maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/polly/test/Isl/CodeGen/simple_vec_strides_multidim.ll

77 lines
2.5 KiB
LLVM
Raw Normal View History

Annotation of SIMD loops Use 'mark' nodes annotate a SIMD loop during ScheduleTransformation and skip parallelism checks. The buildbot shows the following compile/execution time changes: Compile time: Improvements Δ Previous Current σ …/gesummv -6.06% 0.2640 0.2480 0.0055 …/gemver -4.46% 0.4480 0.4280 0.0044 …/covariance -4.31% 0.8360 0.8000 0.0065 …/adi -3.23% 0.9920 0.9600 0.0065 …/doitgen -2.53% 0.9480 0.9240 0.0090 …/3mm -2.33% 1.0320 1.0080 0.0087 Execution time: Regressions Δ Previous Current σ …/viterbi 1.70% 5.1840 5.2720 0.0074 …/smallpt 1.06% 12.4920 12.6240 0.0040 Reviewed-by: Tobias Grosser <tobias@grosser.es> Differential Revision: http://reviews.llvm.org/D14491 llvm-svn: 261620
2016-02-23 17:00:13 +08:00
; RUN: opt %loadPolly -polly-opt-isl -polly-codegen -polly-vectorizer=polly -polly-prevect-width=8 -S -dce < %s | FileCheck %s
[Vectorizer] Detect strides in multi-dimensional arrays The original code was only correct for one-dimensional arrays, but derived incorrect strides for multi-dimensional arrays. llvm-svn: 245888
2015-08-25 06:20:46 +08:00
;
; void foo(long n, float A[restrict][n], float B[restrict][n],
; float C[restrict][n], float D[restrict][n]) {
[FIX] Repair test case that was unprofitable llvm-svn: 248124
2015-09-21 00:14:41 +08:00
; for (long i = 0; i < 8; i++)
; for (long j = 0; j < 8; j++)
[Vectorizer] Detect strides in multi-dimensional arrays The original code was only correct for one-dimensional arrays, but derived incorrect strides for multi-dimensional arrays. llvm-svn: 245888
2015-08-25 06:20:46 +08:00
; A[i][j] += B[i][0] + C[i][2 * j] + D[j][0];
; }
;
; CHECK: shufflevector
; CHECK: insertelement
; CHECK: insertelement
; CHECK: insertelement
; CHECK: insertelement
; CHECK: insertelement
; CHECK: insertelement
; CHECK: insertelement
; CHECK: insertelement
[FIX] Repair test case that was unprofitable llvm-svn: 248124
2015-09-21 00:14:41 +08:00
; CHECK: store <8 x float>
[Vectorizer] Detect strides in multi-dimensional arrays The original code was only correct for one-dimensional arrays, but derived incorrect strides for multi-dimensional arrays. llvm-svn: 245888
2015-08-25 06:20:46 +08:00
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
define void @foo(i64 %n, float* noalias %A, float* noalias %B, float* noalias %C, float* noalias %D) {
bb:
br label %bb3
bb3: ; preds = %bb25, %bb
%i.0 = phi i64 [ 0, %bb ], [ %tmp26, %bb25 ]
[FIX] Repair test case that was unprofitable llvm-svn: 248124
2015-09-21 00:14:41 +08:00
%exitcond2 = icmp ne i64 %i.0, 8
[Vectorizer] Detect strides in multi-dimensional arrays The original code was only correct for one-dimensional arrays, but derived incorrect strides for multi-dimensional arrays. llvm-svn: 245888
2015-08-25 06:20:46 +08:00
br i1 %exitcond2, label %bb4, label %bb27
bb4: ; preds = %bb3
br label %bb5
bb5: ; preds = %bb22, %bb4
%j.0 = phi i64 [ 0, %bb4 ], [ %tmp23, %bb22 ]
[FIX] Repair test case that was unprofitable llvm-svn: 248124
2015-09-21 00:14:41 +08:00
%exitcond = icmp ne i64 %j.0, 8
[Vectorizer] Detect strides in multi-dimensional arrays The original code was only correct for one-dimensional arrays, but derived incorrect strides for multi-dimensional arrays. llvm-svn: 245888
2015-08-25 06:20:46 +08:00
br i1 %exitcond, label %bb6, label %bb24
bb6: ; preds = %bb5
%tmp = mul nsw i64 %i.0, %n
%tmp7 = getelementptr inbounds float, float* %B, i64 %tmp
%tmp8 = load float, float* %tmp7, align 4
%tmp9 = shl nsw i64 %j.0, 1
%tmp10 = mul nsw i64 %i.0, %n
%.sum = add i64 %tmp10, %tmp9
%tmp11 = getelementptr inbounds float, float* %C, i64 %.sum
%tmp12 = load float, float* %tmp11, align 4
%tmp13 = fadd float %tmp8, %tmp12
%tmp14 = mul nsw i64 %j.0, %n
%tmp15 = getelementptr inbounds float, float* %D, i64 %tmp14
%tmp16 = load float, float* %tmp15, align 4
%tmp17 = fadd float %tmp13, %tmp16
%tmp18 = mul nsw i64 %i.0, %n
%.sum1 = add i64 %tmp18, %j.0
%tmp19 = getelementptr inbounds float, float* %A, i64 %.sum1
%tmp20 = load float, float* %tmp19, align 4
%tmp21 = fadd float %tmp20, %tmp17
store float %tmp21, float* %tmp19, align 4
br label %bb22
bb22: ; preds = %bb6
%tmp23 = add nsw i64 %j.0, 1
br label %bb5
bb24: ; preds = %bb5
br label %bb25
bb25: ; preds = %bb24
%tmp26 = add nsw i64 %i.0, 1
br label %bb3
bb27: ; preds = %bb3
ret void
}