Apple M1 Microarchitecture Research by Dougall Johnson

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

SQRSHL (scalar, S)

Test 1: uops

Code:

  sqrshl s0, s0, s1
  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)030918191e3a3f4e51inst 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)a0a8acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372300000612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372300000612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372300000612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372300000612548251000100010003983131301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372200000612548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372200000822548251000100010003983130301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
1004303723000001262548251000100010003983131301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372200000842548251000100010003983131301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
100430372200000612548251000100010003983131301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038
1004303722000001032548251000100010003983131301830373037241532895100010002000303730371110011000000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  sqrshl s0, s0, s1
  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)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)9fa0a1a8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100001207101161129634100001003003830038300383003830038
10204300372250822954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
102043003722507262954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038
10204300372250612954825101001001000010010000500427731330018300373003728265328745101002001000020020000300373003711102011009910010010000100000007101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0307080a0b18191e1f3f4e51inst 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)9fa0a1a6a8a9acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10024300372250000000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006406162229630010000103003830038300383003830038
10024300372250000000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000030006403162229630010000103003830038300383003830038
10024300372250000000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830083
10024300372250000000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000030006402162229630010000103003830038300383003830038
10024300372250000000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038
10024300372250000000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000000006402162229630010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  sqrshl s0, s1, s0
  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)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)9fa0a1a6a8a9acc2branch mispredict (cb)cfd5d6ddinst fetch restart (de)e0? int output thing (e9)ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000000286629548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000000000710116112963402100001003003830038300383003830038
102043003722400000006129548251010010010000100100005004277313130018300373003728265032876210417241100002002000030037300371110201100991001001000010000020000710116112963400100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313130018300373003728265032874510100200100002002000030037300371110201100991001001000010000010000710116112963400100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313130018300373003728265032874510100200100002002000030037300371110201100991001001000010000000000710116112963400100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313130018300373003728265032874510100200100002002000030037300371110201100991001001000010000000000710116112963400100001003003830038300383003830038
102043003722400000006129548251010010010000100100005004277313130018300373003728265032874510100200100002002000030037300371110201100991001001000010000000000710116112963400100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313130018300373003728265032874510100200100002002000030037300371110201100991001001000010000000000710216112963400100001003003830038300383003830038
1020430037225000002106129548251010010010000100100005004277313030018300373003728265032874510100200100002002000030037300371110201100991001001000010000000020710116112966700100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313030018300373003728269092874510100200100712002000030037300373110201100991001001000010000014000710116112963400100001003003830038300383003830038
102043003722500000006129548251010010010000100100005004277313130018300373003728265032874510100200100002002000030037300371110201100991001001000010000000000710116112963400100001003003830038300383003830038

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)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)9fa1a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037224061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133005430037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037224061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250726295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000647216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250631295482510010101000010100005042773133001830037300372828732876710010201000020203443003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
1002430037225061295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038
10024300372250726295482510010101000010100005042773133001830037300372828732876710010201000020200003003730037111002110910101000010000640216222963010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  sqrshl s0, s8, s9
  sqrshl s1, s8, s9
  sqrshl s2, s8, s9
  sqrshl s3, s8, s9
  sqrshl s4, s8, s9
  sqrshl s5, s8, s9
  sqrshl s6, s8, s9
  sqrshl s7, s8, s9
  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)030b1e1f3f51inst 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)9fa8cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
802042004915000041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100051102161120036800001002004020040200402004020040
802042003915000041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915000041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915000041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915000041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915000041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915000041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915000041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040
802042003915000041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020100
802042003915000041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100051101161120036800001002004020040200402004020040

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)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)9fa8c5branch mispredict (cb)cfd0d5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815004025800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000050200816532003680000102004020040200402004020040
800242003915004025800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000050200516352003680000102004020040200892004020040
800242003915004025800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000050200316462003680000102004020040200402004020040
800242003915004025800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000050200616532003680000102004020040200402004020040
800242003915004525800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000050200516352003680000102004020040200402004020040
800242003915004025800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000050200316532003680000102004020040200402004020040
800242003915004025800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000050200516532003680000102004020040200402004020040
800242003915004025800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000050200516642003680000102004020040200402004020040
800242003915004025800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000050200416462003680000102004020040200402004020040
800242003915004025800101080000108000050640000200202003920039999631001980010208000020160000200392003911800211091010800001000050200616642003680000102004020040200402004020040