Teach DAGCombine to fold fold (sra (trunc (sr x, c1)), c2) -> (trunc (sra x, c1+c2) when c1 equals the amount of bits that are truncated off.

This happens all the time when a smul is promoted to a larger type.

On x86-64 we now compile "int test(int x) { return x/10; }" into
  movslq  %edi, %rax
  imulq $1717986919, %rax, %rax
  movq  %rax, %rcx
  shrq  $63, %rcx
  sarq  $34, %rax <- used to be "shrq $32, %rax; sarl $2, %eax"
  addl  %ecx, %eax

This fires 96 times in gcc.c on x86-64.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@124559 91177308-0d34-0410-b5e6-96231b3b80d8

test/CodeGen/X86/divide-by-constant.ll

@@ -51,3 +51,12 @@ define i32 @test5(i32 %A) nounwind {
 ; CHECK: mull	4(%esp)
 }
 
+define signext i16 @test6(i16 signext %x) nounwind {
+entry:
+  %div = sdiv i16 %x, 10
+  ret i16 %div
+; CHECK: test6:
+; CHECK: imull	$26215, %eax, %eax
+; CHECK: shrl	$31, %ecx
+; CHECK: sarl	$18, %eax
+}