Apple M1 Microarchitecture Research by Dougall Johnson

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

FRINTP (vector, 4S)

Test 1: uops

Code:

  frintp v0.4s, v0.4s
  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)0307080a0b18191e1f3f4e51inst 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)a0a1a6a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303724000000006125472510001000100039816003018303730372414328951000100010003037303711100110000000000073216222629100030383038303830383038
1004303724000000006125472510001000100039816003018303730372414328951000100010003037303711100110000000000073216222629100030383038303830383038
10043037230000000014425472510001000100039816003018303730372414328951000100010003037303711100110000000100073216222629100030383038303830383038
1004303723000000006125472510001000100039816003018303730372414328951000100010003037303711100110000000000073216222629100030383038303830383038
1004303723000000006125472510001000100039816003018303730372414328951000100010003037303711100110000000000073216222629100030383038303830383038
10043037240000000015125472510001000100039816003018303730372414328951000100010003037303711100110000000103073216222629100030383038303830383038
10043037230000001806125472510001000100039816003018303730372414328951000100010003037303711100110000000000073216222629100030383038303830383038
10043037240000000010325472510001000100039816003018303730372414328951000100010003037303711100110000000000073216222629100030383038303830383038
10043037230000000022025472510001000100039816003018303730372414328951000100010003037303711100110000000000073216222629100030383038303830383038
1004303724000000006125472510001000100039816003018303730372414328951000100010003037303711100110000000000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  frintp v0.4s, v0.4s
  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)030b18191e1f3f4e51inst 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)9fa0a1a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037233000006129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
10204300372331224588149729547251013210010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000289307101161129633100001003003830038300383003830038
10204300372320000010329547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100001007101161129633100001003003830038300383003830038
1020430037233000006129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
10204300372330009006129547251010010010000100100006494277160130018300373003728264328745101002001000021210000300373003711102011009910010010000100001007101161129633100001003003830038300383003830038
10204300372320008406129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
10204300372330000061295472510100100100001001000050042771600300183003730037282642328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003723200031806129547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000307321161129633100001003003830038300383003830038
10204300372320000022329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038
102043003723300090010329547251010010010000100100005004277160130018300373003728264328745101002001000020010000300373003711102011009910010010000100000007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03181e3f4e51inst 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)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003723300612954725100101010000101000050427716003001830037300372828632876710010201000020106543003730037111002110910101000010006640216222962910000103003830038300383003830038
100243003722500612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010009640216222962910000103003830038300383003830038
10024300372240017629547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100030640216222962910000103003830038300383003830038
100243003722500612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722500612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722500612954725100101010000101000050427716013001830037300372828632876710010201000020101623003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722500612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722500612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722500612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038
100243003722500612954725100101010000101000050427716013001830037300372828632876710010201000020100003003730037111002110910101000010000640216222962910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frintp v0.4s, v8.4s
  frintp v1.4s, v8.4s
  frintp v2.4s, v8.4s
  frintp v3.4s, v8.4s
  frintp v4.4s, v8.4s
  frintp v5.4s, v8.4s
  frintp v6.4s, v8.4s
  frintp v7.4s, v8.4s
  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)03081e3f51inst 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)9fa0acc2c5branch mispredict (cb)cdcfd6e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042006815509302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181620036800001002004020040200402004020040
8020420039155027302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181620036800001002004020040200402004020040
802042003915500582580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181620036800001002004020040200402004020040
802042003915600302580108100800081008002050064013220020200392003999779999080120200800322008003220039200391180201100991001008000010000011151181620036800001002004020040200402004020040
802042003915500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181620036800001002004020040200402004020040
802042003915500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181620036800001002004020040200402004020040
802042003915500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181620036800001002004020040200402004020040
80204200391550165582580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181620036800001002008820040200402004020040
802042003915500302580108100800081008002050064013220020200392003999866999080120200800322008003220039200391180201100991001008000010003011151181620036800001002004020040200402004020040
802042003915500302580108100800081008002050064013220020200392003999776999080120200800322008003220039200391180201100991001008000010000011151181620036800001002004020040200402004020040

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)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)91inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa7a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511561714025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211090101080000100105020516252003680000102004020040200402004020040
800242003915534025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211090101080000100005020216242003680000102004020040200402004020040
800242003915564025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211090101080000100005020216522003680000102004020040200402004020040
8002420039155306825800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211090101080000100005020216242003680000102004020040200402004020040
800242003915664025800101080000108000050640000120020200392003999963100198001020800002080000200392003911800211090101080000100005020416452003680000102004020040200402004020040
800242003915604025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211090101080000100005020216422003680000102004020040200402004020040
800242003915564025800101080000108000050640820020020200392003999963100198001020800002080000200392003911800211090101080000100005020440452003680000102004020040200402004020040
8002420039156154025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211090101080000100005020216522003680000102004020040200402004020040
800242003915504025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211090101080000100005020416422003680000102004020040200402004020040
8002420039155334025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211090101080000100005020416442003680000102004020040200402004020040