RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 20:51:52 +01:00
Code Issues Projects Releases Wiki Activity

[NFC][Scalarizer] Also scalarize loads in newly-added tests

Browse Source 
Should help better showcase improvements
This commit is contained in:
Roman Lebedev 2020-07-03 02:37:29 +03:00
parent 0ea8f6b013
commit f3b790c8b1
4 changed files with 58 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
test/Transforms/Scalarizer/constant-extractelement.ll
View File

@ -1,19 +1,22 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt %s -scalarizer -dce -S | FileCheck --check-prefixes=ALL %s
; 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: [[VAL0:%.*]] = load <4 x i32>, <4 x i32>* [[SRC:%.*]], align 16
; ALL-NEXT: [[VAL0_I0:%.*]] = extractelement <4 x i32> [[VAL0]], i32 0
; 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: [[SRC_I3:%.*]] = getelementptr i32, i32* [[SRC_I0]], i32 3
; ALL-NEXT: [[VAL0_I3:%.*]] = load i32, i32* [[SRC_I3]], align 4
; ALL-NEXT: [[VAL1_I0:%.*]] = shl i32 1, [[VAL0_I0]]
; ALL-NEXT: [[VAL0_I1:%.*]] = extractelement <4 x i32> [[VAL0]], i32 1
; ALL-NEXT: [[VAL1_I1:%.*]] = shl i32 2, [[VAL0_I1]]
; ALL-NEXT: [[VAL0_I2:%.*]] = extractelement <4 x i32> [[VAL0]], i32 2
; ALL-NEXT: [[VAL1_I2:%.*]] = shl i32 3, [[VAL0_I2]]
; ALL-NEXT: [[VAL0_I3:%.*]] = extractelement <4 x i32> [[VAL0]], i32 3
; ALL-NEXT: [[VAL1_I3:%.*]] = shl i32 4, [[VAL0_I3]]
; ALL-NEXT: [[VAL1_UPTO0:%.*]] = insertelement <4 x i32> undef, i32 [[VAL1_I0]], i32 0
; ALL-NEXT: [[VAL1_UPTO1:%.*]] = insertelement <4 x i32> [[VAL1_UPTO0]], i32 [[VAL1_I1]], i32 1

27
test/Transforms/Scalarizer/constant-insertelement.ll
View File

@ -1,18 +1,29 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt %s -scalarizer -dce -S | FileCheck --check-prefixes=ALL %s
; 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: [[VAL0:%.*]] = load <4 x i32>, <4 x i32>* [[SRC:%.*]], align 16
; ALL-NEXT: [[VAL0_I0:%.*]] = extractelement <4 x i32> [[VAL0]], i32 0
; ALL-NEXT: [[VAL2_I0:%.*]] = shl i32 1, [[VAL0_I0]]
; ALL-NEXT: [[VAL0_I1:%.*]] = extractelement <4 x i32> [[VAL0]], i32 1
; ALL-NEXT: [[VAL2_I1:%.*]] = shl i32 2, [[VAL0_I1]]
; ALL-NEXT: [[VAL0_I2:%.*]] = extractelement <4 x i32> [[VAL0]], i32 2
; ALL-NEXT: [[VAL2_I2:%.*]] = shl i32 3, [[VAL0_I2]]
; 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: [[SRC_I3:%.*]] = getelementptr i32, i32* [[SRC_I0]], i32 3
; ALL-NEXT: [[VAL0_I3:%.*]] = load i32, i32* [[SRC_I3]], align 4
; ALL-NEXT: [[VAL0_UPTO0:%.*]] = insertelement <4 x i32> undef, i32 [[VAL0_I0]], i32 0
; ALL-NEXT: [[VAL0_UPTO1:%.*]] = insertelement <4 x i32> [[VAL0_UPTO0]], i32 [[VAL0_I1]], i32 1
; ALL-NEXT: [[VAL0_UPTO2:%.*]] = insertelement <4 x i32> [[VAL0_UPTO1]], i32 [[VAL0_I2]], i32 2
; ALL-NEXT: [[VAL0:%.*]] = insertelement <4 x i32> [[VAL0_UPTO2]], i32 [[VAL0_I3]], i32 3
; ALL-NEXT: [[VAL0_I01:%.*]] = extractelement <4 x i32> [[VAL0]], i32 0
; ALL-NEXT: [[VAL2_I0:%.*]] = shl i32 1, [[VAL0_I01]]
; ALL-NEXT: [[VAL0_I12:%.*]] = extractelement <4 x i32> [[VAL0]], i32 1
; ALL-NEXT: [[VAL2_I1:%.*]] = shl i32 2, [[VAL0_I12]]
; ALL-NEXT: [[VAL0_I23:%.*]] = extractelement <4 x i32> [[VAL0]], i32 2
; ALL-NEXT: [[VAL2_I2:%.*]] = shl i32 3, [[VAL0_I23]]
; ALL-NEXT: [[VAL2_I3:%.*]] = shl i32 4, [[REPL:%.*]]
; ALL-NEXT: [[VAL2_UPTO0:%.*]] = insertelement <4 x i32> undef, i32 [[VAL2_I0]], i32 0
; ALL-NEXT: [[VAL2_UPTO1:%.*]] = insertelement <4 x i32> [[VAL2_UPTO0]], i32 [[VAL2_I1]], i32 1

