Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTZ (scalar, D)

Test 1: uops

Code:

  frintz d0, d0
  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)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372314461254725100010001000398160301830373037241432895100010001000303730371110011000073216112629100030383038303830383038
10043037234861254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372312061254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
10043037226661254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303722061254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303722661254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723061254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723061254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
100430372327661254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
10043037233361254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintz d0, d0
  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)0308193f4e51inst 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
102043003722400612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
102043003722400612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
1020430037225007262954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038
102043003722500612954725101001001000010010000500427716013001803003730037282643287451010020010000200100003003730037111020110099100100100001000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03090b18191e1f3f4e51inst 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)9fa6a7a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000120103295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000106640416432962910000103003830038300383003830038
10024300372250000120103295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000103640316342962910000103003830038300383003830038
1002430037225000012061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000103640316442962910000103003830038300383003830038
100243003722500000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000100640416342962910000103003830038300383003830038
1002430037225000000103295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000103640416432962910000103003830038300383003830038
100243003722500001201242954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010001018640416322962910000103003830038300383003830038
10024300372250000300810295472510010101001610100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000203661424542962910000103003830038300383003830038
1002430037225000000103295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000103640316342962910000103003830038300383003830038
100243003722500001830103295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000503640416342962910000103003830038300383003830038
10024300372240000120103295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000103640316432962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frintz d0, d8
  frintz d1, d8
  frintz d2, d8
  frintz d3, d8
  frintz d4, d8
  frintz d5, d8
  frintz d6, d8
  frintz d7, d8
  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)03080b181e3f51inst 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)9fa8a9acc5branch mispredict (cb)cdcfd5d6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581500009186258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100203111511811620036800001002004020040200402004020040
802042003915000012722580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000015111511801620036800001002004020040200402004020040
802042003915000003025801081008000810080020500640132120020200392003999776999080120200800322008003220039200391180201100991001008000010000177111511801620036800001002004020040200402004020040
8020420039150000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100106111511801620036800001002004020040200402004020040
8020420039150000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100303111511801620036800001002004020040200402004020040
8020420039150000030258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000111511801620036800001002009120040200402004020040
80204200391500001230258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000111511801620036800001002004020040200402004020091
802042003915000002012580108100800081008023250064013202002020039200399977699908012020080032200800322003920039118020110099100100800001006006111511801620036800001002004020040200402004020040
80204200391500000114258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000111511801620036800001002004020040200402004020040
80204200391500000302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000072111511801620036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3a3f51inst 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
800242005115048040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010135020131612122003680000102004020040200402004020040
800242003915012082258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020151616132003680000102004020040200402004020040
8002420039150120252258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010135020111613102003680000102004020040200402004020040
800242003915012040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010135020111612142003680000102004020040200402004020040
800242003915012088258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010135020161617142003680000102004020040200402004020040
800242003914912082258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010135020131612162003680000102004020040200402004020040
800242003915012082258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010105020101614112003680000102004020040200402004020040
800242003914912040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010035020131616132003680000102004020040200402004020040
800242003915012082258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010105045121616122003680000102004020040200402004020040
800242003915012040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010135020141615112003680000102004020040200402004020040