Apple M1 Microarchitecture Research by Dougall Johnson

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

FADDP (scalar, S)

Test 1: uops

Code:

  faddp s0, 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)03090b181e3f4e51inst 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
10043037230000612547251000100010003981603018303730372414328951000100020003037303711100110000073216332629100030383038303830383038
10043037230000612547251000100010003981603018303730372414328951000100020003037303711100110002073316332629100030383038303830383038
10043037220000612547251000100010003981603018303730372414328951000100020003037303711100110001373316332629100030383038303830383038
100430372300006125472510001000100039816030183037303724143289510001000200030373037111001100047073316332629100030383038303830383038
10043085230000612547251000100010003981603018303730372414328951000100020003037303711100110002073316332629100030383038303830383038
10043037220000612547251000100010003981603018303730372414328951000100020003037303711100110000073316332629100030383038303830383038
10043037230000612547251000100010003981603018303730372414328951000100020003037303711100110000073316332629100030383038303830383038
10043037220000612547251000100010003981603018303730372414328951000100020003037303711100110000073316332629100030383038303830383038
100430372300012612547251000100010003981603018303730372414328951000100020003037303711100110000073316332629100030383038303830383038
10043037220000842547251000100010003981603018303730372414328951000100020003037303711100110000073316332629100030383038303830383038

Test 2: Latency 1->2

Code:

  faddp s0, 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)03080918191e1f3a3f4e51inst 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)9fa0a1a8a9acc2c5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000006129547251010010010000100100005004277160130018300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
102043003722400000006129547251010010010000100100005004277160130018300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
1020430037225000000010329547251010010010000100100005004277160130018300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
102043003722501000006129547251010010010000100100005004277160130018300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
102043003722500000006129547251010010010000100100005004277160130018300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
102043003722400000006129547251010010010000100100005004277160130018300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
102043003722500000006129547251010010010000100100005004277160130018300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
102043003722500000006129547251010010010000100100005004277160130018300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
102043003722500000006129547251010010010000100100005004277160130018300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038
102043003722400000108053629547251010010010000100100005004277160130018300373003728264328745101002001000020020000300373003711102011009910010010000100000000071011611296330100001003003830038300383003830038

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)5e60696b6d6edispatch 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)9facc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225061295472510010101000010100005042771600130018030037300372828632876710010201000020200003003730037111002110910101000010006402162229629010000103003830038300383003830038
1002430037225061295472510010101000010100005042771600130018030037300372828632876710010201000020200003003730037111002110910101000010006402162229629010000103003830038300383003830038
1002430037225061295472510010101000010100005042771600130018030037300372828632876710010201000020200003003730037111002110910101000010306402162229629010000103003830038300383003830038
1002430037225061295472510010101000010100005042771600130018030037300372828632876710010201000020200003003730037111002110910101000010006402162229629010000103003830038300383003830038
1002430037225061295472510010101000010100005042771600130018030037300372828632876710010201000020200003003730037111002110910101000010006402162229629010000103003830038300383003830038
10024300372250147295472510010101000010100005042771600130018030037300372828632876710010201000020200003003730037111002110910101000010006402162229629010000103003830038300383003830038
1002430037225061295472510010101000010100005042771600130018030037300372828632876710010201000020200003003730037111002110910101000010006402162229629010000103003830038300383003830038
1002430037225061295472510010101000010100005042771600130018030037300372828632876710010201000020200003003730037111002110910101000010006402162229629010000103003830038300383003830038
1002430037225061295472510010101000010100005042771600130018030037300372828632876710010201000020200003003730037111002110910101000010006402162229629010000103003830038300383003830038
1002430037225061295472510010101000010100005042771600130018030037300372828632876710010201000020200003003730037111002110910101000010006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  faddp s0, v8.2s
  faddp s1, v8.2s
  faddp s2, v8.2s
  faddp s3, v8.2s
  faddp s4, v8.2s
  faddp s5, v8.2s
  faddp s6, v8.2s
  faddp s7, 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)03081e3f51inst 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)9fa0a6a8a9acc2c5branch mispredict (cb)cdcfd6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8020420058150003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000000210111511816020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013202002020039200399977699908012020080032200160064200392003911802011009910010080000100000000111511816020036800001002004020040200402004020040
8020420039150021302580108100800081008002050064013202002020039200399977699908012020080032200160064200392003911802011009910010080000100003000111511816020036800001002004020040200402004020040
802042003915000512580108100800081008002050064013202002020039200399977699908012020080032200160064200392003911802011009910010080000100000000111511816020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002020039200399977699908012020080032200160064200392003911802011009910010080000100000000111511816020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002020039200399977699908012020080032200160064200392003911802011009910010080000100000000111511816020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002020039200399977699908012020080032200160064200392003911802011009910010080000100000060111511816020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013202002020039200399977699908012020080032200160064200392003911802011009910010080000100001000111511816020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013212002020039200399977699908012020080032200160064200392003911802011009910010080000100000000111511816020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013202002020039200399977699908012020080032200160064200392003911802011009910010080000100000000111511816020036800001002004020040200402004020040

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)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)9fa1a6a8accdcfd5d6d9ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115000402580010108000010800005064000011200202003920039999631001980010208000020160000200392003911800211091010800001000000502051607620036080000102004020040200402004020040
800242003915000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000130502081606620036080000102004020040200402004020040
8002420039150007052580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000000502071606420036080000102004020040200402004020040
800242003915000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000000502041604320036080000102004020040200402004020040
800242003915000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000000502041603420036080000102004020040200402004020040
800242003915000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000000502061606620036080000102004020040200402004020040
800242003915000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000000502071604420036080000102004020040200402004020040
800242003915000402580010108000010800005064000001200202003920039999631001980010208000020160000200392003911800211091010800001000000502061606620036080000102004020040200402004020040
800242003915000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000000502041607620036080000102004020040200402004020040
800242003915000402580010108000010800005064000000200202003920039999631001980010208000020160000200392003911800211091010800001000000502071606720036080000102004020040200402004020040