (01)cycle (02)03080b181e1f3a3f4e51inst 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)9fa0a1a6a7a8acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100244003730000000061394072510010101000010100005557069084001840037400373813033876710010201000020200004003740037111002110910101000010000003653016402162239473010000104003840038400384003840038
100244003730000000061394072510010101000010100005057069084001840037400373813033876710010201000020200004003740037111002110910101000010000000006402162239473010000104003840038400384003840038
1002440037299000000613940725100101010000101000050570690840018400374003738130338767100102010000202000040037400371110021109101010000100000018006402162239473010000104003840038400384003840038
1002440037299000000613940725100101010000101000050570690840018400374003738130338767100102010000202000040037400371110021109101010000100000096006402162239473010000104003840038400384003840038
1002440037300000000613940725100101010000101000050570690840018400374003738130338767100102010000202000040037400371110021109101010000100000072006402162239473010000104003840038400384003840038
1002440037300000000613940725100101010000101000050570690840018400374003738130338767100102010000202000040037400371110021109101010000100000078006402162239473010000104003840038400384003840038
1002440037300000000613940725100101010000101000050570690840018400374003738130338767100102010000202000040037400371110021109101010000100000087006402162239473010000104003840038400384003840038
10024400373000000006139407251001010100001010000505706908400184003740037381303387671001020100002020000400374003711100211091010100001000000144006402162239473010000104003840038400384003840038
1002440037299000000613940725100101010000101000050570690840018400374003738130338767100102010000202000040037400371110021109101010000100000024006402162239473010000104003840038400384003840038
100244003730000000061394072510010101000010100005057069084001840037400373813033876710010201000020200004003740037111002110910101000010000003006402162239473010000104003840038400384003840038

Test 4: throughput

Count: 8

Code:

  frsqrts v0.2s, v8.2s, v9.2s
  frsqrts v1.2s, v8.2s, v9.2s
  frsqrts v2.2s, v8.2s, v9.2s
  frsqrts v3.2s, v8.2s, v9.2s
  frsqrts v4.2s, v8.2s, v9.2s
  frsqrts v5.2s, v8.2s, v9.2s
  frsqrts v6.2s, v8.2s, v9.2s
  frsqrts 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)696d6edispatch 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)9fa6a8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815004225801001008000010080000500640000200212004020040997303999880100200800002001600002004020040118020110099100100800001000000511021611200370800001002004120041200412004120041
8020420040150033025801001008000010080000500640000200212004020040997303999880100200800002001600002004020040118020110099100100800001000030511011611200370800001002004120041200412004120041
802042004015004225801001008000010080000500640000200212004020040997373999880100200800002001600002004020040118020110099100100800001000330511011611200370800001002009220041200412004120041
8020420040150042258010010080000100800005006400002002120040200409973039998801002008000020016000020040200401180201100991001008000010000120511011611200370800001002004120041200412004120041
8020420040150023225801001008000010080000500640000200212004020040997303999880100200800002001600002004020040118020110099100100800001000000511011611200370800001002004120041200412004120041
802042004015504225801001008000010080000500640000200212004020040997303999880100200800002001600002004020040118020110099100100800001000000511011611200370800001002004120041200412004120041
802042004015004725801001008000010080000500640000201812004020040997303999880100200800002001600002004020040118020110099100100800001000000513011611200370800001002004120041200412004120041
802042004015004725801001008000010080000500640000200212004020040997303999880100200800002001603002004020040118020110099100100800001000230511011611200370800001002004120041200412004120041
802042004015004225801001008000010080000500640000200212004020040997303999880100200800002001600002004020040118020110099100100800001000000511011611200370800001002004120041200412004120041
802042004015004225801001008000010080000500640000200212004020040997303999880100200800002001600002004020040118020110099100100800001000030511011611200370800001002004120041200412004120041

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)9fa8acc5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200491500412580010108000010800005064000012002120040200409996310020800102080000201600002004020040118002110910108000010000050201016171720037080000102004120041200412004120041
800242004015004125800101080000108000050640000120021200402004099963100208001020800002016000020040200401180021109101080000100000502081617820037080000102004120041200412004120041
8002420040150041258001010800001080000506400001200212004020040999631002080010208000020160000200402004011800211091010800001000005020171617620101080000102004120041200412004120041
800242004015004125800101080000108000050640000020021200402004099963100208001020800002016000020040200401180021109101080000102000502081681720037080000102004120041200412004120041
8002420040150041258001010800001080000506400001200212004020040999631002080010208000020160000200402004011800211091010800001000005020171617620037080000102004120041200412004120041
80024200401500412580010108000010800005064000002002120040200409996310020800102080000201600002004020040118002110910108000010100150201716171720037080000102004120041200412004120041
8002420040150041258001010800001080000506400000200212004020040999631002080010208000020160000200402004011800211091010800001000005020171617820037080000102004120041200412004120041
800242004015004125800101080000108000050640000020021200402004099963100208001020800002016000020040200401180021109101080000100000502081617620037080000102004120041200412004120041
8002420040150041258001010800001080000506400000200212004020040999631002080010208000020160000200402004011800211091010800001000005020171617620037080000102004120041200412004120041
800242004015004125800101080000108000050640000020021200402004099963100208001020800002016000020040200401180021109101080000101230050201716171720037080000102004120041200412004120041