llvm-project/polly/test/ScheduleOptimizer/pattern-matching-based-opts...

66 lines
2.5 KiB
LLVM
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

; RUN: opt %loadPolly -polly-opt-isl -polly-pattern-matching-based-opts=true -debug < %s 2>&1 | FileCheck %s
; REQUIRES: asserts
;
; /* C := alpha*A*B + beta*C */
; for (i = 0; i < _PB_NI; i++)
; for (j = 0; j < _PB_NJ; j += 2)
; {
; C[i][j] *= beta;
; for (k = 0; k < _PB_NK; ++k)
; C[i][j] += alpha * A[i][k] * B[k][j];
; }
;
; Check that we wont detect the matrix multiplication pattern,
; if, for example, there are memory accesses that have stride 2
; after the interchanging of loops.
;
; CHECK-NOT: The matrix multiplication pattern was detected
;
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-unknown"
define internal void @kernel_gemm(i32 %arg, i32 %arg1, i32 %arg2, double %arg3, double %arg4, [1056 x double]* %arg5, [1024 x double]* %arg6, [1056 x double]* %arg7) #0 {
bb:
br label %bb8
bb8: ; preds = %bb29, %bb
%tmp = phi i64 [ 0, %bb ], [ %tmp30, %bb29 ]
br label %bb9
bb9: ; preds = %bb26, %bb8
%tmp10 = phi i64 [ 0, %bb8 ], [ %tmp27, %bb26 ]
%tmp11 = getelementptr inbounds [1056 x double], [1056 x double]* %arg5, i64 %tmp, i64 %tmp10
%tmp12 = load double, double* %tmp11, align 8
%tmp13 = fmul double %tmp12, %arg4
store double %tmp13, double* %tmp11, align 8
br label %Copy_0
Copy_0: ; preds = %Copy_0, %bb9
%tmp15 = phi i64 [ 0, %bb9 ], [ %tmp24, %Copy_0 ]
%tmp16 = getelementptr inbounds [1024 x double], [1024 x double]* %arg6, i64 %tmp, i64 %tmp15
%tmp17 = load double, double* %tmp16, align 8
%tmp18 = fmul double %tmp17, %arg3
%tmp19 = getelementptr inbounds [1056 x double], [1056 x double]* %arg7, i64 %tmp15, i64 %tmp10
%tmp20 = load double, double* %tmp19, align 8
%tmp21 = fmul double %tmp18, %tmp20
%tmp22 = load double, double* %tmp11, align 8
%tmp23 = fadd double %tmp22, %tmp21
store double %tmp23, double* %tmp11, align 8
%tmp24 = add nuw nsw i64 %tmp15, 1
%tmp25 = icmp ne i64 %tmp24, 1024
br i1 %tmp25, label %Copy_0, label %bb26
bb26: ; preds = %Copy_0
%tmp27 = add nuw nsw i64 %tmp10, 2
%tmp28 = icmp ne i64 %tmp27, 1056
br i1 %tmp28, label %bb9, label %bb29
bb29: ; preds = %bb26
%tmp30 = add nuw nsw i64 %tmp, 1
%tmp31 = icmp ne i64 %tmp30, 1056
br i1 %tmp31, label %bb8, label %bb32
bb32: ; preds = %bb29
ret void
}