[X86] Allow X86ISD::Wrapper to be folded into the base of gather/scatter address

If the base of our gather corresponds to something contained in X86ISD::Wrapper we should be able to fold it into the address.

This patch refactors some of the address matching to more fully use the X86ISelAddressMode struct and the getAddressOperands helper. A new helper function matchVectorAddress is added to call matchWrapper or fall back to matchAddressBase.

We should also be able to support constant offsets from a wrapper, but I'll look into that in a future patch. We may even be able to completely reuse matchAddress here, but I wanted to start simple and work up to it.

Differential Revision: https://reviews.llvm.org/D39927

llvm-svn: 318057

1 files changed, 75 insertions, 38 deletions

diff --git a/llvm/test/CodeGen/X86/masked_gather_scatter.ll b/llvm/test/CodeGen/X86/masked_gather_scatter.ll
index 7cd698e3760..70472c49f57 100644
--- a/llvm/test/CodeGen/X86/masked_gather_scatter.ll
+++ b/llvm/test/CodeGen/X86/masked_gather_scatter.ll
@@ -1,7 +1,8 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=x86_64-unknown-linux-gnu  -mattr=+avx512f < %s | FileCheck %s --check-prefix=ALL --check-prefix=KNL_64
 ; RUN: llc -mtriple=i386-unknown-linux-gnu  -mattr=+avx512f < %s | FileCheck %s --check-prefix=ALL --check-prefix=KNL_32
-; RUN: llc -mtriple=x86_64-unknown-linux-gnu  -mattr=+avx512vl -mattr=+avx512dq < %s | FileCheck %s --check-prefix=ALL --check-prefix=SKX
+; RUN: llc -mtriple=x86_64-unknown-linux-gnu  -mattr=+avx512vl -mattr=+avx512dq < %s | FileCheck %s --check-prefix=ALL --check-prefix=SKX --check-prefix=SKX_SMALL
+; RUN: llc -mtriple=x86_64-unknown-linux-gnu  -mattr=+avx512vl -mattr=+avx512dq -code-model=large < %s | FileCheck %s --check-prefix=ALL --check-prefix=SKX --check-prefix=SKX_LARGE
 ; RUN: llc -mtriple=i386-unknown-linux-gnu  -mattr=+avx512vl -mattr=+avx512dq < %s | FileCheck %s --check-prefix=ALL --check-prefix=SKX_32
 ; RUN: opt -mtriple=x86_64-apple-darwin -scalarize-masked-mem-intrin -mcpu=corei7-avx -S < %s | FileCheck %s -check-prefix=SCALAR
 ; RUN: llc -O0 -mtriple=x86_64-unknown-linux-gnu -mcpu=skx < %s -o /dev/null
@@ -491,18 +492,34 @@ define <8 x i32> @test9(%struct.ST* %base, <8 x i64> %ind1, <8 x i32>%ind5) {
 ; KNL_32-NEXT:    vpgatherqd (,%zmm1), %ymm0 {%k1}
 ; KNL_32-NEXT:    retl
 ;
-; SKX-LABEL: test9:
-; SKX:       # BB#0: # %entry
-; SKX-NEXT:    vpbroadcastq %rdi, %zmm2
-; SKX-NEXT:    vpmullq {{.*}}(%rip){1to8}, %zmm0, %zmm0
-; SKX-NEXT:    vpmovsxdq %ymm1, %zmm1
-; SKX-NEXT:    vpmullq {{.*}}(%rip){1to8}, %zmm1, %zmm1
-; SKX-NEXT:    vpaddq %zmm1, %zmm0, %zmm0
-; SKX-NEXT:    vpaddq %zmm0, %zmm2, %zmm0
-; SKX-NEXT:    vpaddq {{.*}}(%rip){1to8}, %zmm0, %zmm1
