mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-24 19:52:54 +01:00
c0b1184e0b
Summary: It appears to be better IR-wise to aggressively scalarize it, rather than relying on gathering it, and leaving it as-is. Reviewers: jdoerfert, bjope, arsenm, cameron.mcinally Reviewed By: jdoerfert Subscribers: arphaman, wdng, hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D83101
20 lines
921 B
LLVM
20 lines
921 B
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt %s -scalarizer -scalarize-load-store -dce -S | FileCheck --check-prefixes=ALL %s
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
|
|
; Test that constant extracts are nicely scalarized
|
|
define i32 @f1(<4 x i32> *%src, i32 %index) {
|
|
; ALL-LABEL: @f1(
|
|
; ALL-NEXT: [[SRC_I0:%.*]] = bitcast <4 x i32>* [[SRC:%.*]] to i32*
|
|
; ALL-NEXT: [[SRC_I3:%.*]] = getelementptr i32, i32* [[SRC_I0]], i32 3
|
|
; ALL-NEXT: [[VAL0_I3:%.*]] = load i32, i32* [[SRC_I3]], align 4
|
|
; ALL-NEXT: [[VAL2:%.*]] = shl i32 4, [[VAL0_I3]]
|
|
; ALL-NEXT: ret i32 [[VAL2]]
|
|
;
|
|
%val0 = load <4 x i32> , <4 x i32> *%src
|
|
%val1 = shl <4 x i32> <i32 1, i32 2, i32 3, i32 4>, %val0
|
|
%val2 = extractelement <4 x i32> %val1, i32 3
|
|
ret i32 %val2
|
|
}
|