15
test/Transforms/Scalarizer/variable-extractelement.ll
View File

@ -1,5 +1,5 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt %s -scalarizer -dce -S | FileCheck --check-prefixes=ALL %s
; 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"
@ -15,14 +15,17 @@ define i32 @f1(<4 x i32> %src, i32 %index) {
define i32 @f2(<4 x i32> *%src, i32 %index) {
; ALL-LABEL: @f2(
; ALL-NEXT: [[VAL0:%.*]] = load <4 x i32>, <4 x i32>* [[SRC:%.*]], align 16
; ALL-NEXT: [[VAL0_I0:%.*]] = extractelement <4 x i32> [[VAL0]], i32 0
; 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: [[SRC_I3:%.*]] = getelementptr i32, i32* [[SRC_I0]], i32 3
; ALL-NEXT: [[VAL0_I3:%.*]] = load i32, i32* [[SRC_I3]], align 4
; ALL-NEXT: [[VAL1_I0:%.*]] = shl i32 1, [[VAL0_I0]]
; ALL-NEXT: [[VAL0_I1:%.*]] = extractelement <4 x i32> [[VAL0]], i32 1
; ALL-NEXT: [[VAL1_I1:%.*]] = shl i32 2, [[VAL0_I1]]
; ALL-NEXT: [[VAL0_I2:%.*]] = extractelement <4 x i32> [[VAL0]], i32 2
; ALL-NEXT: [[VAL1_I2:%.*]] = shl i32 3, [[VAL0_I2]]
; ALL-NEXT: [[VAL0_I3:%.*]] = extractelement <4 x i32> [[VAL0]], i32 3
; ALL-NEXT: [[VAL1_I3:%.*]] = shl i32 4, [[VAL0_I3]]
; ALL-NEXT: [[VAL1_UPTO0:%.*]] = insertelement <4 x i32> undef, i32 [[VAL1_I0]], i32 0
; ALL-NEXT: [[VAL1_UPTO1:%.*]] = insertelement <4 x i32> [[VAL1_UPTO0]], i32 [[VAL1_I1]], i32 1

28
test/Transforms/Scalarizer/variable-insertelement.ll
View File

@ -1,5 +1,5 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt %s -scalarizer -dce -S | FileCheck --check-prefixes=ALL %s
; 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"
@ -15,7 +15,22 @@ define <4 x i32> @f1(<4 x i32> %src, i32 %val, i32 %index) {
define void @f2(<4 x i32> *%dest, <4 x i32> *%src, i32 %index) {
; ALL-LABEL: @f2(
; ALL-NEXT: [[VAL0:%.*]] = load <4 x i32>, <4 x i32>* [[SRC:%.*]], align 16
; ALL-NEXT: [[DEST_I0:%.*]] = bitcast <4 x i32>* [[DEST:%.*]] to i32*
; ALL-NEXT: [[DEST_I1:%.*]] = getelementptr i32, i32* [[DEST_I0]], i32 1
; ALL-NEXT: [[DEST_I2:%.*]] = getelementptr i32, i32* [[DEST_I0]], i32 2
; ALL-NEXT: [[DEST_I3:%.*]] = getelementptr i32, i32* [[DEST_I0]], i32 3
; 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: [[SRC_I3:%.*]] = getelementptr i32, i32* [[SRC_I0]], i32 3
; ALL-NEXT: [[VAL0_I3:%.*]] = load i32, i32* [[SRC_I3]], align 4
; ALL-NEXT: [[VAL0_UPTO0:%.*]] = insertelement <4 x i32> undef, i32 [[VAL0_I0]], i32 0
; ALL-NEXT: [[VAL0_UPTO1:%.*]] = insertelement <4 x i32> [[VAL0_UPTO0]], i32 [[VAL0_I1]], i32 1
; ALL-NEXT: [[VAL0_UPTO2:%.*]] = insertelement <4 x i32> [[VAL0_UPTO1]], i32 [[VAL0_I2]], i32 2
; ALL-NEXT: [[VAL0:%.*]] = insertelement <4 x i32> [[VAL0_UPTO2]], i32 [[VAL0_I3]], i32 3
; ALL-NEXT: [[VAL1:%.*]] = insertelement <4 x i32> [[VAL0]], i32 1, i32 [[INDEX:%.*]]
; ALL-NEXT: [[VAL1_I0:%.*]] = extractelement <4 x i32> [[VAL1]], i32 0
; ALL-NEXT: [[VAL2_I0:%.*]] = shl i32 1, [[VAL1_I0]]
@ -25,11 +40,10 @@ define void @f2(<4 x i32> *%dest, <4 x i32> *%src, i32 %index) {
; ALL-NEXT: [[VAL2_I2:%.*]] = shl i32 3, [[VAL1_I2]]
; ALL-NEXT: [[VAL1_I3:%.*]] = extractelement <4 x i32> [[VAL1]], i32 3
; ALL-NEXT: [[VAL2_I3:%.*]] = shl i32 4, [[VAL1_I3]]
; ALL-NEXT: [[VAL2_UPTO0:%.*]] = insertelement <4 x i32> undef, 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: store <4 x i32> [[VAL2]], <4 x i32>* [[DEST:%.*]], align 16
; ALL-NEXT: store i32 [[VAL2_I0]], i32* [[DEST_I0]], align 16
; ALL-NEXT: store i32 [[VAL2_I1]], i32* [[DEST_I1]], align 4
; ALL-NEXT: store i32 [[VAL2_I2]], i32* [[DEST_I2]], align 8
; ALL-NEXT: store i32 [[VAL2_I3]], i32* [[DEST_I3]], align 4
; ALL-NEXT: ret void
;
%val0 = load <4 x i32> , <4 x i32> *%src