Apple M1 Microarchitecture Research by Dougall Johnson

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

FCVTPU (vector, 4S)

Test 1: uops

Code:

  fcvtpu 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)03181e3f4e51inst 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)a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037230061254725100010001000398160030183037303724143289511501000100030373037111001100000073216112629100030383038303830383038
10043037230061254725100010001000398160030183037303724143289510001000100030373037111001100001373116112629100030383038303830383038
10043037240061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037240061254725100010001000398160130183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372300131254725100010001000398160030183037303724143289510001000100030373037211001100000073116112629100030383038303830383038
10043037230061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
100430372300103254744100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030383038303830383038
10043037230061254725100010001000398160030183037303724143289510001000100030373037111001100000073116112629100030863038303830383038

Test 2: Latency 1->2

Code:

  fcvtpu 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)9fa8a9accdcfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225906129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071001161129633100001003003830038300383003830038
102043003722446806129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071001161129633100001003003830038300383003830038
102043003722519506129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071001161129633100001003003830038300383003830038
102043003722562126129547251011510010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071001161129633100001003003830038300383003830038
102043003722515006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000071001161129633100001003003830038300383003830038
1020430037225456061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000024071001161129633100001003003830038300383003830038
10204300372251206129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100003071001161129633100001003003830038300383003830038
102043003722500295029547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071001161129633100001003003830038300383003830038
102043003722521010329547251010010410000129100005004278512030018300373003728264928745101002001000020010167300373003711102011009910010010000100022763071001161129633100001003003830038300383003830038
102043003722512010329547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071001161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03191e3f4e51inst 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)inst ldst (9b)9fa0a1a8accfd5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225007472954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000001000006402162329629010000103003830038300383003830038
1002430037225004032954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000001040006402162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000001000006402162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000001000006402162229629010000103003830038300383003830038
1002430037225001032954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000021000006402162229629010000103003830038300383003830038
1002430037225021612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000001000006402162229629010000103003830038300383003830038
100243003722500822954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000001004006402162229629010000103003830038300383003830038
1002430037224001032954725100101010000101000050427716013001830037300372828632876710010201000020100003013130133111002110910101000001000036402162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000001000006402162229629010000103003830038300383003830038
100243003722500612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000001000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtpu v0.4s, v8.4s
  fcvtpu v1.4s, v8.4s
  fcvtpu v2.4s, v8.4s
  fcvtpu v3.4s, v8.4s
  fcvtpu v4.4s, v8.4s
  fcvtpu v5.4s, v8.4s
  fcvtpu v6.4s, v8.4s
  fcvtpu 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)031e1f3f51inst 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)9fa7a8acc5branch mispredict (cb)cdcfd6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815000532580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013202002020039200399977699908023220080032200800322003920039118020110099100100800001000001115118160020036800001002004020040200402004020040
8020420039150902452580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013202002020039200899977699908012020080032200800322003920039118020110099100100800001000001115118160020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160020036800001002004020040200402004020040
80204200391502760302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160020036800001002004020040200402004020040
802042003915039176302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160020036800001002004020040200402004020040
802042003915031505602580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000031115118160020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000001115118160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b1e1f3f51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200391560035704025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100350207168172003680000102004020040200402004020040
800242003915500004025800101080000108000050640000112002020039200399996310019800102080000208000020039200391180021109101080000101050206166172003680000102004020040200402004020040
80024200391550015040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000502017168172003680000102004020040200402004020040
800242003915500420402580010108000010800005064000000200202003920039999631001980010208000020800002003920039118002110910108000010005020171617172003680000102004020040200402004020040
800242003915500004025800101080000108000050640000012007020039200399996310019800102080000208000020039200391180021109101080000100050207161462003680000102004020040200402004020040
80024200391550036040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000502017168172003680000102004020040200402004020040
80024200391550039040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000502017161762003680000102004020040200402004020040
800242003915500315040258001010800001080000506400000020020200392003999963100198001020800002080000200392003911800211091010800001000502017161782003680000102004020040200402004020040
8002420039155002104025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100050208167142003680000102004020040200402004020040
8002420039156003904025800101080000108000050640000002002020039200399996310019800102080000208000020039200391180021109101080000100050206167142003680000102004020040200402004020040