Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINT64Z (vector, 2D)

Test 1: uops

Code:

  frint64z 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)03070a18191e3a3f4e51inst 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
10043037231100026825472510001000100039816013018303730372414328951000100010003037303711100110001077416442629100030383038303830383038
10043037231100026825472510001000100039816003018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
10043037231100026825472510001000100039816003018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
10043037231100026825472510001000100039816003018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
100430372311001226825472510001000100039816003018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
10043037241100026825472510001000100039816013018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
10043037241100026825472510001000100039816003018303730372414328951000100010003037303711100110000077416442657100030383038303830383038
10043037241100026825472510001000100039816003018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
10043037231100326825472510001000100039816003018303730372414328951000100010003037303711100110000077416442629100030383038303830383038
1004303723110012211025472510001000100039816003018303730372414328951000100010003037303711100110000077416442629100030383038303830383038

Test 2: Latency 1->2

Code:

  frint64z 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)0308090b1e1f3f4e51inst 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)9fa8acc9cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372330000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100083003730037111020110099100100100001000165071011611296330100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000153071011611296330100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000153071011611296330100001003003830038300383003830038
1020430037233000001084295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000132071011611296330100001003003830038300383003830038
102043003723300000251295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000150071011611296330100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771600300183008430037282643287451010020010000200100003003730037111020110099100100100001000153071011612296330100001003003830038300383003830038
1020430037241000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100021071011611296330100001003003830038300383003830038
1020430037234000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100021071011611296330100001003003830038300383003830038
1020430037233000008929547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100078071011611296330100001003003830038300383003830038
102043003723300000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010003071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03090b191e1f3f4e51inst 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)9fa1a6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771600300183003730037282866287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771601300183003730071282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250000061295472510010141000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000613003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frint64z v0.2d, v8.2d
  frint64z v1.2d, v8.2d
  frint64z v2.2d, v8.2d
  frint64z v3.2d, v8.2d
  frint64z v4.2d, v8.2d
  frint64z v5.2d, v8.2d
  frint64z v6.2d, v8.2d
  frint64z 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)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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042004915695825801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000111511811600200360800001002004020040200402004020040
8020420039156042825801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
802042003915503025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000111511801600200360800001002004020040200402004020040
8020420039155032826801161008001610080028500640196020029200482004999769998680128200800382008003820048200481180201100991001008000010000222512912311200460800001002005020049200492005020049
80204200491550190268011610080016100800285006401961200292004920048997610998680128200800382008003820048200481180201100991001008000010000222512812311200450800001002004920050200492005020049
8020420048155019626801161008001610080028500640196020029200482004999769998680128200800382008003820049200481180201100991001008000010000222512812311200460800001002004920050200492005020050
80204200481550190268011610080016100800285006401960200292004820048997610998680128200800382008003820048200481180201100991001008000010006222512812311200450800001002004920050200492004920049
802042007615506426801161008001610080028500640196020029200482004999769998680128200800382008003820048200481180201100991001008000010000222512812311200460800001002004920049200502004920049
8020420048155956626801161008001610080028500640196120029200492004999769998680128200800382008003820048200481180201100991001008000010000222512812311200450800001002005020049200502004920049
8020420049155039826801161008001610080028500640196120029200492004999769998680128200800382008003820049200481180201100991001008000010000222512812311200450800001002004920049200492005020049

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080a0b18191e1f3f51inst 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)5f60696d6edispatch 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)9fa0a1a6a8acc2c5cfd5d6ddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050196000000279040668001010800001080105506400000020020200392003999963100198001020800002080000200392003911800211091010800001000000005020916752003601780000102004020040200402004020040
8002420039155000000004025800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100000000502021634200360580000102004020040200402004020040
8002420039161000000004025800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100000000502021624200360080000102004020040200402004020040
8002420039155000000004025800101080000108000050640000012002020039200399996310019800102080105208000020039200391180021109101080000100000000502041646200360080000102004020040200402004020040
8002420039156000000004025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100000000502021644200360080000102004020040200402004020040
8002420039155000000004025800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100000000502061642200360080000102004020040200402004020040
80024200391610000000020825800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100000000502061653200360080000102004020040200402004020040
8002420039155000000004025800101080000108000050640000012002020039200399996310019800102080000208000020039200932180021109101080000100000040502041642200360080000102004020040200402004020040
80024200391550000000024225800101080097108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100000000502041663200360080000102004020040200402004020040
8002420039156000000004025800101080000108000050640000012002020039200399996310019800102080000208000020039200391180021109101080000100000000502041624200360080000102095820649212182004020040