Apple M1 Microarchitecture Research by Dougall Johnson

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

UQRSHL (vector, 16B)

Test 1: uops

Code:

  uqrshl v0.16b, v0.16b, v1.16b
  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)030818191e1f3a3f4e51inst 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)a0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
1004303722000000612548251000100010003983131301830373037241532895100010002000303730371110011000000000073116112630100030383038303830383038
1004303723000000612548251000100010003983131301830373037241532895100010002000303730371110011000000000073116112630100030383038303830383038
1004303723000000612548251000100011213983131301830373037241532895100010002000303730371110011000000000073116112630100030383038303830383038
1004303723000000612548441000100010003983131301830373037241532895100010002000303730371110011000000000073116112630100030383038303830383038
100430372300012006125482510001000100039831313018303730372415328951000100020003037303711100110000000036073116112630100030383038303830383038
1004303723000000612548251000100010003983131301830373037241532895100010002000303730371110011000000000073116112656100030383038303830383038
10043037250000002742548251000100010003983130301830373037241532895100010002000303730371110011000000000073116112630100030383038303830383038
1004303723000000612548251008100010003983131301830373037241532895100010002000303730371110011000000000073116112630100030383038303830383038
1004303722000000612548251000100010003983131301830373037241532895100010002000303730371110011000000000073116112630100030383038303830383038
1004303723000000612548251000100010003983131301830373037241532895100010002000303730371110011000000000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  uqrshl v0.16b, v0.16b, v1.16b
  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)0308090b18191e1f3f4e51inst 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)9fa0a1a6a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722500000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000007102241129668100001003003830086301323008630038
102043008622400000006129548251010010010000122100005004278670130018300373008528272328745104142001000020620000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722400000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300863003830038
102043008622510012006129548641010010010000100101495004277313130018300373003728265828745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
1020430037225000001206129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000037101161129634100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000037101161129634100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313130018300373003728265328745104192001000020020000300373003711102011009910010010000100000037101161129634100001003003830038300383003830038
102043003722500100006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100002307101161129634100001003003830038300383003830038
1020430037224000000021229548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2c5cficache miss (d3)d5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000061295482510010101000010100005042773131300183003730037282870328767100102010000202000030037300371110021109101010000100000000064002162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131300183003730037282870328767100102010000202000030037300371110021109101010000100000000064002162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131300183003730037282870328767100102010000202000030037300371110021109101010000100000000064002162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131300183003730037282870328767100102010000202032230084300371110021109101010000100000000064002162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131300183003730037282870328767100102010000202000030037300371110021109101010000100000000064002162229630010000103003830038300383003830038
10024300372250000001040295482510010101000010100005042773131300183003730037282870328767100102010000202000030037300371110021109101010000100000000064002163229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131300183003730037282870328767100102010000202000030037300371110021109101010000100000000064002162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131300183003730037282870328767100102010000202000030037300371110021109101010000100000000064002162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131300183003730037282870328767100102010000202000030037300371110021109101010000100000000064002162229630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131300183003730037282870328767100102010000202000030037300371110021109101010000100000000064002162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  uqrshl v0.16b, v1.16b, v0.16b
  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)031e1f3f4e51inst 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)9fa6a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
102043003722536061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722551061295482510100100100001001000050042773133001830085300852826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722572061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722512061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722548061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722554061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225288061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
102043003722515061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038
1020430037225135061295482510100100100001001000050042773133001830037300372826532874510100200100002002000030037300371110201100991001001000010000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030818191e1f3a3f4e51inst 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)9fa0a1a7a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006405165529630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006405165529630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131300183003730037282873287671001020106482020000300373003711100211091010100001000000306404165529630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006405165429630010000103003830038300383003830038
100243003722500000061295482510010131000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000026405165529630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000000006405165429630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773130300183003730037282879287671001020100002020000300373003711100211091010100001000000006405165429630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006405165529630010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773130300183003730037282873287671001020100002021320300373003711100211091010100001000000006405325529630010000103003830178300383003830038
1002530037225000000103295482510010101000010100005042773130300183003730037282873287671001020100002020000300373003711100211091010100001000030006405164529630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  uqrshl v0.16b, v8.16b, v9.16b
  uqrshl v1.16b, v8.16b, v9.16b
  uqrshl v2.16b, v8.16b, v9.16b
  uqrshl v3.16b, v8.16b, v9.16b
  uqrshl v4.16b, v8.16b, v9.16b
  uqrshl v5.16b, v8.16b, v9.16b
  uqrshl v6.16b, v8.16b, v9.16b
  uqrshl v7.16b, v8.16b, v9.16b
  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)03080b18191e1f3f51inst 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
80204200391500000004125801001008000010080000500640000200202003920039997339997801002008000020016027220039200391180201100991001008000010000511071622200360800001002004020040200402004020040
802042003915000000020925801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000511021622200360800001002004020040200402004020040
80204200391500000004125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000511021622200360800001002004020040200402004020040
802042003915000000041258010010080000100800005006400002002020039200399973310023801002008000020016000020039200391180201100991001008000010000511021622200360800001002004020040200402004020040
80204200391500000004125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000511021622200360800001002004020040200402004020040
80204200391500000004125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000511021622200360800001002004020040200402004020040
80204200391500000004125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000511021622200360800001002004020040200402004020040
8020420039150000090023125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010089511021622200360800001002004020040200402004020040
80204200391500000004125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000511021622200360800001002004020040200402004020040
80204200391500000604125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000511021622200360800001002004020040200402004020040

1000 unrolls and 10 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)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)dfe0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420087150904025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050201316139020036080000102004020040200402004020040
8002420039150303252580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010005020916128020036080000102004020040200402004020040
8002420039150210402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010105020816813020036080000102004020040200402004020040
80024200391502404025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050201316912020036080000102004020040200402004020040
80024200391501204025800101080000108000050640000120020200392003999963100488001020800002016000020039200391180021109101080000100050208161310020036080000102004020040200402004020040
800242003915000358725800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050201216129020036080000102004020040200402004020040
8002420039150240402580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010005020916914020036080000102004020040200402004020040
8002420039150004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050201316139020036080000102004020040200402004020040
80024200391501504025800101080000108000050640000020020200392003999963100198001020800002016000020039200391180021109101080000100050201316812020036080000102004020040200402004020040
8002420039150004025800101080000108000050640000120020200392003999963100198001020800002016000020039200391180021109101080000100050201216128020036080000102004020040200402004020040