Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTZU (vector, integer, 4S)

Test 1: uops

Code:

  fcvtzu v0.4s, v0.4s
  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
1004303723099612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723012612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724006125472510001000100039816030183037303724143289510001000100030373037111001100011673116112629100030383038303830383038
100430372406612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723001032547251000100010003981603018303730372414328951000100010003037303711100110000073216112629100030383038303830383038
10043037230141612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724001032547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372400612547251000100010003981603018303730372413328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtzu v0.4s, v0.4s
  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)031e3a3f4e51inst 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)9fa6a8acc2c5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037233006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
1020430037233008229547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003723300113329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003022930038300383003830038
1020430037232006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
1020430037233006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
10204300372331206129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
10204300372320011729547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
10204300372416073129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300853003711102011009910010010000100200007101161129633100001003003830038300383003830038
1020430037232006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
1020430037232006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100003007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03070b1e3f4e51inst 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)9fa8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640416442962910000103003830038300383003830038
1002430037225000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640416442962910000103003830038300383008630038
1002430037225000612954725100101010000101000050427716003001830037300372828632878610010201000020100003003730037111002110910101000010000640416432962910000103003830038300383003830038
1002430037225000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000640316442962910000103003830038300383003830038
1002430037225000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000640416432962910000103003830038300383003830038
1002430037224000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640316442962910000103003830038300383003830038
1002430037225000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640416442962910000103003830038300383003830038
1002430037224000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640416432962910000103003830038300383003830038
10024300372250005362954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640316442962910000103003830038300383003830038
10024300372250007262954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640416442962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtzu v0.4s, v8.4s
  fcvtzu v1.4s, v8.4s
  fcvtzu v2.4s, v8.4s
  fcvtzu v3.4s, v8.4s
  fcvtzu v4.4s, v8.4s
  fcvtzu v5.4s, v8.4s
  fcvtzu v6.4s, v8.4s
  fcvtzu v7.4s, v8.4s
  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)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)9fa8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200391560302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181160020036800001002004020040200402004020040
802042003915503025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010001211151350160020036800001002004020040200402004020040
80204200391550302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039161390302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
80204200391550302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039155102302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151180160020036800001002004020040200402004020040

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)6061696d6edispatch 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)9fa6a8acc2cdcfd0d2d5d6d9dadbddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039155002132580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000005020003160001120036080000102004020040200402004020040
800242003915600402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000005020001160001120036080000102004020040200402004020040
800242003915500402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000005020001160001120036080000102004020040200402004020040
8002420039155002292580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000015020001160001120036080000102004020040200402004020040
8002420039156120402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000005020002160001120036080000102004020040200402004020040
800242003915500402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000005020001160001120036080000102004020040200402004020040
800242003915500402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000005020001160001120036080000102004020040200402004020040
800242003915600402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000005020001160001120036080000102004020040200402004020040
800242003915500402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000005020001160001120036080000102004020040200402004020040
8002420039155001052580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010000005020001160001120036080000102004020040200402004020040