Apple M1 Microarchitecture Research by Dougall Johnson

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

SQABS (vector, 2D)

Test 1: uops

Code:

  sqabs 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)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
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000073216112629100030383038303830383038
1004303722126125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723156125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000673116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372336125472510001000100039816013018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
1004303723061254725100010001000398160130183037303724143289510001000100030373037111001100019673116112629100030383038303830383038
1004303722061254725100010001000398160130183037303724143289510001000100030373037111001100029973116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqabs 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)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)9fa0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225952212947515510212142100401451120068842879761303063041830466282862728892113442261132322011326304173046361102011009910010010000100630413945071011611296330100001003003830038300383003830038
10204300372240612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000000710116112963324100001003003830038300383003830038
10204300372250612954743101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000106271011611296330100001003003830038300383003830038
10204300372250612953825101001251000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071013311296330100001003003830038300863008630085
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
102043003722507262954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038
1020430037225121242954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030408090b18191e1f3a3f4e51inst 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)9fa0a1a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037224000000002133129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000644101651029629010000103003830038300383003830038
1002430037225000000002106029547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000644101610529629010000103003830038300383003830038
100243003722400000000291229547251001010100001210300504277160130018300373013328286328767100102010000201000030037300371110021109101010000100000000644101651029629010000103003830038300383003830038
100243003722500000000264529547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000644816101029629010000103003830038300383003830038
10024300372250000000021051295472510010101000010100005042771601300183003730037282863287671001020100002010000300373022711100211091010100001000000006441116101029629010000103003830038300383003830038
1002430037225000000002746295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006441016101029629010000103003830038300383003830226
100243003722500000000283929547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000644101610529629010000103003830038302273003830038
1002430037225000000002761295474410010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006441016101029629010000103003830038300383003830038
100243003722400000000285729547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000644101610529629010000103003830038300383003830038
1002430037225000000002853295472510010101000010100005042771601300183003730037282953287671001020100002010000300373003711100211091010100001000000006441116101029629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqabs v0.2d, v8.2d
  sqabs v1.2d, v8.2d
  sqabs v2.2d, v8.2d
  sqabs v3.2d, v8.2d
  sqabs v4.2d, v8.2d
  sqabs v5.2d, v8.2d
  sqabs v6.2d, v8.2d
  sqabs 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)03070a0b18191e1f3f51inst 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)9fa8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420039150110000011625801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151183161120036800001002004020040200402004020040
802042003915011000009325801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161220036800001002004020040200402004020040
802042003915011000007425801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
802042003915011000005325801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161220036800001002004020040200402004020040
8020420090150110001803025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161220036800001002004020040200402004020040
802042003915011000005125801081008000810080020500640132120020200392003999876999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
802042003915011000003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
8020420039150110000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100039011151181161120036800001002004020040200402004020040
802042003915011000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161120036800001002004020040200402004020040
802042003915011000009725801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181161220036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03091e3f51inst 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)9fa7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150204202580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020116132003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020116142003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020116122003680000102004020040200402004020040
800242003915000612580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020116112003680000102004020040200402019620040
800242003915006612580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020116142003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020116122003680000102004020040200402004020040
800252003915000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020116142003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020116122003680000102004020040200402004020040
800242003915000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020116152003680000102004020040200402004020040
800242003915000402580010128000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100005020116132003680000102004020040200402004020040