Apple M1 Microarchitecture Research by Dougall Johnson

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

SQABS (vector, 4S)

Test 1: uops

Code:

  sqabs 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)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)inst neon or fp (9a)a8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723061254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303722061254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723061254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
10043037220124254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723061254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723061254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303722061254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723061254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723061254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303722661254725100010001000398160301830373037241432895100010001000303730371110011000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqabs 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)030818191e1f3f4e51inst 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
1020430037224000306129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372250002706129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102021009910010010000100007101161129633100001003003830038300383003830038
1020430037225000006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225000006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225000006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373008411102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225000006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3a3f4e51inst 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)9fa0a1a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500002100612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006404163329629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006403163329629010000103003830038300383003830038
10024300372250000600612954725100101010000101000050427716003001830037300372830232876710010201000020100003003730037111002110910101000010000006403163329629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006403163329629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006403163329629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006403163329629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006403163329698010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830037300372829032876710010201000020100003003730037111002110910101000010000006403163329629010000103003830038300383003830038
100243003722500001200612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010000006403163329629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716003001830082300372828632876710010201000020100003003730037111002110910101000010000006403163329629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqabs v0.4s, v8.4s
  sqabs v1.4s, v8.4s
  sqabs v2.4s, v8.4s
  sqabs v3.4s, v8.4s
  sqabs v4.4s, v8.4s
  sqabs v5.4s, v8.4s
  sqabs v6.4s, v8.4s
  sqabs 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)cdcfd6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006015051302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
80204200391500302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
80204200391500512580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001001011151181620036800001002004020040200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
80204200391500302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
80204200391500302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
80204200391500302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040
802042003915033302580108100800081008002050064013212002020039200399977699908012020080032200800322003920039118020110099100100800001000011151181620036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308091e3f51inst 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)9fa6accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050150000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050201016582003680000102004020040200402004020040
800242003915000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005020616592003680000102004020040200402004020040
8002420039150000402580090108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050201016992003680000102004020040200402004020040
8002420039150000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100050208161552003680000102004020040200402004020040
8002420039150020402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000101050207161282003680000102004020040200402004020040
800242003915000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010005020716752003680000102004020040200402004020040
8002420039150000402580010108000010800005064000012002020039200399996310019800102080000208000020039200391180021109101080000100050207161052003680000102004020040200402004020040
8002420039150000402580010108000010800005064000012002020039200399996310019800102080000208000020039200891180021109101080000100650205166102003680000102004020040200402004020040
800242003915000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010005020616842003680000102004020040200402004020040
800242003915000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010035020716862003680000102004020040200402004020040