mirror of
				https://github.com/c64scene-ar/llvm-6502.git
				synced 2025-11-03 14:21:30 +00:00 
			
		
		
		
	This solves PR22276. Splats of constants would sometimes produce redundant shuffles, sometimes ridiculously so (see the PR for details). Fold these shuffles into BUILD_VECTORs early on instead. Differential Revision: http://reviews.llvm.org/D7093 Fixed recommit of r226811. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@226816 91177308-0d34-0410-b5e6-96231b3b80d8
		
			
				
	
	
		
			41 lines
		
	
	
		
			1.5 KiB
		
	
	
	
		
			LLVM
		
	
	
	
	
	
			
		
		
	
	
			41 lines
		
	
	
		
			1.5 KiB
		
	
	
	
		
			LLVM
		
	
	
	
	
	
; RUN: llc < %s -mcpu=penryn | FileCheck %s --check-prefix=SSE
 | 
						|
; RUN: llc < %s -mcpu=sandybridge | FileCheck %s --check-prefix=AVX
 | 
						|
; RUN: llc < %s -mcpu=haswell | FileCheck %s --check-prefix=AVX2
 | 
						|
; This checks that lowering for creation of constant vectors is sane and
 | 
						|
; doesn't use redundant shuffles. (fixes PR22276)
 | 
						|
target triple = "x86_64-unknown-unknown"
 | 
						|
 | 
						|
define <4 x i32> @zero_vector() {
 | 
						|
; SSE-LABEL: zero_vector:
 | 
						|
; SSE: xorps %xmm0, %xmm0
 | 
						|
; SSE-NEXT: retq
 | 
						|
; AVX-LABEL: zero_vector:
 | 
						|
; AVX: vxorps %xmm0, %xmm0, %xmm0
 | 
						|
; AVX-NEXT: retq
 | 
						|
; AVX2-LABEL: zero_vector:
 | 
						|
; AVX2: vxorps %xmm0, %xmm0, %xmm0
 | 
						|
; AVX2-NEXT: retq
 | 
						|
  %zero = insertelement <4 x i32> undef, i32 0, i32 0
 | 
						|
  %splat = shufflevector <4 x i32> %zero, <4 x i32> undef, <4 x i32> zeroinitializer
 | 
						|
  ret <4 x i32> %splat
 | 
						|
}
 | 
						|
 | 
						|
; Note that for the "const_vector" versions, lowering that uses a shuffle
 | 
						|
; instead of a load would be legitimate, if it's a single broadcast shuffle.
 | 
						|
; (as opposed to the previous mess)
 | 
						|
; However, this is not the current preferred lowering.
 | 
						|
define <4 x i32> @const_vector() {
 | 
						|
; SSE-LABEL: const_vector:
 | 
						|
; SSE: movaps {{.*}}, %xmm0 # xmm0 = [42,42,42,42]
 | 
						|
; SSE-NEXT: retq
 | 
						|
; AVX-LABEL: const_vector:
 | 
						|
; AVX: vmovaps {{.*}}, %xmm0 # xmm0 = [42,42,42,42]
 | 
						|
; AVX-NEXT: retq
 | 
						|
; AVX2-LABEL: const_vector:
 | 
						|
; AVX2: vbroadcastss {{[^%].*}}, %xmm0
 | 
						|
; AVX2-NEXT: retq
 | 
						|
  %const = insertelement <4 x i32> undef, i32 42, i32 0
 | 
						|
  %splat = shufflevector <4 x i32> %const, <4 x i32> undef, <4 x i32> zeroinitializer
 | 
						|
  ret <4 x i32> %splat
 | 
						|
}
 |