From a561d46633db845079102bb396581e9cb9c11ae7 Mon Sep 17 00:00:00 2001
From: Simon Pilgrim <llvm-dev@redking.me.uk>
Date: Sat, 9 Feb 2019 22:21:09 +0000
Subject: [PATCH] [X86] Add tests for funnel undef argument combines

If one of the shifted arguments is undef we should be folding to a regular shift.

llvm-svn: 353628
---
 llvm/test/CodeGen/X86/funnel-shift.ll | 138 ++++++++++++++++++++++++++
 1 file changed, 138 insertions(+)

diff --git a/llvm/test/CodeGen/X86/funnel-shift.ll b/llvm/test/CodeGen/X86/funnel-shift.ll
index 9feab00516b8..ade636bc3ec1 100644
--- a/llvm/test/CodeGen/X86/funnel-shift.ll
+++ b/llvm/test/CodeGen/X86/funnel-shift.ll
@@ -358,6 +358,144 @@ define i32 @fshr_i32_demandedbits(i32 %a0, i32 %a1) nounwind {
   ret i32 %res
 }
 
+; undef handling
+
+define i32 @fshl_i32_undef0(i32 %a0, i32 %a1) nounwind {
+; X32-SSE2-LABEL: fshl_i32_undef0:
+; X32-SSE2:       # %bb.0:
+; X32-SSE2-NEXT:    movb {{[0-9]+}}(%esp), %cl
+; X32-SSE2-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-SSE2-NEXT:    shldl %cl, %eax, %eax
+; X32-SSE2-NEXT:    retl
+;
+; X64-AVX2-LABEL: fshl_i32_undef0:
+; X64-AVX2:       # %bb.0:
+; X64-AVX2-NEXT:    movl %esi, %ecx
+; X64-AVX2-NEXT:    # kill: def $cl killed $cl killed $ecx
+; X64-AVX2-NEXT:    shldl %cl, %edi, %eax
+; X64-AVX2-NEXT:    retq
+  %res = call i32 @llvm.fshl.i32(i32 undef, i32 %a0, i32 %a1)
+  ret i32 %res
+}
+
+define i32 @fshl_i32_undef0_cst(i32 %a0) nounwind {
+; X32-SSE2-LABEL: fshl_i32_undef0_cst:
+; X32-SSE2:       # %bb.0:
+; X32-SSE2-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-SSE2-NEXT:    shldl $9, %eax, %eax
+; X32-SSE2-NEXT:    retl
+;
+; X64-AVX2-LABEL: fshl_i32_undef0_cst:
+; X64-AVX2:       # %bb.0:
+; X64-AVX2-NEXT:    shldl $9, %edi, %eax
+; X64-AVX2-NEXT:    retq
+  %res = call i32 @llvm.fshl.i32(i32 undef, i32 %a0, i32 9)
+  ret i32 %res
+}
+
+define i32 @fshl_i32_undef1(i32 %a0, i32 %a1) nounwind {
+; X32-SSE2-LABEL: fshl_i32_undef1:
+; X32-SSE2:       # %bb.0:
+; X32-SSE2-NEXT:    movb {{[0-9]+}}(%esp), %cl
+; X32-SSE2-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-SSE2-NEXT:    shldl %cl, %eax, %eax
+; X32-SSE2-NEXT:    retl
+;
+; X64-AVX2-LABEL: fshl_i32_undef1:
+; X64-AVX2:       # %bb.0:
+; X64-AVX2-NEXT:    movl %esi, %ecx
+; X64-AVX2-NEXT:    movl %edi, %eax
+; X64-AVX2-NEXT:    # kill: def $cl killed $cl killed $ecx
+; X64-AVX2-NEXT:    shldl %cl, %eax, %eax
+; X64-AVX2-NEXT:    retq
+  %res = call i32 @llvm.fshl.i32(i32 %a0, i32 undef, i32 %a1)
+  ret i32 %res
+}
+
+define i32 @fshl_i32_undef1_cst(i32 %a0) nounwind {
+; X32-SSE2-LABEL: fshl_i32_undef1_cst:
+; X32-SSE2:       # %bb.0:
+; X32-SSE2-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-SSE2-NEXT:    shldl $9, %eax, %eax
