mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-26 05:32:25 +00:00
fb55a8fd7c
Adds a function to target transform info to query for the cost of address computation. The cost model analysis pass now also queries this interface. The code in LoopVectorize adds the cost of address computation as part of the memory instruction cost calculation. Only there, we know whether the instruction will be scalarized or not. Increase the penality for inserting in to D registers on swift. This becomes necessary because we now always assume that address computation has a cost and three is a closer value to the architecture. radar://13097204 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@174713 91177308-0d34-0410-b5e6-96231b3b80d8
47 lines
1.5 KiB
LLVM
47 lines
1.5 KiB
LLVM
; RUN: opt -cost-model -analyze -mtriple=thumbv7-apple-ios6.0.0 -mcpu=swift < %s | FileCheck %s
|
|
|
|
target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:32:64-v128:32:128-a0:0:32-n32-S32"
|
|
target triple = "thumbv7-apple-ios6.0.0"
|
|
|
|
; Multiple insert elements from loads into d subregisters are expensive on swift
|
|
; due to renaming constraints.
|
|
%T_i8v = type <8 x i8>
|
|
%T_i8 = type i8
|
|
; CHECK: insertelement_i8
|
|
define void @insertelement_i8(%T_i8* %saddr,
|
|
%T_i8v* %vaddr) {
|
|
%v0 = load %T_i8v* %vaddr
|
|
%v1 = load %T_i8* %saddr
|
|
;CHECK: estimated cost of 3 for {{.*}} insertelement <8 x i8>
|
|
%v2 = insertelement %T_i8v %v0, %T_i8 %v1, i32 1
|
|
store %T_i8v %v2, %T_i8v* %vaddr
|
|
ret void
|
|
}
|
|
|
|
|
|
%T_i16v = type <4 x i16>
|
|
%T_i16 = type i16
|
|
; CHECK: insertelement_i16
|
|
define void @insertelement_i16(%T_i16* %saddr,
|
|
%T_i16v* %vaddr) {
|
|
%v0 = load %T_i16v* %vaddr
|
|
%v1 = load %T_i16* %saddr
|
|
;CHECK: estimated cost of 3 for {{.*}} insertelement <4 x i16>
|
|
%v2 = insertelement %T_i16v %v0, %T_i16 %v1, i32 1
|
|
store %T_i16v %v2, %T_i16v* %vaddr
|
|
ret void
|
|
}
|
|
|
|
%T_i32v = type <2 x i32>
|
|
%T_i32 = type i32
|
|
; CHECK: insertelement_i32
|
|
define void @insertelement_i32(%T_i32* %saddr,
|
|
%T_i32v* %vaddr) {
|
|
%v0 = load %T_i32v* %vaddr
|
|
%v1 = load %T_i32* %saddr
|
|
;CHECK: estimated cost of 3 for {{.*}} insertelement <2 x i32>
|
|
%v2 = insertelement %T_i32v %v0, %T_i32 %v1, i32 1
|
|
store %T_i32v %v2, %T_i32v* %vaddr
|
|
ret void
|
|
}
|