Apple M1 Microarchitecture Research by Dougall Johnson

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

FRECPX (scalar, D)

Test 1: uops

Code:

  frecpx d0, d0
  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)6061696d6edispatch 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)a8accfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230611900251000100010001044511030183037303727383289510001000100030373037111001100000730116112919100030383038303830383038
100430372202391900251000100010001044511030183037303727383289510001000100030373037111001100006730116112919100030383038303830383038
100430372301781900251000100010001044511030183037303727383289510001000100030373037111001100000730116112919100030383038303830383038
10043037220611900251000100010001044511030183037303727383289510001000100030373037111001100000730116112919100030383038303830383038
100430372305501900251000100010001044511030183037303727383289510001000100030373037111001100000730116112919100030383038303830383038
10043037220611884251000100010001044511030183037303727383289510001000100030373037111001100000730116112919100030383038303830383038
100430372202421900251000100010001044511030183037303727383289510001000100030373037111001100000730116112919100030383038303830383038
100430372301701900251000100010001044511030183037303727383289510001000100030373037111001100000730116112919100030383038303830383038
100430372301681900251000100010001044511030183037303727383289510001000100030373037111001100000730116112919100030383038303830383038
100430372201511900251000100010001044511030183037303727383289510001000100030373037111001100000730116112919100030383038303830383038

Test 2: Latency 1->2

Code:

  frecpx d0, d0
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000611990025101001001000010010000500106745103001803003730037285883287451010020010000200100003003730037111020110099100100100001000071011611299190100001003003830038300383003830038
1020430037225000611990025101001001000010010000500106745103001803003730037285883287451010020010000200100003003730037111020110099100100100001000071011611299190100001003003830038300383003830038
1020430037225000611990025101001001000010010000500106745103001803003730037285883287451010020010000200100003003730037111020110099100100100001000071011611299190100001003003830038300383003830038
1020430037225000611990025101001001000010010000500106745103001803003730037285883287451010020010000200100003003730037111020110099100100100001000071011611299190100001003003830038300383003830038
1020430037225000611990025101001001000010010000500106745113001803003730037285883287451010020010000200100003003730037111020110099100100100001000071011611299190100001003003830038300383003830038
1020430037225000611990025101001001000010010000500106745103001803003730037285883287451010020010000200100003003730037111020110099100100100001000071011611299190100001003003830038300383003830038
1020430037225000611990025101001001000010010000500106745113001803003730037285883287451010020010000200100003003730037111020110099100100100001000071011611299190100001003003830038300383003830038
1020430037225000611990025101001001000010010000500106745103001803003730037285883287451010020010000200100003003730037111020110099100100100001000071011611299190100001003003830038300383003830038
1020430037225000611990025101001001000010010000500106745113001803003730037285883287451010020010000200100003003730037111020110099100100100001000071011611299190100001003003830038300383003830038
1020430037225000611990025101001001000010010000500106745113001803003730037285883287451010020010000200100003003730037111020110099100100100001000071011611299190100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

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)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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500611990025100101010000101000050106745113001803003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
100243003722500611990025100101010000101000050106745113001803003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
100243003722500611990025100101010000101000050106745113001803003730037286103287671001020100002010000300373003711100211091010100001000640316222991910000103003830038300383003830038
100243003722500611990025100101010000101000050106745113001803003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
100243003722500611990025100101010000101000050106745113001803003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
100243003722500611990025100101010000101000050106745113001803003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038
100243003722500611990025100101010000101000050106745113001803003730037286103287671001020100002010000300373007611100211091010100001000640216222991910000103003830038300383003830038
100243003722500611990025100101010000101000050106745113001803003730037286103287671001020100002010000300373003711100211091010100001003640116222991910000103003830038300383003830038
100243003722500611990025100101010000101000050106745103001803003730037286103287671001020100002010000300373003711100211091010100001000640316222991910000103003830038300383003830038
100243003722500611990025100101010000101000050106745113001803003730037286103287671001020100002010000300373003711100211091010100001000640216222991910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frecpx d0, d8
  frecpx d1, d8
  frecpx d2, d8
  frecpx d3, d8
  frecpx d4, d8
  frecpx d5, d8
  frecpx d6, d8
  frecpx d7, d8
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 1.0005

retire (01)cycle (02)030a191e1f3f51inst 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)9fa6a8a9acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802048004060000003925801001008000010080000500640000180020800398003969971669993801002008000820080008800398003911802011009910010080000100000011151172163480036800001008004080040800408004080040
8020480039599000070425801001008000010080000500640000180020800398003969971669993801002008000820080008800398003911802011009910010080000100000011151174164480036800001008004080040800408004080040
8020480039599000070425801001008000010080000500640000180020800398003969971669993801002008000820080008800398003911802011009910010080000100000011151175173480036800001008004080040800408004080040
802048003959900003925801001008000010080000500640000180020800398003969971669993801002008000820080008800398003911802011009910010080000100000011151174164380036800001008004080040800408004080040
802048003960000003925801001008000010080000500640000180020800398003969971669993801002008000820080008800398003911802011009910010080000100000011151174162380036800001008004080040800408004080040
802048003960000003925801001008000010080000500640000180020800398003969971669993801002008000820080008800398003911802011009910010080000100000011151174163480036800001008004080040800408004080040
802048003959900003925801001008000010080000500640000180020800398003969971669993801002008000820080008800398003911802011009910010080000100000011151173163480036800001008004080040800408004080040
802048003960000003925801001008000010080000500640000180020800398003969971669993801002008000820080048800398003911802011009910010080000100000011151173164380036800001008004080040800408004080040
802048003959900003925801001008000010080000500640000180020800398003969971669993801002008000820080008800398003911802011009910010080000100000011151174164380036800001008004080040800408004080040
8020480039600001203925801001008000010080000500640000180020800398003969971669993801002008000820080008800398003911802011009910010080000100010311151173164480036800001008004080040800408004080040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 1.0005

retire (01)cycle (02)030b181e1f3f51inst 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)9fa1a6a8a9acc5cfd5d6daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002480040600004826450258001010800001080000506400000800208003980039699863700198001020800002080114800398003911800211091010800001000000050204160438003480000108004080040800408004080040
8002480039599000050258001010800001080000506400001800208003980039699863700198001020800002080000800398003911800211091010800001000003050204160438003480000108023880040800408004080040
8002480039599000050258001010800001080000506400001800208003980039699863700198001020800002080000800398003911800211091010800001000400050204160438003480000108004080040800408004080138
8002480039600000092258001010800001080000506400001800208003980039699863700198003620800002080000800398003911800211091010800001000000050204160348003480000108004080040800408004080040
8002480039599100050258001010800001080000506400001800208003980039699863700198001020800002080000800398003911800211091010800001000000050204160448003480000108004080040800408004080040
8002480039599000050258001010800001080026506400001800208003980039699863700198001020800002080000800398003911800211091010800001000000050203160448003480000108004080040800408004080040
8002480039600000050258001010800001080000506400001800208003980039699863700198001020801522080000800398003911800211091010800001000000050203160448003480000108004080040800408004080040
8002480039599000050258001010800001080000506400001800208003980039699863700198001020800002080000800398003911800211091010800001000000050204160348003480000108004080040800408004080040
8002480039599000050258001010800001080000506400001800208003980039699863700198001020800002080000800398003911800211091010800001000000050203160348003480000108004080040800408004080040
8002480039600000050258001010800001080000506400001800208003980039699863700198001020800002080000800398003911800211091010800001000000050204160348003480000108004080040800408004080040