Improve GVN to be able to forward substitute a small load

from a piece of a large store when both are in the same block.

This allows clang to compile the testcase in PR4216 to this code:

_test_bitfield:
	movl	4(%esp), %eax
	movl	%eax, %ecx
	andl	$-65536, %ecx
	orl	$32962, %eax
	andl	$40186, %eax
	orl	%ecx, %eax
	ret

This is not ideal, but is a whole lot better than the code produced
by llvm-gcc:

_test_bitfield:
	movw	$-32574, %ax
	orw	4(%esp), %ax
	andw	$-25350, %ax
	movw	%ax, 4(%esp)
	movw	7(%esp), %cx
	shlw	$8, %cx
	movzbl	6(%esp), %edx
	orw	%cx, %dx
	movzwl	%dx, %ecx
	shll	$16, %ecx
	movzwl	%ax, %eax
	orl	%ecx, %eax
	ret

and dramatically better than that produced by gcc 4.2:

_test_bitfield:
	pushl	%ebx
	call	L3
"L00000000001$pb":
L3:
	popl	%ebx
	movl	8(%esp), %eax
	leal	0(,%eax,4), %edx
	sarb	$7, %dl
	movl	%eax, %ecx
	andl	$7168, %ecx
	andl	$-7201, %ebx
	movzbl	%dl, %edx
	andl	$1, %edx
	sall	$5, %edx
	orl	%ecx, %ebx
	orl	%edx, %ebx
	andl	$24, %eax
	andl	$-58336, %ebx
	orl	%eax, %ebx
	orl	$32962, %ebx
	movl	%ebx, %eax
	popl	%ebx
	ret



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@82439 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 50 insertions, 0 deletions

diff --git a/test/Transforms/GVN/rle.ll b/test/Transforms/GVN/rle.ll
index 503a5bb..736a7e4 100644
--- a/test/Transforms/GVN/rle.ll
+++ b/test/Transforms/GVN/rle.ll
@@ -141,6 +141,35 @@ Cont:
 ; CHECK: ret i8 %A
 }
 
+;; non-local i32/float -> i8 load forwarding.  This also tests that the "P3"
+;; bitcast equivalence can be properly phi translated.
+define i8 @coerce_mustalias_nonlocal1(i32* %P, i1 %cond) {
+  %P2 = bitcast i32* %P to float*
+  br i1 %cond, label %T, label %F
+T:
+  store i32 42, i32* %P
+  br label %Cont
+  
+F:
+  store float 1.0, float* %P2
+  br label %Cont
+
+Cont:
+  %P3 = bitcast i32* %P to i8*
+  %A = load i8* %P3
+  ret i8 %A
+
+;; FIXME: This is disabled because this caused a miscompile in the llvm-gcc
+;; bootstrap, see r82411
+;
+; HECK: @coerce_mustalias_nonlocal1
+; HECK: Cont:
+; HECK:   %A = phi i8 [
+; HECK-NOT: load
+; HECK: ret i8 %A
+}
+
+
 ;; non-local i32 -> i8 partial redundancy load forwarding.
 define i8 @coerce_mustalias_pre0(i32* %P, i1 %cond) {
   %P3 = bitcast i32* %P to i8*
@@ -165,3 +194,24 @@ Cont:
 ; CHECK: ret i8 %A
 }
 
+;;===----------------------------------------------------------------------===;;
+;; Store -> Load  and  Load -> Load forwarding where src and dst are different
+;; types, and the reload is an offset from the store pointer.
+;;===----------------------------------------------------------------------===;;
+
+;; i32 -> f32 forwarding.
+define i8 @coerce_offset0(i32 %V, i32* %P) {
+  store i32 %V, i32* %P
+   
+  %P2 = bitcast i32* %P to i8*
+  %P3 = getelementptr i8* %P2, i32 2
+
+  %A = load i8* %P3
+  ret i8 %A
+; CHECK: @coerce_offset0
+; CHECK-NOT: load
+; CHECK: ret i8
+}
+
+
+