Apple M1 Microarchitecture Research by Dougall Johnson

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

ABS (vector, 4S)

Test 1: uops

Code:

  abs v0.4s, v0.4s
  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
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000973216222629100030383038303830383038
100430372206125472510001000100039816003018303730372418328951000100010003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303722876125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110001073216222629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
10043037221236125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372406125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  abs v0.4s, v0.4s
  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)031e1f3f4e51inst 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)9fa8c2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500612954725101001001000010010000500427716030018300373003728264328745107262001000020010000300373003711102011009910010010000100007103161129633100001003003830038300383003830038
1020430037225120612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100107101161129633100001003003830038300383003830038
102043003722500612954725101001001002410010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225240612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225330612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372253306129547251010010010000100100005004277160300183003730037282641928745101002001000020010000300373003711102011009910010010000100007101161129704100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722560612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372251650612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722560612954725101001001000010010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038

1000 unrolls and 10 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)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? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000640416222962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010250640216222962910000103003830038300383003830038
1002430037225061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001010640216222962910000103003830038300383003830038
1002430037225084295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001010640216222962910000103003830038300383003830038
1002430037225094295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001020640216222962910000103003830038300383003830038
1002430037225061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001010640216222962910000103003830038300383003830038
1002430037225061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001010640216222962910000103003830038300383003830038
1002430037225061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001010640216222962910000103003830038300383003830038
1002430037225061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001010640216222962910000103003830038300383003830038
10024300372240612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010293640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  abs v0.4s, v8.4s
  abs v1.4s, v8.4s
  abs v2.4s, v8.4s
  abs v3.4s, v8.4s
  abs v4.4s, v8.4s
  abs v5.4s, v8.4s
  abs v6.4s, v8.4s
  abs v7.4s, v8.4s
  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)030708191e3f51inst 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)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200611500000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181160020036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001001011151180160020036800001002004020040200402004020040
8020420039150000038102580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001001011151180160020036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180170020036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
802042003915000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010018011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3f51inst 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)9fa8accdcfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001006050202416242220036080000102004020040200412004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000050202516252520036080000102004020040200412004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001016050202516242420036080000102004020040200522004020040
800242003915021822580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001003050202616152620036080000102004020040200522004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001006050202516252620036080000102004020040200412004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000050202716252520036080000102004020040200522004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001019050202416252420036080000102004020040200412004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000050202316262420036080000102004020040200412004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001000050202516202520036080000102004020040200412004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002080000200392003911800211091010800001016050202516152520036080000102004020040200522004020040