Apple M1 Microarchitecture Research by Dougall Johnson

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

SQNEG (vector, 8H)

Test 1: uops

Code:

  sqneg v0.8h, v0.8h
  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)033f4e51inst 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)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043085221272547251008100010003981600301830373037241432895100010001000303730371110011000073216222629100030383038303830383038
1004303722842547251000100010003981600301830373037241432895100010001000303730371110011000073216222629100030383038303830383038
1004303723612547251000100010003981601301830373037241432895100010001000303730371110011000073216222629100030383038303830383038
1004303723612547251000100010003981600301830373037241432895100010001000303730371110011000073216222629100030383038303830383038
1004303723612547251000100010003981600301830373037241432895100010001000303730371110011000073216222629100030383038303830383038
1004303723822547251000100010003981600301830373037241432895100010001000303730371110011000073216222629100030383038303830383038
1004303723822547251000100010003981600301830373037241432895100010001000303730371110011000073216222629100030383038303830383038
1004303723612547251000100010003981600301830373037241432895100010001000303730371110011000073216222629100030383038303830383038
10043037231072547251000100010003981600301830373037241432895100010001000303730371110011000073216222629100030383038303830383038
10043037231052547251000100010003981600301830373037241432895100010001000303730371110011000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqneg v0.8h, v0.8h
  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)9fa0a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372240612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722512612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000371011611296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300862826432874510100200101672061000030037300371110201100991001001000010040371011621296331100001003008630038300383008530038
102043003722507682954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830086
10204300372240612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372250612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037225010672954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3f4e51inst 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)9fa0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722500000120612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000000006402162229629010000103003830038300383003830038
100243003722500000120612950213410069141005617101507142866240302703036830372283132728895110642211143241113630319303708110021109101010000100000122198307892416529881310000103036630369303683022630368
10024303722280017710566164585294841521003914100561511050664286624030162303563037128309312889911064221122022113073037030381911002110910101000010000000006822162229845310000103032430357303223036730369

Test 3: throughput

Count: 8

Code:

  sqneg v0.8h, v8.8h
  sqneg v1.8h, v8.8h
  sqneg v2.8h, v8.8h
  sqneg v3.8h, v8.8h
  sqneg v4.8h, v8.8h
  sqneg v5.8h, v8.8h
  sqneg v6.8h, v8.8h
  sqneg v7.8h, v8.8h
  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)cdcfd6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015015302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000311151181620036800001002004020040200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
80204200391503302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
8020420039150241142580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
80204200391500302580108100800081008002050064072412002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03080b18191e3f51inst 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)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150000046240798010610800001080000506400001200202003920039998931001280010208000020800002003920039118002110910108000010220005020116112003680000102004020040200402004020040
80024200391500035040258001010800001080000506400000200202003920039998931001280010208000020800002003920039118002110910108000010000005020116112003680000102004020040200402004020040
80024200391500000040258001010800001080000506400001200202003920039998931001280010208000020800002003920039118002110910108000010000005020116112003680000102004020040200402004020040
80024200391500000040258001010800001080000506400001200202003920039998931001280010208000020800002003920039118002110910108000010000005020116112003680000102004020040200402004020040
80024200391500000640258001010800001080000506400001200202003920039998931001280010208000020800002003920039118002110910108000010000005020116112003680000102004020040200402004020040
80024200391500000040258001010800001080000506400001200202003920039998931001280010208000020800002003920039118002110910108000010000005020116112003680000102004020040200402004020040
80024200391500000040258001010800001080000506400001200202003920039998931001280010208000020800002003920039118002110910108000010000005020116112003680000102004020040200402004020040
80024200391500000040258001010800001080000506400000200202003920039998931001280010208000020800002003920039118002110910108000010000005020116112003680000102004020040200402004020040
80024200391500000040258001010800001080000506400001200202003920039998931001280010208000020800002003920039118002110910108000010000005020116112003680000102004020040200402004020040
80024200391500000040258001010800001080000506400000200202003920039998931001280010208000020800002003920039118002110910108000010000005020116112003680000102004020040200402004020040