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, 16B)

Test 1: uops

Code:

  sqneg v0.16b, v0.16b
  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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372333612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037220612547251000100010003981603018303730372414328951000100010003037303711100110001073116112629100030383038303830383038
10043037220612547251000100010003981603054303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723159612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037236612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037220612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
1004303723432612547251000100010003981603018303730372414328951000100010003037303711100110000973116112629100030383038303830383038
10043037230612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038
10043037226612547251000100010003981603018303730372414328951000100010003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqneg v0.16b, v0.16b
  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)9fa1a8accfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225072629547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100043371011611296332100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100051671011611296330100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100046071011611296330100001003003830038300383003830038
102043003722508229547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100045371011611296330100001003003830038300383003830038
10204300372240612954725101001001000010010600500427716013001830037300372826932874510100200100002001000030037300371110201100991001001000010000281671011611296330100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100046071011611296330100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100052371011611296330100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100045071011611296330100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160130018300373008428264328745101002001000020010000300373003711102011009910010010000100043071011611296330100001003003830038300383003830038
102043003722506129547251010010010000100100005004282226130018300373003728264728781101002001000020010000300373003711102011009910010010000100018371011611296330100001003003830038300383003830038

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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372240000000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000540606402162229629010000103003830038300383003830038
100243003722500000008229547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100002803606402162229629010000103003830038300383003830038
10024300372250000000726295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000306402162229629010000103003830038300383003830038
10024300372250000000156295472510010101000010100005542771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000004806402162229629010000103003830038300383003830038
10024300372250000000822954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000008106402162229629010000103003830038300383003830038
10024300372250000000612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000007806402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000000306402162229629010000103003830038300383003830038
1002430037225000000061295472510010101000010100006642771601300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000006129547251001010100001010000504277160130018300373003728286328767100102010000201000030037300371110021109101010000100000018306402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqneg v0.16b, v8.16b
  sqneg v1.16b, v8.16b
  sqneg v2.16b, v8.16b
  sqneg v3.16b, v8.16b
  sqneg v4.16b, v8.16b
  sqneg v5.16b, v8.16b
  sqneg v6.16b, v8.16b
  sqneg v7.16b, v8.16b
  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)0308090b18191e1f3f51inst 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)9fa0a6a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006815000000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151183161220036800001002004020040200402004020040
802042003915000000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151181161220036800001002004020040200402004020040
802042003915000000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151181162220036800001002004020040200402004020040
8020420039150000000030525801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151182162220036800001002004020040200402004020040
802042003915000000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151182162220036800001002004020040200402004020040
802042003915000000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000003011151182162220036800001002004020040200402004020040
802042003915000000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151182162220036800001002004020040200402004020040
802042003915000000003025801081008000810080020512640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151181161220036800001002004020040200402004020040
802042003915000000003025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000000011151182162220036800001002004020040200402004020040
8020420039150000000060025801081008000810080020500640132020020200392003999776999080120200800322008003220039200391180201100991001008000010000100011151181162220036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030b1e1f3f51inst 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
8002420051150100300258001010800001080000506400001200202003920039999631001980010208000020800002008820039118002110910108000010135020202917102007580000102004020040200402004020040
8002420039150008840258001010800001080000506400000200202003920039999631001980010208000020800002003920039118002110910108000010131415020171617172003680000102004020040200402004020040
8002420039150000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000103235020171617172003680000102004020040200402004020040
80024200391500004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502071617172003680000102004020040200402004020040
80024200391500004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502017166172003680000102004020040200402004020040
8002420039150000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100050205161662003680000102004020040200402004020040
8002420039150000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000100050206166172003680000102004020040200402004020040
8002420039150000402580010108000010800005064000002002020039200399996310019800102080000208000020039200391180021109101080000106965020161617172003680000102004020040200402004020040
80024200391500004025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211091010800001000502014167172003680000102004020040200402004020040
800242003915000040258001010800001080000506400001200202003920039999631001980010208000020800002003920039118002110910108000010303502017166172003680000102004020040200402004020040