Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTMU (scalar, H to H)

Test 1: uops

Code:

  fcvtmu 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)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)91inst neon or fp (9a)a8accficache miss (d3)d5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037240105254725100010001000398160301830373037241432895100010001000303730371110010100000730316222629100030383038303830383038
10043037240103254725100010001000398160301830373037241432895100010001000303730371110010100000730216222629100030383038303830383038
1004303724061254725100010001000398160301830373037241432895100010001000303730371110010100000730216222629100030383038303830383038
1004303723061254725100010001000398160301830373037241432895100010001000303730371110010100000730216222629100030383038303830383038
1004303723082254725100010001000398160301830373037241432895100010001000303730371110010100000730216222629100030383038303830383038
1004303723061254725100010001000398160301830373037241432895100010001000303730371110010100003730216222629100030383038303830383038
1004303723061254725100010001000398160301830373037241432895100010001000303730371110010100000730216222629100030383038303830383038
10043037240260254725100010001000398160301830373037241432895100010001000303730371110010100010730216222629100030383038303830383038
1004303724061254725100010001000398160301830373037241432895100010001000303730371110010100000730216222629100030383038303830383038
1004303723061253825100010001000398160301830373037241432895100010001000303730371110010100000730216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtmu 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)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
102043003723306129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037233015629547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003723306129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003723306129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003723206129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003723306129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037233083329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003723206129547251010010010000100100005004278507130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003723206129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
102043003724106129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0304080b1e3f4e51inst 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)9fa8a9acc5cdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003723200001032954725100101010000101000050427716003001830037300842828632876710010201000020100003003730037111002110910101000010000006403162429629010000103003830038300383007130038
10024300372330000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000006403163429629010000103003830038300383003830038
10024300372330000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000006404163429683010000103003830038300383003830038
10024300372330000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000006404164429629010000103003830038300383003830038
100243003723300007262954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000006404164329629010000103003830038300383003830038
100243003723300001242954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000006404163429629010000103003830038300383003830038
10024300372320000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000006403163329629010000103003830038300383003830038
10024300372330000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000006403163429629010000103003830038300383003830038
10024300372330000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000006403163429629010000103003830038300383003830038
10024300372330000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000006404163329629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtmu h0, h8
  fcvtmu h1, h8
  fcvtmu h2, h8
  fcvtmu h3, h8
  fcvtmu h4, h8
  fcvtmu h5, h8
  fcvtmu h6, h8
  fcvtmu 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)03040b1e3a3f51inst 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)9fa0a8a9acc2c5branch mispredict (cb)cdcfd0d5d6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200581551000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180016020036800001002004020040200402004020040
80204200391550000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000003011151180016020036800001002009420040200402004020040
80204200391550000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180016020036800001002004020040200402004020040
802042003915500006952580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180016020036800001002004020040200402004020040
80204200391550012030258010810080112100800205006401320201092003920039997769990801202008003220080032200392003911802011009910010080000100200758011151180016020036800001002004020040200402004020040
80204200391550190302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180016020036800001002004020040200402004020040
80204200391550000722580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180016020036800001002004020040200402004020040
8020420039156000053625801081008000810080020500640132020020200392003999861699908012020080032200800322003920039118020110099100100800001000003211151180016020036800001002004020040200402004020040
80204200391550000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000003011151180016020036800001002004020040200402004020040
80204200391550030302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000011151180016020036800001002004020040200402004020040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)03080f1e3f51inst 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)9fa1accfd0d2d5d6d9ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242005115500040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020013160252003680000102004020040200402004020040
800242003915600040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005020003160322003680000102004020040200402004020040
800242003915500040258001010800001080000506400000200202003920039999671001980010208000020800002003920039118002110910108000010005020003160652003680000102004020040200402004020040
800242003915600040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020012162322003680000102004020040200402004020040
800242003915600940258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020006160322003680000102004020040200402004020040
800242003915500040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020003160232003680000102004020040200402004020040
800242003915500040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020005160332003680000102004020040200402004020040
800242003915500040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020003160342003680000102004020040200402004020040
800242003915500040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020003160232003680000102004020040200402004020040
800242003915500040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020006160332003680000102004020040200402004020040