[X86] Adding a test for vector shuffle extractions.

[jbhateja]

Summary

When both the vector inputs of the shuffle vector is comprising of same
vector or shuffle mask is accessing elements from only one operand vector
(like in PR33758 test already present).

[jbhateja]

Hi Simon,

Can you kindly land this revision into trunk. This will be updated with new results of D35788.

Thanks

[RKSimon]

In D36271#830700, @jbhateja wrote:

Hi Simon,

Can you kindly land this revision into trunk. This will be updated with new results of D35788.

Thanks

OK - but if you don't mind I'd like to put this in vector-shuffle-512-v64.ll instead of adding a new file?

[jbhateja]

Its ok, you can add it to already existing file.

I do not have commit rights so please merge this test.

Thanks

[RKSimon]

In D36271#830709, @RKSimon wrote:

In D36271#830700, @jbhateja wrote:

Hi Simon,

Can you kindly land this revision into trunk. This will be updated with new results of D35788.

Thanks

OK - but if you don't mind I'd like to put this in vector-shuffle-512-v64.ll instead of adding a new file?

Sorry, I should have said shuffle-vs-trunc-512.ll

[jbhateja]

You can add it where ever you think it shall make more sense.

Thanks

test/CodeGen/X86/shuffle-vector-same-inputs.ll

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512F
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vl | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512VL
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512BW
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl | FileCheck %s --check-prefix=AVX512 --check-prefix=AVX512BWVL
+
+define <16 x i8> @foo(<64 x i8> %x) {
+; AVX512F-LABEL: foo:
+; AVX512F:       # BB#0:
+; AVX512F-NEXT:    vextracti128 $1, %ymm0, %xmm2
+; AVX512F-NEXT:    vmovdqa {{.*#+}} xmm3 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
+; AVX512F-NEXT:    vpshufb %xmm3, %xmm2, %xmm2
+; AVX512F-NEXT:    vpshufb %xmm3, %xmm0, %xmm0
+; AVX512F-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
+; AVX512F-NEXT:    vextracti128 $1, %ymm1, %xmm2
+; AVX512F-NEXT:    vpshufb {{.*#+}} xmm2 = xmm2[u,u,u,u,1,5,9,14,u,u,u,u,u,u,u,u]
+; AVX512F-NEXT:    vpshufb {{.*#+}} xmm1 = xmm1[u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u]
+; AVX512F-NEXT:    vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
+; AVX512F-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
+; AVX512F-NEXT:    vzeroupper
+; AVX512F-NEXT:    retq
+;
+; AVX512VL-LABEL: foo:
+; AVX512VL:       # BB#0:
+; AVX512VL-NEXT:    vextracti128 $1, %ymm0, %xmm2
+; AVX512VL-NEXT:    vmovdqa {{.*#+}} xmm3 = <1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u>
+; AVX512VL-NEXT:    vpshufb %xmm3, %xmm2, %xmm2
+; AVX512VL-NEXT:    vpshufb %xmm3, %xmm0, %xmm0
+; AVX512VL-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
+; AVX512VL-NEXT:    vextracti128 $1, %ymm1, %xmm2
+; AVX512VL-NEXT:    vpshufb {{.*#+}} xmm2 = xmm2[u,u,u,u,1,5,9,14,u,u,u,u,u,u,u,u]
+; AVX512VL-NEXT:    vpshufb {{.*#+}} xmm1 = xmm1[u,u,u,u,1,5,9,13,u,u,u,u,u,u,u,u]
+; AVX512VL-NEXT:    vpunpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
+; AVX512VL-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
+; AVX512VL-NEXT:    vzeroupper
+; AVX512VL-NEXT:    retq
+;
+; AVX512BW-LABEL: foo:
+; AVX512BW:       # BB#0:
+; AVX512BW-NEXT:    vpextrb $5, %xmm0, %eax
+; AVX512BW-NEXT:    vpextrb $1, %xmm0, %ecx
+; AVX512BW-NEXT:    vmovd %ecx, %xmm1
+; AVX512BW-NEXT:    vpinsrb $1, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpextrb $9, %xmm0, %eax
+; AVX512BW-NEXT:    vpinsrb $2, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpextrb $13, %xmm0, %eax
+; AVX512BW-NEXT:    vpinsrb $3, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vextracti32x4 $1, %zmm0, %xmm2
