Apple M1 Microarchitecture Research by Dougall Johnson

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

SMINV (vector, 4H)

Test 1: uops

Code:

  sminv h0, 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)031e1f3f4e51inst 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
100430372300612547251000100010003981603018303730372414328951000100020003037303711100110000973116112629100030383038303830383038
100430372200612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
1004303723120612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372200612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372200612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038
100430372200612547251000100010003981603018303730372414328951000100020003037303711100110000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  sminv h0, 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)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)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)9fa8accdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722506129547251010010010000100100005004277160300183003730037282643287451010020010000200200003003730037111020110099100100100001007007101161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160300183003730037282643287451010020010000200200003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160300183003730037282643287451010020010000200200003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160300183003730037282643287451010020010000200200003003730037111020110099100100100001003007101161129633100001003003830038300383003830038
10204300372250124295472510100100100001001000050042771603001830037300372826432874510100200100002002000030037300371110201100991001001000010046607101161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160300183003730037282643287451010020010000200200003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160300183003730037282643287451010020010000200200003003730037111020110099100100100001005007101161129633100001003003830038300383003830038
102043003722406129547251010010010000100100005004277160300183003730037282643287451010020010000200200003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160300183003730037282643287451010020010000200200003003730037111020110099100100100001000007101161129633100001003003830038300383003830038
102043003722506129547251010010010000100100005004277160300183003730037282643287451010020010000200200003003730037111020110099100100100001003017102161129633100001003003830038300383003830038

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)9fa7a8acc2c5cfd5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372240612954725100101010000101014850427716003001830037300372828632876710010201000020200003003730037111002110910101000010000006402162229629010000103003830038300383003830038
10024300372240612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000006402162229629210000103003830038300383003830038
10024300372250612954725100101010000101014850427716003001830037300372828632876710010201018020200003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722472612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000006402162329629010000103003830038300383003830038
10024300372250612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000006402162329629010000103003830038300383003830038
10024300372240842954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000006402162229629010000103003830038300383003830038
100243003722501702954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000006402162329629010000103003830038300383003830038
100243003722501912954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000006402162229629010000103003830038300383003830038
10024300372240612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000006402162329629010000103003830038300383003830038
100243003722502322954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000006402162329629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sminv h0, v8.4h
  sminv h1, v8.4h
  sminv h2, v8.4h
  sminv h3, v8.4h
  sminv h4, v8.4h
  sminv h5, v8.4h
  sminv h6, v8.4h
  sminv h7, v8.4h
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)03070a191e3f51inst 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)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815000005125801081008000810080020500640132120020200392003999776999080120200800322001600642003920039118020110099100100800001000011151181161220036800001002004020040200402004020040
802042003915011003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920064118020110099100100800001000011151181161120036800001002004020040200402004020040
8020420039150110022925801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
802042003915011003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920088118020110099100100800001000011151181161220036800001002004020040200402004020040
8020420039150110020225801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
8020420039150110054125801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
802042003915011009325801081008000810080020500640132020020200392003999776999080120200801402001600642003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
80204200391501100121025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
802042003915011003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151181161120036800001002004020040200402004020040
802042003915011003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151181161120036800001002004020040200402004020040

1000 unrolls and 10 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)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)9fa8acbranch mispredict (cb)cfd0d5d6daddinst fetch restart (de)e0ec? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004015006432580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100005020041604420036080000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100005020021602620036080000102004020040200402004020040
8002420039150012425800101080000108000050640000200202003920039999631001980010208000020160214200392003911800211091010800001010050200416041120036080000102004020040200402004020040
800242003915004025800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001080050200416041420036080000102004020040200402004020040
800242003915004025800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000050200216041420036080000102004020040200402004020040
80024200391500402580010108000010800005064000020020200392003999963100198001020800002016000020039200391180021109101080000100005020041602420036080000102004020040200402004020040
800242003915004025800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000050200416021320036080000102004020040200402004020040
8002420039150016625800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000050200316021320036080000102004020040200402004020040
800242003915004025800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000050200416041820036080000102004020040200402004020040
800242003915004625800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000050200416021520036080000102004020040200402004020040