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, 4H)

Test 1: uops

Code:

  umaxv 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)03080b18191e1f3a3f4e51inst 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)a0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303723000000061254725100010001000398160301830373037241432895100010002000303730371110011000000000073216112629100030383038303830383038
1004303722000000061254725100010001000398160301830373037241432895100010002000303730371110011000000000073116112629100030383038303830383038
1004303723000000061254725100010001000398160301830373037241432895100010002000303730371110011000000000073116112629100030383038303830383038
10043037230000000103254725100010001000398160301830373037241432895100010002000303730371110011000000000073116112629100030383038303830383038
10043037230000000191254725100010001000398160301830373037241432895100010002000303730371110011000000000073116112629100030383038303830383038
1004303723000000061254725100010001000398160301830373037241432895100010002000303730371110011000000000073116112629100030383038303830383038
1004303723000000061254725100010001000398160301830373037241432895100010002000303730371110011000000000073116112629100030383038303830383038
1004303722000000084254725100010001000398160301830373037241432895114810002000303730371110011000000000073116112629100030383038303830383038
1004303722000000061254725100010001000398160301830373037241432895100010002000303730371110011000000000073116112629100030383038303830383086
1004303723000000061254725100010001000398160301830373037241462895115010002000303730371110011000000000073116112629100030383038303830383038

Test 2: Latency 1->2

Code:

  umaxv 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)0307090b18191e3f4e51inst 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)9fa8accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225100000104129547251010010010000100100005004277160300183003730037282643287451010020010000200200003003730037111020110099100100100001000071021622296330100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160300183003730037282643287451010020010000200200003003730037111020110099100100100001000071021632296330100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160300183003730037282643287451010020010000200200003003730037111020110099100100100001003071021622296330100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160300183003730037282643287451010020010000200200003003730037111020110099100100100001000071021622296330100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004281216300183003730037282643287451010020010000200200003003730037111020110099100100100001000071021622296330100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160300183003730037282643287451010020010000200200003003730037111020110099100100100001000071021622296330100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160300183003730037282643287451010020010000200200003003730037111020110099100100100001000071021622296330100001003003830038300383003830038
10204300372250000001367295472510100100100001001000050042771603001830037300372826432874510100200100002002000030037300371110201100991001001000010019671021622296330100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160300183003730037282643287451010020010000200200003003730037111020110099100100100001000071021622296330100001003003830038300383003830038
10204300372250000006129547251010010010000100100005004277160300183003730037282643287451010020010000200200003003730037111020110099100100100001000071021622296330100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030b18191e1f3a3f4e51inst 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)9fa0a1a6a7a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000900612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000000064041622296290010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716013001830037300372828632876710010201000020200003007630037111002110910101000010000000064021622296290010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000006064021622296290010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000000064021622296290010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716003001830037300372828632876710010201000020200003003730037111002110910101000010000000064011622296290010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000000064021622296290010000103003830038300383003830038
1002430037225000000612954725100101010000101000050427716013001830037300372828632876710010201000020200003003730037111002110910101000010000000064021622296290010000103003830038300383007430038
10024300372240001068704052432954715210069131005611110507142866241303063041530370283003528915112162611313242264830415300379110021109101010000100000125210483228933299263010000103041330133304153041630422
10024304042280991068792058222949318910079141007215102438742879761303103045330463283213728936112142011402262294230417304539110021109101010000102000025248085038852299173010000103032030455304633042030369
1002430415228099119179215890294751721008712100641311350504287976030306304513046428318628917113442610000242297030463304149110021109101010000104000013870282938934299724010000103013330370301813027830085

Test 3: throughput

Count: 8

Code:

  umaxv h0, v8.4h
  umaxv h1, v8.4h
  umaxv h2, v8.4h
  umaxv h3, v8.4h
  umaxv h4, v8.4h
  umaxv h5, v8.4h
  umaxv h6, v8.4h
  umaxv 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): 0.2506

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)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
802042003915003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
8020420039150041025801081008000810080020500640132120020200392003999776999080120200800322001600642003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151181160020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151181160020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920090118020110099100100800001000011151180160020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151180160020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151181160020036800001002004020040200402004020040
802042003915003025802071008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151181160020036800001002004020040200402004020040
802042003915003025801081008000810080020500640132020020200392003999776999080120200800322001600642003920039118020110099100100800001000011151181160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)0307080b18191e1f3a3f51inst 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)5f60696d6edispatch 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)9fa0a1a6a8a9acc2branch mispredict (cb)cfd0d2icache miss (d3)d5d6d9daddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024200511500000000014725800101080000108000050640000012002020039200399996310019800102080000201600002003920142118002110910108000010000000005020000116001120036080000102004020040200402004020040
8002420039150000000004025800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010000000005020000116001120036080000102004020040200402004020040
8002420039150000000006125800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010000000005020000116001120036080000102004020040200402004020040
8002420039150000000004025800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010000000005020000116001120036080000102004020040200402004020040
8002420039150000000004025800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010000000005020000116001120036080000102004020040200402004020040
8002420039150000000004025800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010000000005020000116001120036080000102004020040200402004020040
8002420039150000000004025800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010000000005020000116001120036080000102004020040200402004020040
80024200391500000000010325800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010000000005020000116001120036080000102004020040200402004020040
8002420039150000000004025800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010000000005020000116001120036080000102004020040200402004020040
8002420039150000000004025800101080000108000050640000012002020039200399996310019800102080000201600002003920039118002110910108000010000000005020000116001120036080000102004020040200402004020040