Apple M1 Microarchitecture Research by Dougall Johnson

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

SMAXV (vector, 8B)

Test 1: uops

Code:

  smaxv b0, v0.8b
  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)03191e3f4e51inst 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)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303722006125472510001000100039816003018303730372414328951000100020003037303711100110001073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038308430383038
1004303723008225472510001000100039816013018303730372414328951000100020003037303711100110000373116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303722006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100020003037303711100110001073116112629100030383038303830383038
1004303723006125472510001000100039816013018303730372414328951000100020003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  smaxv b0, v0.8b
  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)9fa6a8a9acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722533212295472510100100100001001000050042771600300183003730037282643287451010020010331204200003003730037111020110099100100100001002040071011611296338100001003003830038300383003830038
10204300372250994295472510100113100001001000050042771600300183003730037282643287631010020010000200200003003730037111020110099100100100001000025655071011611296330100001003003830038300383003830038
10204300372250124295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000100071011611296330100001003003830038300383003830038
102043003722512170295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300863003830038
1020430037225061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771601300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037224061295472510100100100001001000050042771600300183003730037282873287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020410000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038
1020430037225061295472510100100100001001000050042771600300183003730037282643287451010020010000200200003003730037111020110099100100100001000000071011611296330100001003003830038300383003830038

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)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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722501452954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000640216222967910000103003830038300383003830038
10024300372250612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372240612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722518612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372253612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372250612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000640216222962910000103003830038300383003830038
10024300372240612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  smaxv b0, v8.8b
  smaxv b1, v8.8b
  smaxv b2, v8.8b
  smaxv b3, v8.8b
  smaxv b4, v8.8b
  smaxv b5, v8.8b
  smaxv b6, v8.8b
  smaxv b7, v8.8b
  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)03191e1f3f51inst 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)9fa8acc2c5branch mispredict (cb)cdcfd5d6inst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200391510007225801081008000810080020500640976020020200392003999876999080120200800322001600642003920039118020110099100100800001000001115118116020036800001002004020040200402004020040
802042003915001203025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
802042003915000011425801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
80204200391500007225801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
80204200391500242647225801081008000810080020500643430020020200392003999776999080120200800322001600642003920039118020110099100100800001000001115118016020036800001002004020090200402004020040
8020420039150114403025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
80204200391500003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000001115118016020036800001002004020040200402004020094
80204200391500003025801081008000810080020500640132120020200392003999776999080120200800322001600642003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
80204200391500003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
80204200391500003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000001115118016020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0308191e1f3f51inst 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)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)9fa6a7a8a9accfd2d5d6dadbddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050150000017325800101080000108000050640000200202003920039999603100198001020800002016000020039200391180021109101080000102100050200616409820036080000102004020040200402004020040
80024200391500000402580010108000010800005064000020020200392003999960310019800102080000201600002003920039118002110910108000010000005020081600111120036080000102004020040200402004020040
800242003915000004025800101080000108000050640000200202003920039999603100198001020800002016000020039200391180021109101080000100007050200516008920036080000102004020040200402004020040
800242003915000004025800101080000108000050640000200202003920039999603100198001020800002016000020039200391180021109101080000100000350200616107820036080000102004020040200402004020040
8002420039150000040258001010800001080000506400002002020039200399996031001080010208000020160000200392003911800211091010800001000000502005162010820036080000102004020040200402004020040
800242003915000008425800101080000108000050640000200202003920039999603100198001020800002016000020039200391180021109101080000100000050200616107820036080000102004020040200402004020040
800242003915000121764025800101080000108000050640000200202003920039999673100198001020800002016000020039200391180021109101080000100000050200516009920036080000102004020040200402004020040
800242003915000004025800101080000108000050640000200202003920039999603100198001020800002016000020039200391180021109101080000100000050200716007920036080000102004020040200402004020040
800242003915000007052580010108000010800005064000020020200392003999960310019800102080000201600002003920039118002110910108000010000005020051600101120036080000102004020040200402004020040
8002420039150000040258001010800001080000506400002002020039200391001103100198001020800002016000020039200391180021109101080000100000050200616006720036080000102004020040200402004020040