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, 4H)

Test 1: uops

Code:

  fcvtpu v0.4h, v0.4h
  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)03191e3f4e51inst 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
1004303723003772547251000100010003981603018303730372414328951000100010003037303711100110001073216112629100030383038303830383038
100430372400612547251000100010003981603018303730372414328951000100010003037303711100110000373116112629100030383038303830383038
100430372400612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
100430372400612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816030183037303724143289510001000100030373037111001100002473116112629100030383038303830383038
1004303724001032547251000100010003981603018303730372414328951000100010003037303711100110001373116112629100030383038303830383038
1004303723036125472510001000100039816030183037303724143289510001000100030373037111001100027073116112629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100010003037303711100110003073116112629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303724006125472510001000100039816030183037303724143289510001000100030373037111001100060373116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  fcvtpu v0.4h, v0.4h
  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)03080e1e3f4e51inst 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)696d6edispatch 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)9fa8a9acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225000612954725101001001001610010000500427716030018300373003728264328745101002001000020010000300373003711102011009910010010000100160007101161129633100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010070007101161129633100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010090007101161129633100001003003830038300383003830038
1020430037224000251295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010080007101161129633100001003003830038300383003830038
1020430037225100612954744101001001000010010000500427716030018300373003728271328745101002001000020010000300373003711102011009910010010000100450007101161129633100001003003830038300383003830038
10204300372330005962954725101001001000010010000500427716030162304173041828283372889011341228113232281066130037300371110201100991001001000010000007101161129633100001003003830038300383003830038
1020430037233011061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003723200061295472510143100100001001000050042771603001830037300372826432874510100200100002001016630037300371110201100991001001000010000007101161129633100001003003830038300383003830038
1020430037225000317295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010000007101161129633100001003003830038300383003830038
102043003722500061295472510100100100001001000050042771603001830037300372826432874510100200100002001000030037300371110201100991001001000010010007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03081e3f4e51inst 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)9fa8a9accfd0d2d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225006129547251001010100001010000504277160003001830037300372828632876710010201000020100003003730037111002110910101000010000640004163329629010000103003830038300383003830038
100243003722401236929547251001010100001010000504277160103001830037300372828632876710010201000020100003003730037111002110910101000010100640003163329629010000103003830038300383003830038
1002430037225006129547251001010100001010000504277160003001830037300372828632876710010201000020100003003730037111002110910101000010000640003163329629010000103003830038300383003830038
10024300372250010329547251001010100001010000504277160003001830037300372828632876710010201000020100003003730037111002110910101000010000640003163329629010000103003830038300383003830038
1002430037225008429547251001010100001010000504277160003001830037300372828632876710010201000020100003003730037111002110910101000010000640003163329629010000103003830038300383003830038
1002430037225006129547251001010100001010000504277160003001830037300372828632876710010201000020100003003730037111002110910101000010000640003163329629010000103008530038300383003830085
1002430037224106129547251001010100001010000504277160003001830037300372828632876710010201000020100003003730037111002110910101000010000640093163329629010000103003830038300383003830038
1002430037225006129547251001010100001010000504277160053001830037300372828632876710010201000020100003003730037111002110910101000010000640003163329629010000103003830038300383003830038
1002430037224006129547251001010100001010000504277160103001830037300372828632876710010201000020100003003730037111002110910101000010000640533163329629010000103003830038300383003830038
1002430037224006129547251001010100001010000504277160053001830037300372828632876710010201000020100003003730037111002110910101000010000640533163329629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  fcvtpu v0.4h, v8.4h
  fcvtpu v1.4h, v8.4h
  fcvtpu v2.4h, v8.4h
  fcvtpu v3.4h, v8.4h
  fcvtpu v4.4h, v8.4h
  fcvtpu v5.4h, v8.4h
  fcvtpu v6.4h, v8.4h
  fcvtpu v7.4h, v8.4h
  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)03070a1e3f51inst 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)72scheduler 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
80204200591501109325801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000011151182161120036800001002004020040200402004020040
80204200391501107225801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000011251181161120036800001002004020040200402004020040
80204200391501103025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000011151361161120036800001002004020040200402004020040
802042003915011026625801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
80204200391501103049801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001002011151181161120036800001002004020040200402004020040
8020420039150110113025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
80204200391501103025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
802042003915011013925801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
80204200391501105325801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000611151181161120036800001002004020040200402004020040
80204200391501103025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000011151181161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03090b1e3f51inst 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
800242005115000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020516542003680000102004020040200402004020040
800242003915000040258001010800001080000506400000200592003920039999631001980010208000020800002003920039118002110910108000010005020416342008780000102004020040200402004020040
800242003915500040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010105020416442003680000102004020040200402004020040
800242003915000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020516552003680000102004020040200402004020040
80024200391500019840258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020416442003680000102004020040200402004020040
800242003915000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020316532003680000102004020040200402004020040
800242003915000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020516532003680000102004020040200402004020040
800242010315000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020516442003680000102004020040200402004020040
800242003915000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020316442003680000102004020040200402004020040
800242003915000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020316332003680000102004020040200402004020040