Apple M1 Microarchitecture Research by Dougall Johnson

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

UCVTF (vector, fixed-point, 4H from 4H)

Test 1: uops

Code:

  ucvtf v0.4h, v0.4h, #3
  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)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
100430372309612547251000100010003981603018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372400612547251000100010003981603018303730372414328951000100010003037303711100110001073216122629100030383038303830383038
1004303724096125472510001000100039816030223037303724143289510001000100030373037111001100001273216222664100030383038303830743038
100430372400612547251008100010003981603018303730372414328951000100011623037303711100110000073216222629100030383038303830383038
1004303726001032547251000100010003981603018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372300612547251000100010003981603018303730372414328951000100010003037303711100110000373216222629100030383038303830383038
100430372406612547251000100010003981603018303730372414328951000100010003037303711100110001073216222629100030383038303830383038
1004303723006125472510001000100039816030183037303724143289510001000100030373037111001100004873216212629100030383038303830383038
100430372400612547251000100010003981603018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372400612547251000100010003981603018303730372414328951000100010003037303711100110000073116222629100030383038303830383038

Test 2: Latency 1->2

Code:

  ucvtf v0.4h, v0.4h, #3
  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)9fa1a8acc5cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003723306129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003723206129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
1020430037233061295472510100100100001001000050042771600300183003730037282641028745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003723306129547251010012810000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100010071011611296330100001003003830038300383003830038
102043003723306129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
102043003723308429547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100010071011611296330100001003003830038300383003830038
1020430037233024329547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100009071011611296330100001003003830038300383003830038
102043003723306129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038
1020430037233044129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100010071011611296330100001003003830038300383003830038
102043003723306129547251010010010000100100005004277160030018300373003728264328745101002001000020010000300373003711102011009910010010000100000071011611296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030918191e1f3f4e51inst 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)9fa7a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372240000061295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001000306402162229629010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000306402162229629010000103003830038300383003830038
10024300372240000084295472510010101000010100006042771601300183008430037282863287671001020100002010000300373003711100211091010100001014006402162229629010000103003830038300383003830038
10024300372250000061295472510010111000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
10024300372330000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000006402162229629010000103003830038300383003830038
100243003722500000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010075306402162229629010000103003830038300383003830038
1002430037225000006129547251001010100001010000504277160030018300373003728286328767100102010000201000030037300371110021109101010000100018006402162229629010000103003830038300383003830038
10024300372250000061295472510010101000010100005042771601300183003730037282866287671001020100002010000300373003711100211091010100001000306402162229629010000103003830038300383003830038
100243003722500000274295472510010101000010100005042771601300183003730037282863287671001020100002010000300373003711100211091010100001005309123242229721010000103003830086301313003830132
100243003722500000612954725100101010000101000050427716003001830037300372828632876710010201000020100003003730037111002110910101000010041006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  ucvtf v0.4h, v8.4h, #3
  ucvtf v1.4h, v8.4h, #3
  ucvtf v2.4h, v8.4h, #3
  ucvtf v3.4h, v8.4h, #3
  ucvtf v4.4h, v8.4h, #3
  ucvtf v5.4h, v8.4h, #3
  ucvtf v6.4h, v8.4h, #3
  ucvtf v7.4h, v8.4h, #3
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)030818191e1f3f51inst 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)9fa0a1a6a7a8a9acc2c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005715600090532580108100800081008002050064013202002020039200399977699908022820080032200800322003920039118020110099100100800001000000000011151181160020036800001002004020040200402004020040
802042003915500000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160020036800001002004020040200402004020040
802042003915500000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160020036800001002004020040200402004020040
802042003915500000584280108100801161008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160020036800001002004020040200402004020040
802042003915500000722580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160020036800001002004020040200402004020040
802042003915500000512580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160020036800001002004020040200402004020040
802042003915500000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160020036800001002004020040200402004020040
802042003915500000302580108100800081008002050064013202002020039200909977699908012020080032200800322003920039118020110099100100800001000000100011151180160020036800001002004020040200402004020040
802042003915500000302580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160020036800001002004020040200402004020040
802042003915500000352580108100800081008002050064013202002020039200399977699908012020080032200800322003920039118020110099100100800001000000000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030408090b1e3f51inst 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)9fa8accfd5d6d9daddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420050155100004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502041601472003680000102004020040200402004020040
8002420039155000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502041600542003680000102004020040200402004020040
80024200391550000070525800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502041600682003680000102004020040200402004020040
8002420039155000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502041601772003680000102004020040200402004020040
8002420039155000004025800101080000108000050640000020020200392003999963100198001020801062080000200392003911800211091010800001000502041601562003680000102004020040200402004020040
8002420039155000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502061601442003680000102004020040200402004020040
8002420039156000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502071600552003680000102004020040200402004020040
8002420039155000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502041601782003680000102004020040200402004020040
8002420039155000004025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502041601482003680000102014520145200402004020040
8002420091156000034025800101080000108000050640000020020200392003999963100198001020800002080000200392003911800211091010800001000502061600542003680000102004020040200402004020040