Commit Graph

6 Commits

Author SHA1 Message Date
Chris Lattner
7900779543 handle the constant case of vector insertion. For something
like this:

struct S { float A, B, C, D; };

struct S g;
struct S bar() { 
  struct S A = g;
  ++A.B;
  A.A = 42;
  return A;
}

we now generate:

_bar:                                   ## @bar
## BB#0:                                ## %entry
	movq	_g@GOTPCREL(%rip), %rax
	movss	12(%rax), %xmm0
	pshufd	$16, %xmm0, %xmm0
	movss	4(%rax), %xmm2
	movss	8(%rax), %xmm1
	pshufd	$16, %xmm1, %xmm1
	unpcklps	%xmm0, %xmm1
	addss	LCPI1_0(%rip), %xmm2
	pshufd	$16, %xmm2, %xmm2
	movss	LCPI1_1(%rip), %xmm0
	pshufd	$16, %xmm0, %xmm0
	unpcklps	%xmm2, %xmm0
	ret

instead of:

_bar:                                   ## @bar
## BB#0:                                ## %entry
	movq	_g@GOTPCREL(%rip), %rax
	movss	12(%rax), %xmm0
	pshufd	$16, %xmm0, %xmm0
	movss	4(%rax), %xmm2
	movss	8(%rax), %xmm1
	pshufd	$16, %xmm1, %xmm1
	unpcklps	%xmm0, %xmm1
	addss	LCPI1_0(%rip), %xmm2
	movd	%xmm2, %eax
	shlq	$32, %rax
	addq	$1109917696, %rax       ## imm = 0x42280000
	movd	%rax, %xmm0
	ret



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112345 91177308-0d34-0410-b5e6-96231b3b80d8
2010-08-28 01:50:57 +00:00
Chris Lattner
3dd08734c1 optimize bitcasts from large integers to vector into vector
element insertion from the pieces that feed into the vector.
This handles a pattern that occurs frequently due to code
generated for the x86-64 abi.  We now compile something like
this:

struct S { float A, B, C, D; };
struct S g;
struct S bar() { 
  struct S A = g;
  ++A.A;
  ++A.C;
  return A;
}

into all nice vector operations:

_bar:                                   ## @bar
## BB#0:                                ## %entry
	movq	_g@GOTPCREL(%rip), %rax
	movss	LCPI1_0(%rip), %xmm1
	movss	(%rax), %xmm0
	addss	%xmm1, %xmm0
	pshufd	$16, %xmm0, %xmm0
	movss	4(%rax), %xmm2
	movss	12(%rax), %xmm3
	pshufd	$16, %xmm2, %xmm2
	unpcklps	%xmm2, %xmm0
	addss	8(%rax), %xmm1
	pshufd	$16, %xmm1, %xmm1
	pshufd	$16, %xmm3, %xmm2
	unpcklps	%xmm2, %xmm1
	ret

instead of icky integer operations:

_bar:                                   ## @bar
	movq	_g@GOTPCREL(%rip), %rax
	movss	LCPI1_0(%rip), %xmm1
	movss	(%rax), %xmm0
	addss	%xmm1, %xmm0
	movd	%xmm0, %ecx
	movl	4(%rax), %edx
	movl	12(%rax), %esi
	shlq	$32, %rdx
	addq	%rcx, %rdx
	movd	%rdx, %xmm0
	addss	8(%rax), %xmm1
	movd	%xmm1, %eax
	shlq	$32, %rsi
	addq	%rax, %rsi
	movd	%rsi, %xmm1
	ret

This resolves rdar://8360454



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112343 91177308-0d34-0410-b5e6-96231b3b80d8
2010-08-28 01:20:38 +00:00
Chris Lattner
26dbe7ec18 optimize "integer extraction out of the middle of a vector" as produced
by SRoA.  This is part of rdar://7892780, but needs another xform to
expose this.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112232 91177308-0d34-0410-b5e6-96231b3b80d8
2010-08-26 22:14:59 +00:00
Chris Lattner
e5a1426174 optimize bitcast(trunc(bitcast(x))) where the result is a float and 'x'
is a vector to be a vector element extraction.  This allows clang to
compile:

struct S { float A, B, C, D; };
float foo(struct S A) { return A.A + A.B+A.C+A.D; }

into:

_foo:                                   ## @foo
## BB#0:                                ## %entry
	movd	%xmm0, %rax
	shrq	$32, %rax
	movd	%eax, %xmm2
	addss	%xmm0, %xmm2
	movapd	%xmm1, %xmm3
	addss	%xmm2, %xmm3
	movd	%xmm1, %rax
	shrq	$32, %rax
	movd	%eax, %xmm0
	addss	%xmm3, %xmm0
	ret

instead of:

_foo:                                   ## @foo
## BB#0:                                ## %entry
	movd	%xmm0, %rax
	movd	%eax, %xmm0
	shrq	$32, %rax
	movd	%eax, %xmm2
	addss	%xmm0, %xmm2
	movd	%xmm1, %rax
	movd	%eax, %xmm1
	addss	%xmm2, %xmm1
	shrq	$32, %rax
	movd	%eax, %xmm0
	addss	%xmm1, %xmm0
	ret

... eliminating half of the horribleness.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112227 91177308-0d34-0410-b5e6-96231b3b80d8
2010-08-26 21:55:42 +00:00
Chris Lattner
a6140a1444 filecheckize
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112225 91177308-0d34-0410-b5e6-96231b3b80d8
2010-08-26 21:51:41 +00:00
Chris Lattner
5333459a1e rename test
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112224 91177308-0d34-0410-b5e6-96231b3b80d8
2010-08-26 21:50:56 +00:00