Apple M1 Microarchitecture Research by Dougall Johnson

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

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

Test 1: uops

Code:

  scvtf 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)a8a9cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372308225472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110001273116112629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  scvtf 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)031e3f4e51inst 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
1020430037225936129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722536129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225156129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722536129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225336129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225336129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722566129547251010010010000100100005004277160130018300373003728282328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038

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)9fa1a6a7a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500003900612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000103006402162229629010000103003830038300383003830038
1002430037225000018001032954740100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000103006402162229629010000103003830038300383003830038
100243003722500003000612954725100101010000101000050427716003001830037300372828672876710010201000020100003003730037111002110910101000010000100006402242229629010000103003830038300383003830038
1002430037224000036001032954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000103006402162229629010000103003830038300383003830038
1002430037225000027001032954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000103006402162229629010000103003830038300383003830038
10024300372250000360040662948415810072131005614110507242866240301983032130367283162728921109162210979241113830367303568110021109101010000102002019373207894943629884010000103035630358303683032030369
100243037022711779486160523029475195100751710064161105082428662413001830085300372828632876710010201000020100003003730037111002110910101000010020128398207242653429848310000103027730320303223018030229
100243022722711652400216929547811001010100001110450504277160030018300373003728319422895410913221163422114733054730510121100211091010100001000012309482086921134330040210000103051130510305133037230510
10024305102281110313295281593729547251001010100001010000504277160030018300373003728286328767115223010978201081530180303224110021109101010000100311022355008784893330107310000103027630038301333003830181
10024300372350113131470880851029430244101291910112171195071429203203023430646300372833556288971136222114822211483305083051111110021109101010000100200036415006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  scvtf v0.2d, v8.2d, #3
  scvtf v1.2d, v8.2d, #3
  scvtf v2.2d, v8.2d, #3
  scvtf v3.2d, v8.2d, #3
  scvtf v4.2d, v8.2d, #3
  scvtf v5.2d, v8.2d, #3
  scvtf v6.2d, v8.2d, #3
  scvtf 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): 0.2505

retire (01)cycle (02)030818191e1f3f51inst 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)9fa0a6a8acc2c5branch mispredict (cb)cdcfd6inst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200391500002040542258010810080008100800205006401321200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118160200360800001002004020040200402004020040
80204200391500003030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118160200360800001002004020040200402004020040
802042003915000018030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118160200360800001002004020040200402004020040
802042003915000012030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118160200360800001002004020040200402004020040
80204200391500000030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118160200360800001002004020040200402004020040
802042003915000027030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118160200360800001002004020040200402004020040
802042003915000024030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118160200360800001002004020040200402004020040
802042003915000036030258010810080008100800205006401320200202003920039997769990801202008003220080032200892003911802011009910010080000100000001115118160200360800001002004020040200402004020040
802042003915000018030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118160200360800001002004020040200402004020040
802042003915000012030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000001115118160200360800001002004020040200402004020040

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)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)9fa0a6a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150036822580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100000350201116422003680000102004020040200402004020040
80024200391500082258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010001035020416422003680000102004020040200402004020040
800242003915001282258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000035020416422003680000102004020040200402004020040
800242003915001282258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000035020216242003680000102004020040200402004020040
800242003915001240258001010800001080000506400001200202003920039999631001980010208000020802042009120248118002110910108000010000005020216422003680000102004020040200402004020040
800242003915001882258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010001035020416422003680000102004020040200402004020040
800242003915002482258001010800001080000506400001200202011420039999631001980010208000020800002003920039118002110910108000010001065020416382003680000102004020040200402004020040
800242003915003982258001010800001080000506400001200202003920191999631001980010208000020800002003920039118002110910108000010000005020416242003680000102004020040200402004020040
80024200391500040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010001035020316442003680000102004020040200402004020040
80024200391550082258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010001235020736242003680000102004020040200402004020040