1fc992bd86
This patch makes Scalarizer to use poison as insertelement's placeholder. It contains two changes in Scalarizer.cpp, and the both changes does not change the semantics of the optimized program. It is because the placeholder value (poison) is already completely hidden by following insertelement instructions. The first change at visitBitCastInst() creates poison vector of MidTy and consecutively inserts FanIn times, which is # of elems of MidTy. The second change at ScalarizerVisitor::finish() creates poison with Op->getType(), and it is filled with Count insertelements. The test diffs show that the poison value is never exposed after insertelements. Reviewed By: nikic Differential Revision: https://reviews.llvm.org/D93989
30 lines
1.7 KiB
LLVM
30 lines
1.7 KiB
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 inserts are nicely scalarized
|
|
define <4 x i32> @f1(<4 x i32> *%src, i32 %repl, i32 %index) {
|
|
; ALL-LABEL: @f1(
|
|
; ALL-NEXT: [[SRC_I0:%.*]] = bitcast <4 x i32>* [[SRC:%.*]] to i32*
|
|
; ALL-NEXT: [[VAL0_I0:%.*]] = load i32, i32* [[SRC_I0]], align 16
|
|
; ALL-NEXT: [[SRC_I1:%.*]] = getelementptr i32, i32* [[SRC_I0]], i32 1
|
|
; ALL-NEXT: [[VAL0_I1:%.*]] = load i32, i32* [[SRC_I1]], align 4
|
|
; ALL-NEXT: [[SRC_I2:%.*]] = getelementptr i32, i32* [[SRC_I0]], i32 2
|
|
; ALL-NEXT: [[VAL0_I2:%.*]] = load i32, i32* [[SRC_I2]], align 8
|
|
; ALL-NEXT: [[VAL2_I0:%.*]] = shl i32 1, [[VAL0_I0]]
|
|
; ALL-NEXT: [[VAL2_I1:%.*]] = shl i32 2, [[VAL0_I1]]
|
|
; ALL-NEXT: [[VAL2_I2:%.*]] = shl i32 3, [[VAL0_I2]]
|
|
; ALL-NEXT: [[VAL2_I3:%.*]] = shl i32 4, [[REPL:%.*]]
|
|
; ALL-NEXT: [[VAL2_UPTO0:%.*]] = insertelement <4 x i32> poison, i32 [[VAL2_I0]], i32 0
|
|
; ALL-NEXT: [[VAL2_UPTO1:%.*]] = insertelement <4 x i32> [[VAL2_UPTO0]], i32 [[VAL2_I1]], i32 1
|
|
; ALL-NEXT: [[VAL2_UPTO2:%.*]] = insertelement <4 x i32> [[VAL2_UPTO1]], i32 [[VAL2_I2]], i32 2
|
|
; ALL-NEXT: [[VAL2:%.*]] = insertelement <4 x i32> [[VAL2_UPTO2]], i32 [[VAL2_I3]], i32 3
|
|
; ALL-NEXT: ret <4 x i32> [[VAL2]]
|
|
;
|
|
%val0 = load <4 x i32> , <4 x i32> *%src
|
|
%val1 = insertelement <4 x i32> %val0, i32 %repl, i32 3
|
|
%val2 = shl <4 x i32> <i32 1, i32 2, i32 3, i32 4>, %val1
|
|
ret <4 x i32> %val2
|
|
}
|