Apple M1 Microarchitecture Research by Dougall Johnson

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

SCVTF (scalar, integer, H from H)

Test 1: uops

Code:

  scvtf 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)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
1004303722012825472510001000100039816013018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
1004303723126125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723216125472510001000100039816003018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723126125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000373116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  scvtf 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)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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000012061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000103071011611296330100001003003830038300383003830038
10204300372250000120103295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000100071011611296330100001003003830038300383003830038
1020430037224000012061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
10204300372250000120726295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000000071011611296330100001003003830038300383003830038
1020430037225000030103295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000103071011611296330100001003003830038300383003830038
10204300372250000120103295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000003071011611296330100001003003830038300383003830038
10204300372250000120103295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000103071011611296330100001003003830038300383003830038
102043003722500000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000003071011611296330100001003003830038300383003830038
10204300372250000120103295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000103071011611296330100001003003830038300383003830038
10204300372250000120103295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000100071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst 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)9fa1a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722400000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006403162229629010000103003830038300383003830038
100243003722500000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
1002430037225000000072629547251001010100001010000504277160130054300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
100243003722500000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
100243003722500000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000101000006402162229629010000103008330038300383003830038
100243003722500000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
100243003722500000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000006402162229629010000103003830038300383003830038
100243003722500000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100010006402162229629010000103003830038300383003830038
100243003722500000006129547251001910100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000101000006402162229629010000103003830038300383003830038
1002430037225000001760405929484152100721610056131100492428662413023430368303202831434288801106320111572211147303213036971100211091010100001001101966807906164629881410000103036930368303693036830361

Test 3: throughput

Count: 8

Code:

  scvtf h0, h8
  scvtf h1, h8
  scvtf h2, h8
  scvtf h3, h8
  scvtf h4, h8
  scvtf h5, h8
  scvtf h6, h8
  scvtf 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)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)61696d6edispatch 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)9fa8acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150012221258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100130111511821600200360800001002004020040200402004020040
8020420039150012181258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100130111511801600200360800001002004020040200402004020040
8020420039150012346258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100130111511801600200360800001002004020040200402004020040
802042003915000179258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100100111511801600200360800001002004020040200402004020040
8020420039150012356258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100100111511801600200360800001002004020040200402004020040
8020420039150012271258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000111511801600200360800001002004020040200402004020040
802042003915001272258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100130111511801600200360800001002004020040200402004020040
8020420039150012307258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100130111511801600200360800001002004020040200402004020040
8020420039150012310258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100130111511801600200360800001002004020040200402004020040
8020420039150012135258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100130111511801600200360800001002004020040200402004020040

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)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511500712258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005020516442003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010805020316472003680000102004020040200402004020040
8002420039155040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010135020316432003680000102004020040200402004020040
8002420039150044302580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000101605020416642003680000102004020040200402004020040
8002420039150040258001010800001080000506400001200202003920039999671001980010208000020800002003920039118002110910108000010005020748742003680000102004020040200402004020040
800242003915012402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180022109101080000101125020416632003680000102004020040200402004020040
80024200391501240258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010165020716342003680000102004020040200402004020040
80024200391501282258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010235020716672003680000102004020040200402004020040
800242003915012557258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010235020416432003680000102004020040200402004020040
8002420039150061258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010135020716472003680000102004020040200402004020040