[Bug target/95524] New: Subtimal codegen for shift by constant for v16qi/v32qi under -march=skylake

[crazylht at gmail dot com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=95524

            Bug ID: 95524
           Summary: Subtimal codegen for shift by constant for v16qi/v32qi
                    under -march=skylake
           Product: gcc
           Version: 11.0
            Status: UNCONFIRMED
          Keywords: missed-optimization
          Severity: normal
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: crazylht at gmail dot com
  Target Milestone: ---
            Target: x86_64-*-* i?86-*-*

cat test.c
---
typedef char v16qi __attribute__ ((vector_size (16)));
typedef char v32qi __attribute__ ((vector_size (32)));
typedef unsigned char v16uqi __attribute__ ((vector_size (16)));
typedef unsigned char v32uqi __attribute__ ((vector_size (32)));

v16qi
ashift (v16qi a)
{
    return  a<<5;
}

v32qi
ashift2 (v32qi a, v32qi b)
{
    return  a<<5;
}

v16qi
ashiftrt (v16qi a)
{
    return  a>>5;
}

v32qi
arshiftrt2 (v32qi a)
{
    return  a>>5;
}

v16uqi
lshiftrt (v16uqi a)
{
    return  a>>5;
}

v32uqi
lshiftrt2 (v32uqi a)
{
    return  a>>5;
}
---

gcc11 -O2 -march=skylake

---
ashift(char __vector(16)):
        vpaddb  xmm0, xmm0, xmm0
        vpaddb  xmm0, xmm0, xmm0
        vpaddb  xmm0, xmm0, xmm0
        vpaddb  xmm0, xmm0, xmm0
        vpaddb  xmm0, xmm0, xmm0
        ret
ashift2(char __vector(32), char __vector(32)):
        vpaddb  ymm0, ymm0, ymm0
        vpaddb  ymm0, ymm0, ymm0
        vpaddb  ymm0, ymm0, ymm0
        vpaddb  ymm0, ymm0, ymm0
        vpaddb  ymm0, ymm0, ymm0
        ret
ashiftrt(char __vector(16)):
        vpmovsxbw       xmm2, xmm0
        vpsrldq xmm1, xmm0, 8
        vpmovsxbw       xmm1, xmm1
        vpsraw  xmm0, xmm2, 5
        vmovdqa xmm2, XMMWORD PTR .LC0[rip]
        vpsraw  xmm1, xmm1, 5
        vpand   xmm0, xmm2, xmm0
        vpand   xmm2, xmm2, xmm1
        vpackuswb       xmm0, xmm0, xmm2
        ret
arshiftrt2(char __vector(32)):
        vmovdqa ymm1, ymm0
        vextracti128    xmm1, ymm1, 0x1
        vmovdqa ymm2, YMMWORD PTR .LC1[rip]
        vpmovsxbw       ymm0, xmm0
        vpmovsxbw       ymm1, xmm1
        vpsraw  ymm1, ymm1, 5
        vpsraw  ymm0, ymm0, 5
        vpand   ymm0, ymm2, ymm0
        vpand   ymm2, ymm2, ymm1
        vpackuswb       ymm0, ymm0, ymm2
        vpermq  ymm0, ymm0, 216
        ret
lshiftrt(unsigned char __vector(16)):
        vpmovzxbw       xmm2, xmm0
        vpsrldq xmm1, xmm0, 8
        vpmovzxbw       xmm1, xmm1
        vpsrlw  xmm0, xmm2, 5
        vmovdqa xmm2, XMMWORD PTR .LC0[rip]
        vpsrlw  xmm1, xmm1, 5
        vpand   xmm0, xmm2, xmm0
        vpand   xmm2, xmm2, xmm1
        vpackuswb       xmm0, xmm0, xmm2
        ret
lshiftrt2(unsigned char __vector(32)):
        vmovdqa ymm1, ymm0
        vextracti128    xmm1, ymm1, 0x1
        vmovdqa ymm2, YMMWORD PTR .LC1[rip]
        vpmovzxbw       ymm0, xmm0
        vpmovzxbw       ymm1, xmm1
        vpsrlw  ymm1, ymm1, 5
        vpsrlw  ymm0, ymm0, 5
        vpand   ymm0, ymm2, ymm0
        vpand   ymm2, ymm2, ymm1
        vpackuswb       ymm0, ymm0, ymm2
        vpermq  ymm0, ymm0, 216
        ret
.LC0:
        .value  255
        .value  255
        .value  255
        .value  255
        .value  255
        .value  255
        .value  255
        .value  255
.LC1:
        .value  255
        .value  255
        .value  255
        .value  255
        .value  255
        .value  255
        .value  255
        .value  255
        .value  255
        .value  255
        .value  255
        .value  255
        .value  255
        .value  255
        .value  255
        .value  255
---

icc has
---
ashift(char __vector(16)):
        vpsllw    xmm1, xmm0, 5                                 #9.16
        vpand     xmm0, xmm1, XMMWORD PTR .L_2il0floatpacket.0[rip] #9.16
        ret                                                     #9.16
ashift2(char __vector(32), char __vector(32)):
        vpsllw    ymm2, ymm0, 5                                 #15.16
        vpand     ymm0, ymm2, YMMWORD PTR .L_2il0floatpacket.1[rip] #15.16
        ret                                                     #15.16
ashiftrt(char __vector(16)):
        vpsrlw    xmm1, xmm0, 5                                 #21.16
        vpand     xmm0, xmm1, XMMWORD PTR .L_2il0floatpacket.2[rip] #21.16
        ret                                                     #21.16
arshiftrt2(char __vector(32)):
        vpsrlw    ymm1, ymm0, 5                                 #27.16
        vpand     ymm0, ymm1, YMMWORD PTR .L_2il0floatpacket.3[rip] #27.16
        ret                                                     #27.16
lshiftrt(unsigned char __vector(16)):
        vpsrlw    xmm1, xmm0, 5                                 #33.16
        vpand     xmm0, xmm1, XMMWORD PTR .L_2il0floatpacket.2[rip] #33.16
        ret                                                     #33.16
lshiftrt2(unsigned char __vector(32)):
        vpsrlw    ymm1, ymm0, 5                                 #39.16
        vpand     ymm0, ymm1, YMMWORD PTR .L_2il0floatpacket.3[rip] #39.16
        ret                                                     #39.16
.L_2il0floatpacket.1:
        .long  
0xe0e0e0e0,0xe0e0e0e0,0xe0e0e0e0,0xe0e0e0e0,0xe0e0e0e0,0xe0e0e0e0,0xe0e0e0e0,0xe0e0e0e0
.L_2il0floatpacket.3:
        .long  
0x07070707,0x07070707,0x07070707,0x07070707,0x07070707,0x07070707,0x07070707,0x07070707
.L_2il0floatpacket.0:
        .long   0xe0e0e0e0,0xe0e0e0e0,0xe0e0e0e0,0xe0e0e0e0
.L_2il0floatpacket.2:
        .long   0x07070707,0x07070707,0x07070707,0x07070707
---

icc take much less instructions than gcc.