Apple M1 Microarchitecture Research by Dougall Johnson

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

ABS (vector, 4H)

Test 1: uops

Code:

  abs 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)03070a3a3f4e51inst 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
100430372211268254725100010001000398160301830373037241432895100010001000303730371110011000077416442629100030383038303830383038
100430372311268254725100010001000398160301830373037241432895100010001000303730371110011000077416442629100030383038303830383038
100430372211268254725100010001000398160301830373037241432895100010001000303730371110011000077416442629100030383038303830383038
1004303723112182254725100010001000398160301830373037241432895100010001000303730371110011000077416442629100030383038303830383038
100430372311268254725100010001000398160301830373037241432895100010001000303730371110011000077416442629100030383038303830383038
100430372211268254725100010001000398160301830373037241432895100010001000303730371110011000077416442629100030383038303830383038
1004303722112110254725100010001000398160301830373037241432895100010001000303730371110011000177416442629100030383038303830383038
100430372211268254725100010001000398160301830373037241432895100010001000303730371110011000077416442629100030383038303830383038
100430372311268254725100010001000398160301830373037241432895100010001000303730371110011000077416442629100030383038303830383038
100430372311268254725100010001000398160301830373037241432895100010001000303730371110011000077416442629100030383038303830383038

Test 2: Latency 1->2

Code:

  abs 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)030b1e3f4e51inst 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
10204300372250081429547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160130018300373003728264328745101002001000020410000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037224006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373008311102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
1020430037225006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100007101161129633100001003003830038300383003830038

1000 unrolls and 10 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)696b6d6edispatch 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)9fa6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722501762954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722501662954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722502312954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722501262954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722501032954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372250822954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000640216222967510000103003830038300383003830038
10024300372250842954725100101010000101000050427716030018030037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  abs v0.4h, v8.4h
  abs v1.4h, v8.4h
  abs v2.4h, v8.4h
  abs v3.4h, v8.4h
  abs v4.4h, v8.4h
  abs v5.4h, v8.4h
  abs v6.4h, v8.4h
  abs 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): 0.2506

retire (01)cycle (02)0318191e3f51inst 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)9fa1a8c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915000015625801081008000810080020500640132120020200392003999770699908012020080032200800322003920039118020110099100100800001000011151180164020036800001002004020040200402004020040
80204200391500003025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000011151180162020036800001002004020040200402004020040
80204200391500003025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000011151180163020036800001002004020040200402004020040
80204200391500003025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000011151180164020036800001002004020040200402004020040
80204200391500003025801081008000810080020500640132020020200392003999770699908012020080032200800322003920039118020110099100100800001000011151180161520036800001002004020040200402004020040
802042003915000030258010810080008100800205006401960200292004820049997601099868012820080038200800382004820049118020110099100100800001000022251281234220045800001002004920049200502015320049
802042004915000037226801161008008410080028500640196120029200482004899760999868012820080038200800382004820049118020110099100100800001000022251281234120045800001002004920049200492004920049
8020420048150000108526801161008001610080028500640196120029200482004899760999868012820080038200800382004920048118020110099100100800001000022251281232120046800001002004920050200502005020049
8020420048150000729268011610080016100800285006401960200292004820048997601099868012820080038200800382004820048118020110099100100800001000022251291232120127800001002004920049200492004920050
802042004915000276426801161008001610080028500640196020029200482004999760999868012820080038200800382004820048118020110099100100800001000022251291234220045800001002005020050200502005020049

1000 unrolls and 10 iterations

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

retire (01)cycle (02)03081e1f3f51inst 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)9fa1a8acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915000082258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000005020316212003680000102004020040200402004020040
800242003915000040258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010000005020116112003680000102004020040200402004020040
800242003915000040258001010800001080000506400000200202003920039999631001980010208000020800992011220039118002110910108000010000005020116112003680000102004020040200402004020040
800242003915000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000005020116112003680000102004020040200402004020040
800242003915000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000005020116322003680000102004020040200402004020040
800242003915000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000005020216112003680000102004020040200402004020040
800242003915000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000005020116112003680000102004020040200402004020040
800242003915000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000005020116222003680000102004020040200402004020040
800242003915000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000005020116112003680000102004020040200402004020040
800242003915000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010000005020217112003680000102004020040200402004020040