Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTN (vector, 2S)

Test 1: uops

Code:

  frintn v0.2s, v0.2s
  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)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
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372301032547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037240612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037240612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037240612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintn v0.2s, 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): 3.0037

retire (01)cycle (02)0318191e1f3f4e51inst 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)93inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723300006129547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100990100100100001000000007101161129633100001003003830038300383003830038
1020430037233000061295472510100100100001001000050042771601300180300373003728264328745101002001000020010000300373003711102011009929100100100001000000007101161129633100001003003830038300383003830038
10204300372330047106129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100990100100100001000000007101161129633100001003003830038300383003830038
10204300372320054006129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100990100100100001000000007101161129633100001003003830038300383003830038
10204300372330043806129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100990100100100001000000027101161129633100001003003830038300383003830038
10204300372331039606129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100990100100100001000000007101161129633100001003003830038300383003830038
10204300372330011706129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100990100100100001000000007101161129633100001003003830038300383003830038
102043003723300210886129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300373110201100990100100100001000200007101161129633100001003003830038300383003830038
10204300372330011406129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100990100100100001000000007101161129633100001003003830038300383003830038
10204300372330025806129547251010010010000100100005004277160130018030037300372826432874510100200100002001000030037300371110201100990100100100001000000007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0304080b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2c5cfd5d6dbddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037233000000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000064031603329629010000103003830038300383003830038
1002430037225000000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000064031603329629010000103003830038300383003830038
1002430037225000006006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110022109101010000100000000064031603329629010000103003830038300383003830038
1002430037237000000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000064031603329920010000103003830038300383003830038
1002430037224000000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000064031603329629010000103003830038300383003830038
1002430037224000000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000064031603329629010000103003830038300383003830038
1002430037224000000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000064031603329629010000103003830038300383003830038
1002430037225000000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000064031603329629010000103003830038300383003830038
1002430037225000000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030071300371110021109101010000100000000072631603329629010000103003830038300383003830038
1002430037225000000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000064031603329629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frintn v0.2s, v8.2s
  frintn v1.2s, v8.2s
  frintn v2.2s, v8.2s
  frintn v3.2s, v8.2s
  frintn v4.2s, v8.2s
  frintn v5.2s, v8.2s
  frintn v6.2s, v8.2s
  frintn v7.2s, v8.2s
  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)030b18191e1f3f51inst 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)9fa0a6acc5branch mispredict (cb)cdcfd5d6dde0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042003916109109787041938137807091008060210280644511643400020235203512034610006521030880738202807332028086220247206098180201100991001008000010042011153036590202392800001002055620615205602061220663
8020420609165110117929681510258010893888001610080028500640196020020200392003999766999080120200800322008003220039200391180201100991001008000010000011151180160200360800001002004020040200402004020040
8020420039155000007226801161008001610080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160200360800001002004020040200402004020040
8020420039150000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160200360800001002004020040200402004020040
8020420039150000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160200360800001002004020040200402004020040
8020420039150000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160200360800001002004020040200402004020040
8020420039150000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160200360800001002004020040200402004020040
8020420039150000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160200360800001002004020040200402004020040
8020420039150000108052825801081008000810080020500640132120020200392003999876999080120200800322008003220039200391180201100991001008000010000011151180160200360800001002004020040200402004020040
80204200391550002403025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b1e1f3f51inst 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)9fa0a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391550000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000000503861634200360080000102004020040200402004020040
800242003915500270402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000000502071666200360080000102004020040200402004020040
80024200391550000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000000502061643200360080000102004020040200402004020040
80024200391550000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000000502041676200360080000102004020040200402004020040
80024200391550000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000000502061667200360080000102004020040200402004020040
800242003915600007052580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000000502031643200360080000102004020040200402004020040
8002420039155000013002580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000000502061645200360080000102004020040200402004020040
80024200391550000402580010108000010800005064000002002020039200399996310019800102080000208000020039202551180021109101080000100000000502041634200360080000102004020040200402004020040
80024200391550000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000000502041643200360080000102004020040200402004020040
80024200391550000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000030502041664200360080000102004020040200402004020040