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, 2S)

Test 1: uops

Code:

  uqrshl 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)031e3f4e51inst 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)accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
10043037220612548251000100010003983131301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
10043037220612548251000100010003983131301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
10043037220612548251000100010003983131301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
10043037220612548251000100010003983131301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
10043037220612548251000100010003983131301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
100430372302632548251000100010003983131301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
10043037220612548251000100010003983131301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
10043037230612548251000100010003983131301830373037241532895100010002000303730371110011000073116112630100030383038303830383038
100430372302122548251000100010003983131301830373037241532895100010002000303730371110011000073116112630100030383038303830383038

Test 2: Latency 1->2

Code:

  uqrshl 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)03081e3f4e51inst 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
102043003722503972629548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100037101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183008530083282653287451010020010000200200003003730037111020110099100100100001000847101161129634100001003003830038300383003830038
1020430037225006129548251011010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100067101161129634100001003003830038300383003830038
1020430037225001608295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000817101161129634100001003003830038300383003830038
102043003722500346295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000967101161129634100001003003830038300383003830038
102043003722500524295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000667101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100107101161129634100001003003830038300383003830038
1020430037225006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100037101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000787101161129634100001003003830038300383003830038
10204300372250061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000997101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03080a0b0f1e1f3f4e51inst 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
100243003722500000061295482510010101000010100006642773131300183003730037282873287671001020100002020000300373003711100211091010100001000640416342963010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640316442963010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640416342963010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640416432963010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640316342963010000103003830038300383003830038
100243003722500000061295482510010101000011100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640416432963010000103003830038300383003830038
100243003722400000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640416432963010000103003830038300383003830038
100243003722500040061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640416432963010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640416342963010000103003830038300383003830038
100243003722500000061295482510010101000010100005042773131300183003730037282873287671001020100002020000300373003711100211091010100001000640416342963010000103003830038300383003830038

Test 3: Latency 1->3

Code:

  uqrshl 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)03080b18191e3f4e51inst 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)9fa9acc5cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372250000061295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000007101161129634100001003003830038300383003830038
102043003722500000726295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000607101161129634100001003003830038300383003830038
1020430037225000009622954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010007807101161129634100001003003830038300383003830038
102043003722400000612954825101001031000010010000500427731303001830085300372826532874510100200100002002000030037300371110201100991001001000010008717101161129634100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010008107101161129634100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010007807101161129634100001003003830038300383003830038
1020430037224000006129548251010010010000100100005004277313130018300373003728265328745101002001000020020000300373003711102011009910010010000100011407101161129634100001003003830038300383003830038
10204300372250000661295482510100100100001001000050042773131300183003730037282653287451010020010000200200003003730037111020110099100100100001000607101161129634100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731303001830037300372826532874510100200100002002000030037300371110201100991001001000010009007101161129634100001003003830038300383003830038
102043003722500000612954825101001001000010010000500427731313001830037300372826532874510100200100002002000030037300371110201100991001001000010008407101161129634100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030708090b181e1f3f4e51inst 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)6061696d6edispatch 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)9fa0a1a8acc2cfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1002430037225000000061295482510010101000010100005042773131130018300373003728287328767100102010000202000030037300371110021109101010000100007806402162229630010000103003830038300383003830038
100243003722400000006129548251001010100001010000504277313103001830037300372828732876710010201000020200003003730037111002110910101000010010006402162229630010000103003830038300383003830038
10024300372250010000208295482510010101000010100005042773131030018300373003728287328767100102010000202000030037300371110021109101010000100007806402162229630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773131030018300373003728287328767100102010000202000030037300371110021109101010000100008106402162229630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773131030018300373003728287328767100102010000202000030037300371110021109101010000100007506402162229630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773131030018300373003728287328767100102010000202000030037300371110021109101010000100007806402162229630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773130030018300373003728287328767100102010000202000030037300371110021109101010000100008106402162229700010000103003830038300383003830038
1002430037225000000061295484410010101000010100005042773131030018300373003728287328767100102010000202000030037300371110021109101010000100009006402162229630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773131030018300373003728287328767100102010000202000030037300371110021109101010000100007806402162229630010000103003830038300383003830038
1002430037225000000061295482510010101000010100005042773131030018300373003728287328767100102010000202000030037300371110021109101010000100008406402162229630010000103003830038300383003830038

Test 4: throughput

Count: 8

Code:

  uqrshl v0.2s, v8.2s, v9.2s
  uqrshl v1.2s, v8.2s, v9.2s
  uqrshl v2.2s, v8.2s, v9.2s
  uqrshl v3.2s, v8.2s, v9.2s
  uqrshl v4.2s, v8.2s, v9.2s
  uqrshl v5.2s, v8.2s, v9.2s
  uqrshl v6.2s, v8.2s, v9.2s
  uqrshl 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)030b191e3f51inst 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)9fa8a9accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200601510004125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000051102161120036800001002009020040200402004020040
80204200391500006225801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010037010851101161120036800001002004020040200402004020040
80204200391500004125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
80204200391500004125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010010351101161120036800001002004020040200402004020040
802042003915000041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100470351101161120036800001002004020040200402004020040
80204200391501004125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010043011451101161120036800001002004020040200402004020040
802042003915000041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100480351101161120036800001002004020040200402004020040
802042003915000214125801001008000010080000500640000200202003920039997339997801002008000020016000020039200391180201100991001008000010000051101161120036800001002004020040200402004020040
802042003915000041258010010080000100800005006400002002020039200399973399978010020080000200160000200392003911802011009910010080000100310351101161120036800001002004020040200402004020040
8020420039150000412580100100800001008000050064000020020200392003999733999780100200800002001600002003920039118020110099100100800001000012051101161120036800001002004020040200402004020040

1000 unrolls and 10 iterations

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

retire (01)cycle (02)031e3f5051inst 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)9fa8accdcfd5d6dbddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
800242004815004020023258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001040050203160332003680000102004020040200402004020040
800242003915004002580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010340050203160332003680000102004020040200402004020040
800242003915004002580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010293050203160232003680000102004020040200402004020040
80024200391500400258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050203160232003680000102004020040200402004020040
80024200391500400258001010800001080000506400001200202003920039999631001980010208010620160210200392003911800211091010800001053050203160332003680000102004020040200402004020040
80024200391500400258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050203160332003680000102004020040200402004020040
80024200391500400258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050202160332003680000102004020040200402004020040
800242003915004002580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010260050203160332003680000102004020040200402004020040
800242003915004002580010108000010800005064000012002020039200399996310019800102080000201600002003920039118002110910108000010250050204160332003680000102004020040200402004020040
80024200391500400258001010800001080000506400001200202003920039999631001980010208000020160000200392003911800211091010800001000050203160352003680000102004020040200402004020040