Apple M1 Microarchitecture Research by Dougall Johnson

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

SQSHRUN (4S)

Test 1: uops

Code:

  sqshrun v0.4h, v0.4s, #3
  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
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303722032025472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110007073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqshrun v0.4h, v0.4s, #3
  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)03091e3f4e51inst 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)9fa8acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500128295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372250061295382510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003722500103295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010009007101161129633100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372250084295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
10204300372250061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03081e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225011702954725100101010000101000050427716003001830037300852828632876710010201000020100003003730037111002110910101000010006403161329629010000103003830038300383003830038
1002430037225001912954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
100243003722500822954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
1002430037225005532954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
10024300372250040842954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
100243007722500842954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
1002430037225002312954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
100243003722500842954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
100243003722500842954725100101010000101014850427716013001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010006403163329629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqshrun v0.4h, v8.4s, #3
  sqshrun v1.4h, v8.4s, #3
  sqshrun v2.4h, v8.4s, #3
  sqshrun v3.4h, v8.4s, #3
  sqshrun v4.4h, v8.4s, #3
  sqshrun v5.4h, v8.4s, #3
  sqshrun v6.4h, v8.4s, #3
  sqshrun v7.4h, v8.4s, #3
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)03181e3f51inst 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)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)9fa8c2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015000302580108100800081008002050064013212002002003920039997706999080120200800322008003220039200391180201100991001008000010000111511811611200360800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002002003920039997706999080120200800322008003220039200391180201100991001008000010000111511811612200360800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002002003920039997706999080120200800322008003220039200391180201100991001008000010000111511811622200360800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002002003920039997706999080120200800322008003220039200391180201100991001008000010000111511821614200360800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002002003920039997706999080120200800322008003220039200391180201100991001008000010000222512822331200450800001002004920049200492004920049
8020420049150006426801161008001610080028500640196020029020048200499976010998680128200800382008003820049200481180201100991001008000010000222512922323200450800001002004920049200492005020050
802042004815000642680116100800161008002850064019612002902004820048997609998680128200800382008003820048200481180201100991001008000010000222512932323200460800001002004920049200492004920049
802042004915000642680116100800161008002850064019612002902004820048997609998680128200800382008003820048200481180201100991001008000010000222512922334200450800001002004920049200502005020050
8020420048150006426801161008001610080028500640196120029020049200489976010998680128200800382008003820048200481180201100991001008000010000222512932311200450800001002005020049200492004920049
802042004915000642680116100800161008002850064019612002902004920048997609998680128200800382008003820049200491180201100991001008000010000222512922332200450800001002004920049200492004920049

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308090b18191e1f3f51inst 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)9fa0a1a6a7a8a9acc2cfd5d6daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004015100000004025800101080000108000050640000200200200392003999960310019800102080000208000020039200391180021109101080000100000000050204160552003680000102004020040200402004020040
800242003915000000004025800101080000108000050640000200200200392003999960310019800102080000208000020039200391180021109101080000100000000050201160722003680000102004020040200402004020040
800242003915000000004025800101080000108000050640000200200200392003999960310019800102080000208000020039200391180021109101080000100000000050202160532003680000102004020040200402004020040
800242003915000000004025800101080000108000050640000200200200392003999960310019800102080000208000020039200391180021109101080000100000000050201160322003680000102004020040200402004020040
800242003915000000004025800101080000108000050640000200200200392003999960310019800102080000208000020039200391180021109101080000100000000050201160422003680000102004020040200402004020040
800242003915000000004025800101080000108000050640000200200200392003999960310019800102080000208000020039200391180021109101080000100000000050202160632003680000102004020040200402004020040
800242003915000000004025800101080000108000050640000200200200392003999960310019800102080000208000020039200391180021109101080000100000000050201160362003680000102004020040200402004020040
800242003915000000004025800101080000108000050640000200200200392003999960310019800102080000208000020039200391180021109101080000100000000050202160332003680000102004020040200402004020040
800242003915000000304025800101080000108000050640000200203200392003999960310019800102080000208000020039200391180021109101080000100000100050202160252003680000102004020040200402004020040
800242003915000000004025800101080000108000050640000200200200392003999960310019800102080000208000020039200391180021109101080000100000000050201160362003680000102004020040200402004020040