Apple M1 Microarchitecture Research by Dougall Johnson

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

UCVTF (vector, fixed-point, 2D from 2D)

Test 1: uops

Code:

  ucvtf v0.2d, v0.2d, #3
  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
10043037231416125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112702100030383038303830383038
100430372496125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372336125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372406125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  ucvtf v0.2d, v0.2d, #3
  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)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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723300126129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000002471011611296330100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000080071011611296330100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000020671011611296330100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000080071011611296330100001003003830038300383003830038
10204300372330006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000300371011611296330100001003003830038300383003830038
10204300372320031032954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000060071011611296330100001003003830038300383003830038
10204300372330012612954725101001001000010010000500427716013001830037300372826432874510100204100002001000030037300371110201100991001001000010000090071011611296330100001003003830038300383003830038
10204300372330008929547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000606071013311296336100001003003830038300383003830038
1020430037233000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000060071011611296330100001003003830038300383003830038
1020430037232000135129529631015412610016136103006174279827130090300373003728264328745101002001016420010166300373003711102011009910010010000100000108171011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b1e3f4e51inst 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)9fa0a8acc2c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003723200089295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
100243003723300061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
100243003723300061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
100243003723300061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001001000640216222962910000103003830038300383003830038
100243003723300061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
1002430037232000536295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
100243003723300061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038
100243003724100061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001001273300640216222962910000103003830038300383003830038
100243003724200061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000020640216222962910000103003830086300383003830038
100243003723301061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  ucvtf v0.2d, v8.2d, #3
  ucvtf v1.2d, v8.2d, #3
  ucvtf v2.2d, v8.2d, #3
  ucvtf v3.2d, v8.2d, #3
  ucvtf v4.2d, v8.2d, #3
  ucvtf v5.2d, v8.2d, #3
  ucvtf v6.2d, v8.2d, #3
  ucvtf v7.2d, v8.2d, #3
  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)03080b191e1f3f51inst 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)9fa1a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006815500000442580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151181161120036800001002004020040200402004020040
802042003915500000732580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151181161120036800001002004020040200402004020040
802042003915500000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151181161120036800001002004020040200402004020040
802042003915500000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151181161120036800001002004020040200402004020040
80204200391560000030258010810080008100800205006401322002020039200399977699908012020080032200800322003920039218020110099100100800001007049024011151181161120036800001002004020040200402004020040
802042003915610000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151181161120036800001002004020040200402004020040
802042003915500000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151181161120036800001002004020040200402004020040
802042003915500000932580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151181161120036800001002004020040200402004020040
802042003915500000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151181161120036800001002004020040200402004020040
802042003915500000302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151181161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e3a3f51inst 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)9fa6a8a9acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0eaec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115500040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000630502051642200360080000102004020040200402004020040
800242003915500059925800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000000502041642200360080000102004020040200402004020040
80024200391560004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001001000502021642200360080000102004020040200402004020040
80024200391550004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000060502031652200360080000102004020040200402004020040
80024200391550004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000502041625200360080000102004020040200402004020040
80024200391560004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000000502041642200360080000102004020040200402004020040
800242003915500040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010029060502021642200360080000102004020040200402004020040
80024200391550004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001001000502051642200360080000102004020040200402004020040
8002420039155000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100004800502041634200360080000102004020040200402004020040
80024200391560004025800101080000108000050640000020020200392003999963100198001020800002080000200392009411800211091010800001001000502021624200360080000102004020040200402004020040