Apple M1 Microarchitecture Research by Dougall Johnson

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

SQXTUN (H)

Test 1: uops

Code:

  sqxtun b0, h0
  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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303722061254725100010001000398160130183037303724143289510001000100030373037111001100008073116112629100030383038303830383038
1004303723082254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000973116112629100030383038303830383038
1004303722061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303722061254725100010001000398160130203084303724173289510001000100030373037111001100000073116112629100030383038303830383038
10043037220156254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqxtun b0, h0
  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)03081e1f3f4e51inst 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)9fa1a6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000612954725101001001000010010000500427716013001830037300372827162874110100200100082001000830037300371110201100991001001000010000001117170160029645100001003003830038300383003830038
102043003722500010772954725101001001000010010000500427716013001830037300372827162874010100200100082001000830037300371110201100991001001000010000001117170160029646100001003003830038300383003830038
10204300372330001722954725101001001000810010000500427716013001830037300372827162874110100200100082001000830037300371110202100991001001000010000001117180160129693100001003003830038300383003830038
1020430037225060822954725101001001000010010000500427716013001830037300372827172874110100200100082001000830037300371110201100991001001000010000001117170160029646100001003003830038300383003830038
10204300372250003352954725101001001000010010000500427716013001830037300372827162874010100200100082001000830037300371110201100991001001000010000000007101161129633100001003003830038300383003830038
10204300372250008102954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000007101161129633100001003003830038300383003830038
10204300372250001452954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000007101161129633100001003003830038300383003830038
10204300372250003962954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000007101161129633100001003003830038300383003830038
10204300372250009992954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000007101161129633100001003003830038300383003830038
102043003722500011392954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080a0b18191e1f3f4e51inst 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)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)9fa1a6a7a8acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000612954725100101010000101000050427716003001830037300372828603287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828603287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828603287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828603287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000612954725100481010000101000050427716013006030037300372828603287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828603287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828603287671001020100002010000300373003711100211091010100001000020006402162229629010000103003830038300383003830038
10024300372250000012014529547251001010100001010000504277160130018300373003728286032876710010201000020100003003730037111002110910101000010000556006402162229629010000103003830038300383003830038
100243003722500000006129547251001010100001010000504277160030018300373003728286032876710010201000020100003003730037111002110910101000010000489006402162229629010000103003830038300383003830038
100243003722500000006129547251001010100001010000504278512030018300373003728286032876710010201000020100003003730037111002110910101000010000403206402162229665010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqxtun b0, h8
  sqxtun b1, h8
  sqxtun b2, h8
  sqxtun b3, h8
  sqxtun b4, h8
  sqxtun b5, h8
  sqxtun b6, h8
  sqxtun b7, h8
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)03081e3f51inst 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)9fa0a1a6a8acc2c5branch mispredict (cb)cdcfd5d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200491501030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511811620036800001002004020040200402004020040
802042003915500695258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801620036800001002004020192200402004020040
80204200391500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801620036800001002004020040200402004020040
80204200391500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801620036800001002004020040200402004020040
80204200391500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000004111511801620036800001002004020040200402004020040
80204200391500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801620036800001002004020040200402004020040
802042003915000856258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801620036800001002004020040200402004020040
80204200391500053258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801620036800001002004020040200402004020040
80204200391500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100200000111511801620036800001002004020040200402004020040
80204200391500030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000000111511801620036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308191e3f51inst 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)9fa0a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050150000281258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100005020716352003680000102004020040200402004020040
8002420039150000124258001010800001080000506400002002020039200399996710019800102080000208010520115200991180021109101080000100005020516532003680000102004020040200402004020040
8002420039150000180258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100005020516532003680000102004020040200402004020040
800242003915000086258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100105020516532003680000102004020040200402004020040
8002420039150000515258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100005020316532003680000102004020040200402004020040
800242003915000040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100005020316532003680000102004020040200402004020040
800242003915000040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100005020316552003680000102004020040200402004020040
800242003915000040258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100105020516352003680000102004020040200402004020040
800242003915000061258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100005020316352003680000102004020040200402004020040
8002420039150000105258001010800001080000506400002002020039200399996310019800102080000208000020039200391180021109101080000100005020516532003680000102004020040200402004020040