Apple M1 Microarchitecture Research by Dougall Johnson

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

SQRSHRUN (D)

Test 1: uops

Code:

  sqrshrun s0, d0, #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)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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037220612547251000100010003981603018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
10043037220612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603054303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037220612547251000100010003981603018303730372414328951000100010003037303711100110003073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
10043037220612547251000100010003981603018303730372414328951000100010003037303711100110000373116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqrshrun s0, d0, #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)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)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)9fa8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250612954725101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826403287451010020010000200100003008430037111020110099100100100001000007101161129633100001003003830038300383003830038
102043003722502482954725101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
1020430037225367262954725101001001000010010000500427716013001830037300372826403287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
102043003722507462954725101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372259612954725101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
102043003722405362954725101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826403287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
102043003722407312954725101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716003001830037300372826403287451010020010000200100003003730037111020110099100100100001000007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)9fa6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000110629547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
100243003722500000008229547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
100243003722500000008229547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
1002430037225000000012429547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100020006402162229629010000103003830038300383003830038
1002430037225000000014529547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
100243003722500000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
1002430037225000000012629547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
100243003722500000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
1002430037225000000010329547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
100243003722500000008182954725100101010000101000061428392003023430367303642830029288921102320109872411147303213035631100211091010100001001141941047924894229883310000103032130404303663037130367

Test 3: throughput

Count: 8

Code:

  sqrshrun s0, d8, #3
  sqrshrun s1, d8, #3
  sqrshrun s2, d8, #3
  sqrshrun s3, d8, #3
  sqrshrun s4, d8, #3
  sqrshrun s5, d8, #3
  sqrshrun s6, d8, #3
  sqrshrun s7, d8, #3
  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)033f51inst 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)9fa0a8acc5branch mispredict (cb)cdcfd6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420049150114258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160020036800001002004020040200402004020040
802042003915051258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160020036800001002004020040200402004020040
802042003915030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160020036800001002004020040200402004020040
802042003915030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160020036800001002004020040200402004020040
802042003915030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160020036800001002004020040200402004020040
802042003915030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160020036800001002004020040200402004020040
80204200391503025801081008000810080020500640132200202003920039997769990801202008003220080032200392003911802011009910010080000100005331115118160020036800001002004020040200402004020040
802042003915030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160020036800001002004020040200402004020040
802042003915030258010810080088100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160020036800001002004020040200402004020040
802042003915030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030e181e1f3f51inst 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)9fa8accfd2d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150000088258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020010161372003680000102004020040200402004020040
800242003915000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502006166122003680000102004020040200402004020040
800242003915000120402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100050200816782003680000102004020040200402004020040
800242003915000001722580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050200916682003680000102004020040200402004020040
800242003915000004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000502008166122003680000102004020040200402004020040
80024200391500000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000101050200816682003680000102004020040200402004020040
800242003915000001282580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050200816862003680000102004020040200402004020040
800242003915000003702580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100050200616682003680000102004020040200402004020040
80024200391500000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050200616682003680000102004020040200402004020040
80024200391500000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100350200816862003680000102004020040200402004020040