Apple M1 Microarchitecture Research by Dougall Johnson

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

UMAXV (vector, 8H)

Test 1: uops

Code:

  umaxv h0, v0.8h
  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)03181e3f4e51inst 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)a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372300612547251000100010003981601301830373037241432895100010002000303730371110011000000073216222629100030383038303830383038
100430372300612547251000100010003981601301830373037241432895100010002000303730371110011000000073216222629100030383038303830383038
100430372200612547251000100010003981601301830373037241432895100010002000303730371110011000000073216222629100030383038303830383038
100430372200612547251000100010003981601301830373037241432895100010002000303730371110011000000073216222629100030383038303830383038
100430372300612547251000100010003981601301830373037241432895100010002000303730371110011000000073216222629100030383038303830383038
100430372300612547251000100010003981601301830373037241432895100010002000303730371110011000200073216222629100030383038303830383038
1004303723002512547251000100010003981601301830373037241432895100010002000303730371110011000000073216222629100030383038303830383038
100430372300612547251000100010003981601301830373037241432895100010002000303730371110011000000073216222629100030383038303830383038
100430372300822547251000100010003981601301830373037241432895100010002000303730371110011000000073116222629100030383038303830383038
100430372300612547251000100010003981601301830373037241432895100010002000303730371110011000000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  umaxv h0, v0.8h
  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)03181e1f3f4e51inst 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
10204300372250006129547251010010010000100100005004277160030054300373003728264328745101002001000020020000300373003711102011009910010010000100028257102251129633100001003003830038300383003830038
10204300372250006129547251010010010000100100005004277160030018300373003728264328745101002061033220020000300373003711102011009910010010000100007101161129633100001003003830087301333003830038
10204300372250006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372250006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372250006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372250006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100037101161129633100001003003830038300383003830038
10204300372250006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000302323003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372240006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372240006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038
10204300372250006129547251010010010000100100005004277160030018300373003728264328745101002001000020020000300373003711102011009910010010000100007101161129633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3a3f4e51inst 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)9fa0a1a6a8acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000061295472510010101000010100005042771600300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000061295472510010101000010100005042771600300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000061295472510010101000010100005042771601300183003730037282863287671001020100002020000302253003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000000726295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000000536295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000000726295472510010101000010100005042771600300183003730037282863287671001020100002020000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000000612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000033006402162229629010000103003830038300383003830038
10024300372250000000061295472510010101000010100005042771600300183003730037282863287671001020100002020000301313003711100211091010100001000000006402162229629010000103003830038300383003830038
10024300372250000000061295472510010101000010100005042771600300183003730037282863287671001020100002020000300373003711100211091010100001000000006672162229698010000103003830038300383003830038
10024300372250000000061295472510010101000010100005042771601300183003730037282863287671001020100002020000300373003711100211091010100001000020016402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  umaxv h0, v8.8h
  umaxv h1, v8.8h
  umaxv h2, v8.8h
  umaxv h3, v8.8h
  umaxv h4, v8.8h
  umaxv h5, v8.8h
  umaxv h6, v8.8h
  umaxv h7, v8.8h
  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)031e1f3f51inst 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)9fa8a9acc5branch mispredict (cb)cdcfd5d6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815100302580108100800081008002050064013220020200392003999776999080120200800322001600642003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
8020420039150570302580108100800081008002050064013220020200392003999776999080120200800322001600642003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013220020200392003999776999080120200800322001600642003920039118020110099100100800001001201115118016020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013220020200392003999776999080120200800322001600642003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013220020200392003999776999080120200800322001600642003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013220020200392003999776999080120200800322001600642003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013220020200392003999776999080120200800322001600642003920039118020110099100100800001000001115118016020036800001002004020040200402004020040
8020420039150001582580108100800081008002050064013220020200392003999776999080120200800322001600642003920039118020110099100100800001000231115118016020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013220020200392003999776999080120200800322001600642003920039418020110099100100800001002001115118016020036800001002004020040200402004020040
802042003915000302580108100800081008002050064013220020200392003999776999080120200800322001600642003920039118020110099100100800001000001115118016020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)030818191e3f51inst 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)9fa1a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420051150000040258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000005020116112003680000102004020040200402004020040
80024200391500110738258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001021325020116112003680000102004020040200402004020040
8002420039150000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000005020116112003680000102004020040200402004020040
8002420039150000082258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000005020116112003680000102004020040200402004020040
80024200391500001240258001010800001080000506400000200202003920039999631001980010208000020160000200392024311800211091010800001000005020116112003680000102004020040200402004020040
8002420039150000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000005020116112003680000102004020040200402004020040
80024200391500000420258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000305020116112003680000102004020040200402004020040
8002420039150000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000005020116112003680000102004020040200402004020040
8002420039150000040258001010800001080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000005020116112003680000102004020040200402004020040
8002420039150000040258001010803911080000506400000200202003920039999631001980010208000020160000200392003911800211091010800001000005020116112003680000102004020040200402004020040