-; SKX-NEXT:    kxnorw %k0, %k0, %k1
-; SKX-NEXT:    vpgatherqd (,%zmm1), %ymm0 {%k1}
-; SKX-NEXT:    retq
+; SKX_SMALL-LABEL: test9:
+; SKX_SMALL:       # BB#0: # %entry
+; SKX_SMALL-NEXT:    vpbroadcastq %rdi, %zmm2
+; SKX_SMALL-NEXT:    vpmullq {{.*}}(%rip){1to8}, %zmm0, %zmm0
+; SKX_SMALL-NEXT:    vpmovsxdq %ymm1, %zmm1
+; SKX_SMALL-NEXT:    vpmullq {{.*}}(%rip){1to8}, %zmm1, %zmm1
+; SKX_SMALL-NEXT:    vpaddq %zmm1, %zmm0, %zmm0
+; SKX_SMALL-NEXT:    vpaddq %zmm0, %zmm2, %zmm0
+; SKX_SMALL-NEXT:    vpaddq {{.*}}(%rip){1to8}, %zmm0, %zmm1
+; SKX_SMALL-NEXT:    kxnorw %k0, %k0, %k1
+; SKX_SMALL-NEXT:    vpgatherqd (,%zmm1), %ymm0 {%k1}
+; SKX_SMALL-NEXT:    retq
+;
+; SKX_LARGE-LABEL: test9:
+; SKX_LARGE:       # BB#0: # %entry
+; SKX_LARGE-NEXT:    vpbroadcastq %rdi, %zmm2
+; SKX_LARGE-NEXT:    vpmovsxdq %ymm1, %zmm1
+; SKX_LARGE-NEXT:    movabsq ${{\.LCPI.*}}, %rax
+; SKX_LARGE-NEXT:    vpmullq (%rax){1to8}, %zmm1, %zmm1
+; SKX_LARGE-NEXT:    movabsq ${{\.LCPI.*}}, %rax
+; SKX_LARGE-NEXT:    vpmullq (%rax){1to8}, %zmm0, %zmm0
+; SKX_LARGE-NEXT:    vpaddq %zmm1, %zmm0, %zmm0
+; SKX_LARGE-NEXT:    vpaddq %zmm0, %zmm2, %zmm0
+; SKX_LARGE-NEXT:    movabsq ${{\.LCPI.*}}, %rax
+; SKX_LARGE-NEXT:    vpaddq (%rax){1to8}, %zmm0, %zmm1
+; SKX_LARGE-NEXT:    kxnorw %k0, %k0, %k1
+; SKX_LARGE-NEXT:    vpgatherqd (,%zmm1), %ymm0 {%k1}
+; SKX_LARGE-NEXT:    retq
 ;
 ; SKX_32-LABEL: test9:
 ; SKX_32:       # BB#0: # %entry
@@ -560,18 +577,34 @@ define <8 x i32> @test10(%struct.ST* %base, <8 x i64> %i1, <8 x i32>%ind5) {
 ; KNL_32-NEXT:    vpgatherqd (,%zmm1), %ymm0 {%k1}
 ; KNL_32-NEXT:    retl
 ;
-; SKX-LABEL: test10:
-; SKX:       # BB#0: # %entry
-; SKX-NEXT:    vpbroadcastq %rdi, %zmm2
-; SKX-NEXT:    vpmullq {{.*}}(%rip){1to8}, %zmm0, %zmm0
-; SKX-NEXT:    vpmovsxdq %ymm1, %zmm1
-; SKX-NEXT:    vpmullq {{.*}}(%rip){1to8}, %zmm1, %zmm1
-; SKX-NEXT:    vpaddq %zmm1, %zmm0, %zmm0
-; SKX-NEXT:    vpaddq %zmm0, %zmm2, %zmm0
-; SKX-NEXT:    vpaddq {{.*}}(%rip){1to8}, %zmm0, %zmm1
-; SKX-NEXT:    kxnorw %k0, %k0, %k1
-; SKX-NEXT:    vpgatherqd (,%zmm1), %ymm0 {%k1}
-; SKX-NEXT:    retq
+; SKX_SMALL-LABEL: test10:
+; SKX_SMALL:       # BB#0: # %entry
+; SKX_SMALL-NEXT:    vpbroadcastq %rdi, %zmm2
+; SKX_SMALL-NEXT:    vpmullq {{.*}}(%rip){1to8}, %zmm0, %zmm0
+; SKX_SMALL-NEXT:    vpmovsxdq %ymm1, %zmm1
+; SKX_SMALL-NEXT:    vpmullq {{.*}}(%rip){1to8}, %zmm1, %zmm1
+; SKX_SMALL-NEXT:    vpaddq %zmm1, %zmm0, %zmm0
+; SKX_SMALL-NEXT:    vpaddq %zmm0, %zmm2, %zmm0
+; SKX_SMALL-NEXT:    vpaddq {{.*}}(%rip){1to8}, %zmm0, %zmm1
+; SKX_SMALL-NEXT:    kxnorw %k0, %k0, %k1
+; SKX_SMALL-NEXT:    vpgatherqd (,%zmm1), %ymm0 {%k1}
+; SKX_SMALL-NEXT:    retq
+;
+; SKX_LARGE-LABEL: test10:
+; SKX_LARGE:       # BB#0: # %entry
