Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTPU (scalar, H to H)

Test 1: uops

Code:

  fcvtpu h0, h0
  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)03181e1f3f4e51inst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303724000822547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037231088612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723000612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723000612547251000100010003981603018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
1004303723000612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724000612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724000612547251000100010003981603018303730372414328951000100010003037303711100110000073116122629100030383038303830383038
1004303723000612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230003712547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723000612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtpu h0, h0
  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)030b1e3f4e51inst 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)9fa7a8a9accfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037233006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
1020430037232006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
1020430037232096129547251010010010000100100005004277160130018300373003728264328745101002001018220010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
1020430037232006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
1020430037233006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100100071013211296330100001003003830038300383003830038
1020430037233106129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100002071011611296330100001003003830038300383003830038
1020430037233006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
1020430037233006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
1020430037233006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003723300151729547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100010071021611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2c5branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
10024300372260000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
10024300372240000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
10024300372250000006129538441001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
10024300372250000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000006403162229629010000103003830038300383003830038
10024300372250000006129529251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000006402162229629010000103003830038300383003830038
100243003722500000012429547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000000106403162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtpu h0, h8
  fcvtpu h1, h8
  fcvtpu h2, h8
  fcvtpu h3, h8
  fcvtpu h4, h8
  fcvtpu h5, h8
  fcvtpu h6, h8
  fcvtpu h7, h8
  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)03080b18191e1f3a3f51inst 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)9fa1a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420039161000000030258010810080109100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000000111511821645200360800001002004020040200402004020040
80204200391560000810072258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000000111511831623200360800001002004020040200402004020040
8020420039155000000030258010810080008100800205006401320200203200392003999776999080120200800322008003220039200391180201100991001008000010000000111511831643200360800001002004020040200402004020040
802042003915500004500030258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000000111511831643200360800001002004020040200402004020040
802042003915500002880030258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000000111511831633200360800001002004020040200402004020040
80204200391560000000529258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000000111511831633200360800001002004020040200402004020040
8020420039155000090030258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000000111511831632200360800001002004020040200402004020040
8020420039155000000030258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000000111511821642200360800001002004020040200402004020040
80204200391560000390030258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000000111511831632200360800001002004020040200402004020040
80204200391550000270030258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000000111511831632200360800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e3f51inst 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)9fa8accfd5d6dbddinst fetch restart (de)e0eaeb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005015609402580109108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005038316044200360080000102004020040200912009120040
80024200391551144402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020316044200360080000102004020040200402004020040
8002420039156004202580010108000010800005064000001200202003920039999631001980010208000020800002003920039118002110910108000010005020316153200360080000102004020040200402004020040
800242003915500402580010108000010800005064000010200202003920039999631001980010208000020800002003920039118002110910108000010035020316055200360080000102004020040200402004020040
800242003915600402580010108000010800005064000011200202003920039999631001980010208000020800002003920039118002110910108000010005020416044200360080000102004020040200402004020040
800242003915600402580010108000010800005064000000200202003920089999631001980010208000020800002003920039118002110910108000010005020416085200360080000102004020040200402004020040
800242003916100402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020416054200360080000102004020040200402004020040
8002420039156001352580010108000010800005064000001200202003920039999631001980010208000020800002003920039118002110910108000010005020316044200360080000102004020040200402004020040
800242003915500402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020416045200360080000102004020040200402004020040
800242003915500402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020516034200360080000102004020040200402004020040