Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTI (vector, 2D)

Test 1: uops

Code:

  frinti v0.2d, v0.2d
  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)03191e3f4e51inst 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
100430372300612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372303612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372400612547251000100010003981603018303730372414328951000100010003037303711100110000973116112629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406612547251000100010003981603018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372400612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100010003037303711100110000973116112629100030383038303830383038
100430372400612547251000100010003981603018303730372414328951000100010003037303711100110000373116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frinti v0.2d, v0.2d
  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)03181e3f4e51inst 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)9fa0a8a9acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372320018929547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003723301210329547251010010010000100100005004277160030018300863008428264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
1020430037233006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
10204300372330012529547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
10204300372330022929547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100010307101161129633100001003003830038300383003830038
1020430037232036129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100010007101161129633100001003003830038300383003830038
10204300372330010329547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
1020430037233006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003723201510329547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000307101161129633100001003003830038300383003830038
10204300372320014729547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b191e3f4e51inst 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)9fa1a8a9acc2c5cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003723300456129547251001010100001010000504277160030018300373003728286328786101612010000201000030037300371110021109101010000100003000640216222962910000103003830038300383003830038
10024300372330006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100103200640216222962910000103003830038300383003830038
10024300372330006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000640216222962910000103003830038300383003830038
10024300372320006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100100000640216222962910000103003830038300383003830038
100243003723301075929538251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100003000640216222962910000103003830084301313003830038
10024300372330006129547251001010100051010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100003000640216222962910000103003830038300383003830038
10024300372320006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000640216222962910000103003830038300383003830038
10024300372330008229547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000640216222962910000103003830038300383003830038
10024300372330006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000640216222962910000103003830038300383003830038
10024300372330006129547251001010100001010000504277160130018300373003728286328767100102010000201000030084300841110021109101010000100100200640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frinti v0.2d, v8.2d
  frinti v1.2d, v8.2d
  frinti v2.2d, v8.2d
  frinti v3.2d, v8.2d
  frinti v4.2d, v8.2d
  frinti v5.2d, v8.2d
  frinti v6.2d, v8.2d
  frinti v7.2d, v8.2d
  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)03181e1f3f51inst 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)9fa8acc5branch mispredict (cb)cdcfd5d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420060150000118125801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511851620036800001002004020040200402004020088
80204200391500003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040
802042003915015403025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040
80204200391500003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040
802042003915002703025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010003111511801620036800001002004020040200402004020040
80204200391500003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040
8020420039150048903025801081008000810080020500640132120020200392003999776999080120200800322008003220039201001180201100991001008000010000111511801620036800001002004020040200402004020040
80204200391500003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040
802042003915001203025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040
802042003915002403025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801620036800001002004020040200402004020040

1000 unrolls and 10 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)9fa0a1a6a7a8a9acc2cfd5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039156000001372580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000000050204165552003680000102004020040200402004020040
800242003915500000612580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000000050206160642003680000102004020040200402004020040
800242003915500000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000000050205162662003680000102004020040200402004020040
800242003915500000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000000050206160552003680000102004020040200402004020040
8002420039155000120402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000100050204160562003680000102004020040200402004020040
800242003915500000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000000050206160662003680000102004020040200402004020040
8002420039156000001392580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000000050205160552003680000102004020040200402004020040
8002420039155000004802580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000000050205160652003680000102004020040200402004020040
800242003915500000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100000000050205160562003680000102004020040200402004020040
800242003915600000612580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000000050206160652003680000102004020040200402004020040