Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTPS (vector, 2S)

Test 1: uops

Code:

  fcvtps v0.2s, v0.2s
  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)03081e3f4e51inst 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
100430372300612547251000100010003981603018303730372414328951000100010003037303711100110000073224222629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372310612547251000100010003981603018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372400612547251000100010003981603018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372400612547251000100010003981603018303730372414328951000100010003037303711100110001373216222629100030383038303830383038
1004303724024612547251000100010003981603018303730372414328951000100010003037303711100110000073116222629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372400612547251000100010003981603018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372400612547251000100010003981603018303730372414328951000100010003037303711100110000073216212629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtps v0.2s, v0.2s
  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)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)9fa0a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037233000012006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000033071011611296330100001003003830038300383003830038
102043003723300000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000042071011611297040100001003003830038300383003830038
102043003723300000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000048071011611296330100001003003830038300383003830038
10204300842330000000726295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000102071011611296330100001003003830038300383003830038
10204300372320000000612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000009071011611296330100001003003830038300383003830038
102043003723300000006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000039071011611296330100001003003830038300383003830038
102043003723300000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000063071011611296330100001003003830038300383003830038
102043003723300000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000093071011611296330100001003003830038300383003830038
1020430037233000000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000177071011611296330100001003003830038300383003830038
10204300372320000000612954725101001001000010010000500427716003001830037300372826432874510100200100002001000030037300371110201100991001001000010000000071011611296330100001003003830038300383003830038

1000 unrolls and 10 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)9fa8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003723306129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640316332962910000103003830038300383003830038
100243003723306129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000101000640316332962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640316332962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640316332962910000103003830038300383003830038
100243003723206129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640316332962910000103003830038300383003830038
1002430037225216129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640316332962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640316332962910000103003830038300383003830038
100243003722406129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000640316332962910000103039230038300383007530038
100243003722506129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100000640316332962910000103003830038300383003830038
100243003722506129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000101000640316332962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtps v0.2s, v8.2s
  fcvtps v1.2s, v8.2s
  fcvtps v2.2s, v8.2s
  fcvtps v3.2s, v8.2s
  fcvtps v4.2s, v8.2s
  fcvtps v5.2s, v8.2s
  fcvtps v6.2s, v8.2s
  fcvtps v7.2s, v8.2s
  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)03091e3f51inst 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)9fa0a7a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915600302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000022011151181160020036800001002004020040200402004020040
80204200391550030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391550030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391550330258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391550030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000311151180160020036800001002004020040200402004020040
802042003915500248258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
802042003915500302580108100800081008002050064013202002020039200399977610023801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391610030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000311151180160020036800001002004020040200402004020040
80204200391550030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100000011151180160020036800001002004020040200402004020040
80204200391560030258010810080008100800205006401320200202003920039997769990801202008003220080032200392003911802011009910010080000100200011151180160020036800001002004020040200402004020040

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)9fa6a8a9accfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039156061258001010800001080000506400001200202003920039999631001980010208000020800002003920039218002110910108000010080050201160112003680000102004020040200402004020040
80024200391550383258001010800001080000506400001200202003920039987431001980010208000020800002003920039118002110910108000010030050201160112003680000102004020040200402004020040
8002420039156040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010010050201160112003680000102004020040200402004020040
8002420039156040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000350201160112003680000102004020040200402004020040
8002420039155040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010020050201160112003680000102004020040200402004020040
8002420039155068258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050201160112003680000102004020040200402004020040
8002420039155040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000050201160112003680000102004020040200402004020040
8002420039155040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000650201160112003680000102004020040200402004020040
80024200391550308258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000050201160112003680000102004020040200402004020040
800242003915514440258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000050201160112003680000102004020040200402004020040