+; SKX_LARGE-NEXT:    vpbroadcastq %rdi, %zmm2
+; SKX_LARGE-NEXT:    vpmovsxdq %ymm1, %zmm1
+; SKX_LARGE-NEXT:    movabsq ${{\.LCPI.*}}, %rax
+; SKX_LARGE-NEXT:    vpmullq (%rax){1to8}, %zmm1, %zmm1
+; SKX_LARGE-NEXT:    movabsq ${{\.LCPI.*}}, %rax
+; SKX_LARGE-NEXT:    vpmullq (%rax){1to8}, %zmm0, %zmm0
+; SKX_LARGE-NEXT:    vpaddq %zmm1, %zmm0, %zmm0
+; SKX_LARGE-NEXT:    vpaddq %zmm0, %zmm2, %zmm0
+; SKX_LARGE-NEXT:    movabsq ${{\.LCPI.*}}, %rax
+; SKX_LARGE-NEXT:    vpaddq (%rax){1to8}, %zmm0, %zmm1
+; SKX_LARGE-NEXT:    kxnorw %k0, %k0, %k1
+; SKX_LARGE-NEXT:    vpgatherqd (,%zmm1), %ymm0 {%k1}
+; SKX_LARGE-NEXT:    retq
 ;
 ; SKX_32-LABEL: test10:
 ; SKX_32:       # BB#0: # %entry
@@ -2330,33 +2363,37 @@ declare <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*>, i32, <4 x i1>, <
 define <8 x i32> @test_global_array(<8 x i64> %indxs) {
 ; KNL_64-LABEL: test_global_array:
 ; KNL_64:       # BB#0:
-; KNL_64-NEXT:    movl $glob_array, %eax
 ; KNL_64-NEXT:    kxnorw %k0, %k0, %k1
-; KNL_64-NEXT:    vpgatherqd (%rax,%zmm0,4), %ymm1 {%k1}
+; KNL_64-NEXT:    vpgatherqd glob_array(,%zmm0,4), %ymm1 {%k1}
 ; KNL_64-NEXT:    vmovdqa %ymm1, %ymm0
 ; KNL_64-NEXT:    retq
 ;
 ; KNL_32-LABEL: test_global_array:
 ; KNL_32:       # BB#0:
-; KNL_32-NEXT:    movl $glob_array, %eax
 ; KNL_32-NEXT:    kxnorw %k0, %k0, %k1
-; KNL_32-NEXT:    vpgatherqd (%eax,%zmm0,4), %ymm1 {%k1}
+; KNL_32-NEXT:    vpgatherqd glob_array(,%zmm0,4), %ymm1 {%k1}
 ; KNL_32-NEXT:    vmovdqa %ymm1, %ymm0
 ; KNL_32-NEXT:    retl
 ;
-; SKX-LABEL: test_global_array:
-; SKX:       # BB#0:
-; SKX-NEXT:    movl $glob_array, %eax
-; SKX-NEXT:    kxnorw %k0, %k0, %k1
-; SKX-NEXT:    vpgatherqd (%rax,%zmm0,4), %ymm1 {%k1}
-; SKX-NEXT:    vmovdqa %ymm1, %ymm0
-; SKX-NEXT:    retq
+; SKX_SMALL-LABEL: test_global_array:
+; SKX_SMALL:       # BB#0:
+; SKX_SMALL-NEXT:    kxnorw %k0, %k0, %k1
+; SKX_SMALL-NEXT:    vpgatherqd glob_array(,%zmm0,4), %ymm1 {%k1}
+; SKX_SMALL-NEXT:    vmovdqa %ymm1, %ymm0
+; SKX_SMALL-NEXT:    retq
+;
+; SKX_LARGE-LABEL: test_global_array:
+; SKX_LARGE:       # BB#0:
+; SKX_LARGE-NEXT:    movabsq $glob_array, %rax
+; SKX_LARGE-NEXT:    kxnorw %k0, %k0, %k1
+; SKX_LARGE-NEXT:    vpgatherqd (%rax,%zmm0,4), %ymm1 {%k1}
+; SKX_LARGE-NEXT:    vmovdqa %ymm1, %ymm0
+; SKX_LARGE-NEXT:    retq
 ;
 ; SKX_32-LABEL: test_global_array:
 ; SKX_32:       # BB#0:
-; SKX_32-NEXT:    movl $glob_array, %eax
 ; SKX_32-NEXT:    kxnorw %k0, %k0, %k1
-; SKX_32-NEXT:    vpgatherqd (%eax,%zmm0,4), %ymm1 {%k1}
+; SKX_32-NEXT:    vpgatherqd glob_array(,%zmm0,4), %ymm1 {%k1}
 ; SKX_32-NEXT:    vmovdqa %ymm1, %ymm0
 ; SKX_32-NEXT:    retl
   %p = getelementptr inbounds [16 x i32], [16 x i32]* @glob_array, i64 0, <8 x i64> %indxs