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, 8B)

Test 1: uops

Code:

  sqabs v0.8b, v0.8b
  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)a1a6a7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000001073116112629100030383038303830383038
10043037220612547251000100010003981603018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
10043037220612547251000100010003981603018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000000373116112629100030383038303830383038
10043037220612547251000100010003981603018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000002073116112629100030383038303830383038
10043037240612547251000100010003981603018303730372414328951000100010003037303711100110000000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqabs v0.8b, v0.8b
  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)03081e3f4e51inst 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)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500822954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000073221611296330100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830086300383003830038
102043003722503612954725101001001000010010000500427716003001803003730037282643287451010020010000200106663003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037225106129511175102021481007215010900731428932803001803003730037282643287451010020010000200101643003730037211020110099100100100001000071011611296330100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830083
10204300372250216129547251010010010000100100005004277160030018030037300372826432874510100200100002001000030037300371110201100991001001000010058071011611296330100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716003001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307080b18191e1f3a3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000000612954725100101010000101000050427716003001830037300372828603287671001020100002010000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
100243003722500000000612954725100101010000101015050427716003001830037300372828603287671001020100002010000300373003711100211091010100001000000006403173329629010000103003830038300383003830038
100243003722500000000612954725100101010000101000050427716003001830037300372828603287671001020100002010000300373003721100211091010100001000000006403163329629010000103003830038300383003830038
100243003722500000000612954725100101010000101000050427716003001830037300372828603287671001020100002210000300373003711100211091010100001000002006403163329629210000103003830038300383003830084
100243003723300000000612954725100101010000101000050427716003001830037300372828603287671001020100002010000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
100243003722500000000612954725100101010000101000050427716003001830037300372828603287671001020100002010000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
100243003722400000000612954725100101010000101000050427716003001830037300372828603287671001020100002010000300373003711100211091010100001000200006403163329629010000103003830038300383003830038
100243003722500000000612954725100101010000101000050427716003001830037300372828603287671001020100002010000300373003711100211091010100001000000006403163329629010000103003830038300383003830038
100243003722500000000612954725100101010000101000050427716003001830037300372828603287671001020100002010000300373017911100211091010100001000000006403163329629010000103003830038300383003830038
100243003722500000000612954725100101110008121015050427716003001830037300372828603287671001020100002010000300373003711100211091010100001000000006403163329629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqabs v0.8b, v8.8b
  sqabs v1.8b, v8.8b
  sqabs v2.8b, v8.8b
  sqabs v3.8b, v8.8b
  sqabs v4.8b, v8.8b
  sqabs v5.8b, v8.8b
  sqabs v6.8b, v8.8b
  sqabs v7.8b, v8.8b
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)0309181e1f3f51inst 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)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006815000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
802042003915000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020093
802042003915001003025801081008000810080020500640940020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
802042003915000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020088
80204200391500000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001002135111511801600200360800001002004020040200402004020040
802042003915000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
802042003915000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
8020420039150000069525801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
802042003915000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
802042003915000005125801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040

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)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)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391500402580010108000010800005064000012002020039200399996310019800102080106208000020039200391180021109101080000100050201216101420098080000102004020040200402004020040
80024200391500822580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050201416141420036080000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005020916131020036080000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050201516121520036080000102004020040200402004020040
800242003915001032580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050201216141420036080000102004020040200402004020040
800242003915001032580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050201516121620036080000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050201716141420036080000102004020040200402004020040
800242003915001052580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050201316161520036080000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050201316141120036080000102004020040200402004020040
80024200391500402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050201116151220036080000102004020040200402004020040