+; AVX512BW-NEXT:    vpextrb $1, %xmm2, %eax
+; AVX512BW-NEXT:    vpinsrb $4, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpextrb $5, %xmm2, %eax
+; AVX512BW-NEXT:    vpinsrb $5, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpextrb $9, %xmm2, %eax
+; AVX512BW-NEXT:    vpinsrb $6, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpextrb $13, %xmm2, %eax
+; AVX512BW-NEXT:    vpinsrb $7, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vextracti32x4 $2, %zmm0, %xmm2
+; AVX512BW-NEXT:    vpextrb $1, %xmm2, %eax
+; AVX512BW-NEXT:    vpinsrb $8, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpextrb $5, %xmm2, %eax
+; AVX512BW-NEXT:    vpinsrb $9, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpextrb $9, %xmm2, %eax
+; AVX512BW-NEXT:    vpinsrb $10, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpextrb $13, %xmm2, %eax
+; AVX512BW-NEXT:    vpinsrb $11, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vextracti32x4 $3, %zmm0, %xmm0
+; AVX512BW-NEXT:    vpextrb $1, %xmm0, %eax
+; AVX512BW-NEXT:    vpinsrb $12, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpextrb $5, %xmm0, %eax
+; AVX512BW-NEXT:    vpinsrb $13, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpextrb $9, %xmm0, %eax
+; AVX512BW-NEXT:    vpinsrb $14, %eax, %xmm1, %xmm1
+; AVX512BW-NEXT:    vpextrb $14, %xmm0, %eax
+; AVX512BW-NEXT:    vpinsrb $15, %eax, %xmm1, %xmm0
+; AVX512BW-NEXT:    vzeroupper
+; AVX512BW-NEXT:    retq
+;
+; AVX512BWVL-LABEL: foo:
+; AVX512BWVL:       # BB#0:
+; AVX512BWVL-NEXT:    vpextrb $5, %xmm0, %eax
+; AVX512BWVL-NEXT:    vpextrb $1, %xmm0, %ecx
+; AVX512BWVL-NEXT:    vmovd %ecx, %xmm1
+; AVX512BWVL-NEXT:    vpinsrb $1, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vpextrb $9, %xmm0, %eax
+; AVX512BWVL-NEXT:    vpinsrb $2, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vpextrb $13, %xmm0, %eax
+; AVX512BWVL-NEXT:    vpinsrb $3, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vextracti32x4 $1, %zmm0, %xmm2
+; AVX512BWVL-NEXT:    vpextrb $1, %xmm2, %eax
+; AVX512BWVL-NEXT:    vpinsrb $4, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vpextrb $5, %xmm2, %eax
+; AVX512BWVL-NEXT:    vpinsrb $5, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vpextrb $9, %xmm2, %eax
+; AVX512BWVL-NEXT:    vpinsrb $6, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vpextrb $13, %xmm2, %eax
+; AVX512BWVL-NEXT:    vpinsrb $7, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vextracti32x4 $2, %zmm0, %xmm2
+; AVX512BWVL-NEXT:    vpextrb $1, %xmm2, %eax
+; AVX512BWVL-NEXT:    vpinsrb $8, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vpextrb $5, %xmm2, %eax
+; AVX512BWVL-NEXT:    vpinsrb $9, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vpextrb $9, %xmm2, %eax
+; AVX512BWVL-NEXT:    vpinsrb $10, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vpextrb $13, %xmm2, %eax
+; AVX512BWVL-NEXT:    vpinsrb $11, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vextracti32x4 $3, %zmm0, %xmm0
+; AVX512BWVL-NEXT:    vpextrb $1, %xmm0, %eax
+; AVX512BWVL-NEXT:    vpinsrb $12, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vpextrb $5, %xmm0, %eax
+; AVX512BWVL-NEXT:    vpinsrb $13, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vpextrb $9, %xmm0, %eax
+; AVX512BWVL-NEXT:    vpinsrb $14, %eax, %xmm1, %xmm1
+; AVX512BWVL-NEXT:    vpextrb $14, %xmm0, %eax
+; AVX512BWVL-NEXT:    vpinsrb $15, %eax, %xmm1, %xmm0
+; AVX512BWVL-NEXT:    vzeroupper
+; AVX512BWVL-NEXT:    retq
+  %res = shufflevector <64 x i8> %x, <64 x i8> %x, <16 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29, i32 33, i32 37, i32 41, i32 45, i32 49, i32 53, i32 57, i32 62>
+  ret <16 x i8> %res
+}