Apple M1 Microarchitecture Research by Dougall Johnson

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

SQABS (scalar, D)

Test 1: uops

Code:

  sqabs d0, d0
  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)03071e1f3f4e51inst 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
1004303723030612547251000100010003981600301830373037241432895100010001000303730371110011000073216112629100030383038303830383038
1004303724000842547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303722000612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303722000612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
10043037220088612547251000100010003981601301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
10043037230001562547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723000612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
1004303723000612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038
10043037220006125472510001000100039816003018303730372414328951000100010003037303711100110003373116112629100030383038303830383038
1004303722000612547251000100010003981600301830373037241432895100010001000303730371110011000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqabs d0, d0
  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)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)9fa6a8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722503211032954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071021611296330100001003003830038300383003830038
102043003722511035612954725101001001000012610000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037225033612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037224018612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037225018612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722506612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
1020430037225099612952925101001001000010010148500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722506612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
102043003722606612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038
10204300372250489612954725101001001000010010000500427716013001830037300372826432874510100200100002001000030037300371110201100991001001000010000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0318191e1f3f4e51inst 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)9fbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225001290612954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100640216222962910000103003830038300383003830038
10024300372250000822954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100640216222962910000103003830038300383003830038
1002430037225000011052954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100640216222962910000103003830038300383003830038
100243003722500007552954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100640324232962910000103003830038300383003830038
1002430037226000010512954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100640216222962910000103003830038300383003830038
100243003722500010816682954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100640216222962910000103003830038300383003830038
1002430037225000060132954725100101010000101000050427716030018300373003728286328767103132010000201016130037300371110021109101010000100640216222962910000103003830038300383003830038
1002430037225000011032954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100640216222962910000103003830038300383003830038
1002430037225000012462954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100640216222962910000103003830038300383003830038
100243003722500002082954725100101010000101000050427716030018300373003728286328767100102010000201000030037300371110021109101010000100640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqabs d0, d8
  sqabs d1, d8
  sqabs d2, d8
  sqabs d3, d8
  sqabs d4, d8
  sqabs d5, d8
  sqabs d6, d8
  sqabs d7, d8
  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)03080a0b18191e1f3f51inst 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)79~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)9fa0a1a6a7a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005915000000003025801081008000810080020500640132120020200392003999776999080120020080032200800322003920039118020110099100100800001000000000011151182160020036800001002004020040200402004020040
802042003915000000003025801081008000810080020500640132120020200392003999776999080120020080032200800322003920039118020110099100100800001000000000011151180160020036800001002004020040200402004020040
8020420039149000000031525801081008000810080020500640132120020200392003999776999080120020080032200800322003920039118020110099100100800001000000103011151180160020036800001002004020040200402004020040
802042003915000100003025801081008000810080020500640132120020200392003999776999080120020080032200800322003920039118020110099100100800001000000000011151180160020087800001002004020040200402004020040
802042003915000000003025801081008000810080020500640132120020200392003999776999080120020080032200800322003920039118020110099100100800001000000000011151180160020036800001002004020040200402004020040
802042003915000000003025801081008000810080020500640132120020200392003999776999080120020080032200800322003920039118020110099100100800001000000000011151180160020036800001002004020040200402004020040
802042003915000000003025801081008000810080020500640132120020200392003999776999080120020080032200800322003920039118020110099100100800001000000000011151180160020036800001002004020040200402004020040
80204200391500000029705125801081008000810080020500640132120020200392003999776999080120020080032200800322003920039118020110099100100800001000000000011151180160020036800001002004020040200402004020040
802042003915000000003025801081008000810080020500640132120020200392003999776999080120020080032200800322003920039118020110099100100800001000000000011151180160020036800001002004020040200402004020040
802042003915000000003025801081008000810080020500640132120020200392003999776999080120020080032200800322003920039118020110099100100800001000000100011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030a0b1e3a3f51inst 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
8002420039150001380402580010108000010800005064000001200202003920039999631001980010208000020800002003920039118002110910108000010005020316442003680000102004020040200402004020040
800242003915000150402580010108000010800005064000001200202003920039999631001980010208000020800002003920039118002110910108000010005020316332003680000102004020040200402004020040
800242003915010480402580010108000010801075064000031200202003920039999631001980010208000020800002003920039118002110910108000010005020316442003680000102004020040200402004020040
80024200391600000402580010108000010800005064000031200202003920039999631001980010208000020800002003920039118002110910108000010005038516432003680000102004020040200402004020040
80024200391500000402580010108000010800005064000031200202003920039999631001980010208000020800002003920039118002110910108000010005020416442003680000102004020040200402004020040
80024200391501000402580010108000010800005064000031200202003920039999631001980010208000020800002003920039118002110910108000010005020516552003680000102004020040200402004020040
80024200391500000402580010108000010800005064000031200202003920039999631001980010208000020800002003920039118002110910108000010005037316532003680000102004020040200402004020040
80024200391500000402580010108000010800005064000031200202003920039999631001980010208000020800002003920039118002110910108000010005020716242003680000102004020040200402004020040
80024200391500000402580010108000010800005064000031200202003920039999631001980010208000020800002003920039118002110910108000010005020316442003680000102004020040200402004020040
80024200391500000402580010108000010800005064000031200202003920039999631001980010208000020800002003920039118002110910108000010005020516342003680000102004020040200402004020040