+; X32-SSE2-NEXT:    retl
+;
+; X64-AVX2-LABEL: fshl_i32_undef1_cst:
+; X64-AVX2:       # %bb.0:
+; X64-AVX2-NEXT:    movl %edi, %eax
+; X64-AVX2-NEXT:    shldl $9, %eax, %eax
+; X64-AVX2-NEXT:    retq
+  %res = call i32 @llvm.fshl.i32(i32 %a0, i32 undef, i32 9)
+  ret i32 %res
+}
+
+define i32 @fshr_i32_undef0(i32 %a0, i32 %a1) nounwind {
+; X32-SSE2-LABEL: fshr_i32_undef0:
+; X32-SSE2:       # %bb.0:
+; X32-SSE2-NEXT:    movb {{[0-9]+}}(%esp), %cl
+; X32-SSE2-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-SSE2-NEXT:    shrdl %cl, %eax, %eax
+; X32-SSE2-NEXT:    retl
+;
+; X64-AVX2-LABEL: fshr_i32_undef0:
+; X64-AVX2:       # %bb.0:
+; X64-AVX2-NEXT:    movl %esi, %ecx
+; X64-AVX2-NEXT:    movl %edi, %eax
+; X64-AVX2-NEXT:    # kill: def $cl killed $cl killed $ecx
+; X64-AVX2-NEXT:    shrdl %cl, %eax, %eax
+; X64-AVX2-NEXT:    retq
+  %res = call i32 @llvm.fshr.i32(i32 undef, i32 %a0, i32 %a1)
+  ret i32 %res
+}
+
+define i32 @fshr_i32_undef0_cst(i32 %a0) nounwind {
+; X32-SSE2-LABEL: fshr_i32_undef0_cst:
+; X32-SSE2:       # %bb.0:
+; X32-SSE2-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-SSE2-NEXT:    shrdl $9, %eax, %eax
+; X32-SSE2-NEXT:    retl
+;
+; X64-AVX2-LABEL: fshr_i32_undef0_cst:
+; X64-AVX2:       # %bb.0:
+; X64-AVX2-NEXT:    movl %edi, %eax
+; X64-AVX2-NEXT:    shrdl $9, %eax, %eax
+; X64-AVX2-NEXT:    retq
+  %res = call i32 @llvm.fshr.i32(i32 undef, i32 %a0, i32 9)
+  ret i32 %res
+}
+
+define i32 @fshr_i32_undef1(i32 %a0, i32 %a1) nounwind {
+; X32-SSE2-LABEL: fshr_i32_undef1:
+; X32-SSE2:       # %bb.0:
+; X32-SSE2-NEXT:    movb {{[0-9]+}}(%esp), %cl
+; X32-SSE2-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-SSE2-NEXT:    shrdl %cl, %eax, %eax
+; X32-SSE2-NEXT:    retl
+;
+; X64-AVX2-LABEL: fshr_i32_undef1:
+; X64-AVX2:       # %bb.0:
+; X64-AVX2-NEXT:    movl %esi, %ecx
+; X64-AVX2-NEXT:    # kill: def $cl killed $cl killed $ecx
+; X64-AVX2-NEXT:    shrdl %cl, %edi, %eax
+; X64-AVX2-NEXT:    retq
+  %res = call i32 @llvm.fshr.i32(i32 %a0, i32 undef, i32 %a1)
+  ret i32 %res
+}
+
+define i32 @fshr_i32_undef1_cst(i32 %a0) nounwind {
+; X32-SSE2-LABEL: fshr_i32_undef1_cst:
+; X32-SSE2:       # %bb.0:
+; X32-SSE2-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; X32-SSE2-NEXT:    shrdl $9, %eax, %eax
+; X32-SSE2-NEXT:    retl
+;
+; X64-AVX2-LABEL: fshr_i32_undef1_cst:
+; X64-AVX2:       # %bb.0:
+; X64-AVX2-NEXT:    shrdl $9, %edi, %eax
+; X64-AVX2-NEXT:    retq
+  %res = call i32 @llvm.fshr.i32(i32 %a0, i32 undef, i32 9)
+  ret i32 %res
+}
+
 ; With constant shift amount, this is 'shrd' or 'shld'.
 
 define i32 @fshr_i32_const_shift(i32 %x, i32 %y) nounwind {