Apple M1 Microarchitecture Research by Dougall Johnson

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

URSHL (vector, 2S)

Test 1: uops

Code:

  urshl v0.2s, v0.2s, v1.2s
  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)03090a1e3f4e51inst 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)a1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372200061254825100010001000398313130183037303724153289510001000200030373037111001100000073216112630100030383038303830383038
100430372300061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383074
100430372300061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372200061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112702100030383038303830383038
100430372200061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372300061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372200061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372200061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372300061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038
100430372300061254825100010001000398313130183037303724153289510001000200030373037111001100000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  urshl v0.2s, v0.2s, v1.2s
  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)9fa0a8accdcfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722508229548251010010010000100100005004277313030018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225033129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100419073511611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100010071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
1020430037225012429548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
102043003722506129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000071011611296340100001003003830038300383003830038
10204300372250286295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000163071011611296340100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0304080b18191e1f3f4e51inst 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)9fa0a1a6a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
100243003722400000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
100243003722510000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313130018300373003728287328767100102010000202000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
100243003722500000006129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006403163329630010000103003830038300383003830038
100243003722500000306129548251001010100001010000504277313030018300373003728287328767100102010000202000030037300371110021109101010000100000006403163329630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  urshl v0.2s, v1.2s, v0.2s
  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)03080b181e1f3f4e51inst 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)9fa0a8accfd5d6dcddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011601129634100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011601129634100001003003830038300383003830038
102043003722400000612953944101001001000011610149500427731313001830037300372826532876210275200100002002000030037300371110201100991001001000010003371012501129634100001003008530085300873008530133
102043003722511000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011601129634100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011601129634100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011601129634100001003003830038300383003830038
1020530037225000001062954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011601129634100001003003830038300383003830038
1020430037225000007262954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011601129634100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011601129634100001003003830038300383003830038
1020430037225000007262954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010000071011601129634100001003003830038300383003830038

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)72scheduler 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)9fa0a6a8acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243008322501032954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001000000640316222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372240612954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828707287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
10024300372250612954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001010000640216222963010000103003830038300383003830038
100243003722504412954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038
100243003722507262954825100101010000101000050427731313001830037300372828703287671001020100002020000300373003711100211091010100001000000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  urshl v0.2s, v8.2s, v9.2s
  urshl v1.2s, v8.2s, v9.2s
  urshl v2.2s, v8.2s, v9.2s
  urshl v3.2s, v8.2s, v9.2s
  urshl v4.2s, v8.2s, v9.2s
  urshl v5.2s, v8.2s, v9.2s
  urshl v6.2s, v8.2s, v9.2s
  urshl v7.2s, v8.2s, v9.2s
  movi v8.16b, 9
  movi v9.16b, 10

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

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

retire (01)cycle (02)0308191e3f51inst 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)9fa0a8acbranch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042005815000274125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000000511021612200360800001002004020040200402004020040
8020420039150003064125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000511011611200770800001002004020040200402004020040
802042003915000758325801001008000010080105500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
80204200391500004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
80204200391500004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
802042003915000124125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
80204200391490004125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
80204200391500004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
80204200391500004125801001008000010080000500640000120020200392003999733999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040
802042003915000364125801001008000010080000500640000020020200392003999733999780100200800002001600002003920039118020110099100100800001000000511011611200360800001002004020040200402004020040

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)696b6d6edispatch 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242003915004025800101080000108000050640000200200200392003999963100198001020800002016000020039200391180021109101080000100005020316112003680000102004020040200402004020040
800242003915004025800101080000108000050640000200200200392003999963100198001020800002016000020039200391180021109101080000100035020116112003680000102004020040200402004020040
8002420039150124025800101080000108000050640000200200200392003999963100198001020800002016000020039200391180021109101080000100005020116112003680000102004020040200402004020040
800242003915004025800101080000108000050640000200200200392003999963100198001020800002016000020039200391180021109101080000100005020116112003680000102004020040200402004020040
8002420039150694025800101080000108000050640000200200200392003999963100198001020800002016000020039200391180021109101080000100005020116112003680000102004020040200402004020040
800242003915064025800101080000108000050640000200200200392003999963100198001020800002016000020039200391180021109101080000100005020116112003680000102004020040200402004020040
800242003915004025800101080000108000050640000200200200392003999963100198001020800002016000020039200391180021109101080000100005020116112003680000102004020040200402004020040
800242003915004025800101080000108000050640000200200200392003999963100198001020800002016000020039200391180021109101080000100005020116112003680000102004020040200402004020040
800242003915004025800101080000108000050640000200200200392003999963100198001020800002016000020039200391180021109101080000100005020116112003680000102004020040200402004020040
8002420039150154025800101080000108000050640000200200200392003999963100198001020800002016000020039200391180021109101080000100005020116112003680000102004020040200402004020040