mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2025-01-25 00:33:15 +00:00
e5a1426174
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
38 lines
1.2 KiB
LLVM
38 lines
1.2 KiB
LLVM
; RUN: opt < %s -instcombine -S | FileCheck %s
|
|
|
|
; Bitcasts between vectors and scalars are valid.
|
|
; PR4487
|
|
define i32 @test1(i64 %a) {
|
|
%t1 = bitcast i64 %a to <2 x i32>
|
|
%t2 = bitcast i64 %a to <2 x i32>
|
|
%t3 = xor <2 x i32> %t1, %t2
|
|
%t4 = extractelement <2 x i32> %t3, i32 0
|
|
ret i32 %t4
|
|
|
|
; CHECK: @test1
|
|
; CHECK: ret i32 0
|
|
}
|
|
|
|
; Optimize bitcasts that are extracting low element of vector. This happens
|
|
; because of SRoA.
|
|
; rdar://7892780
|
|
define float @test2(<2 x float> %A, <2 x i32> %B) {
|
|
%tmp28 = bitcast <2 x float> %A to i64 ; <i64> [#uses=2]
|
|
%tmp23 = trunc i64 %tmp28 to i32 ; <i32> [#uses=1]
|
|
%tmp24 = bitcast i32 %tmp23 to float ; <float> [#uses=1]
|
|
|
|
%tmp = bitcast <2 x i32> %B to i64
|
|
%tmp2 = trunc i64 %tmp to i32 ; <i32> [#uses=1]
|
|
%tmp4 = bitcast i32 %tmp2 to float ; <float> [#uses=1]
|
|
|
|
%add = fadd float %tmp24, %tmp4
|
|
ret float %add
|
|
|
|
; CHECK: @test2
|
|
; CHECK-NEXT: %tmp24 = extractelement <2 x float> %A, i32 0
|
|
; CHECK-NEXT: bitcast <2 x i32> %B to <2 x float>
|
|
; CHECK-NEXT: %tmp4 = extractelement <2 x float> {{.*}}, i32 0
|
|
; CHECK-NEXT: %add = fadd float %tmp24, %tmp4
|
|
; CHECK-NEXT: ret float %add
|
|
}
|