1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
|
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr7 -mattr=+vsx | FileCheck %s
target datalayout = "E-m:e-i64:64-n32:64"
target triple = "powerpc64-unknown-linux-gnu"
; This test checks we don't crash on certain matrix operations, more than
; checks the cost of the intrinsics per-se.
define void @matrix() {
; CHECK-LABEL: 'matrix'
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %matrix1 = call <1 x i32> @llvm.matrix.column.major.load.v1i32.i64(ptr nonnull align 4 undef, i64 1, i1 false, i32 1, i32 1)
; CHECK-NEXT: Cost Model: Found an estimated cost of 452 for instruction: %0 = call <10 x i32> @llvm.matrix.multiply.v10i32.v10i32.v1i32(<10 x i32> undef, <1 x i32> %matrix1, i32 10, i32 1, i32 1)
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
;
entry:
%matrix1 = call <1 x i32> @llvm.matrix.column.major.load.v1i32.i64(ptr nonnull align 4 undef, i64 1, i1 false, i32 1, i32 1)
%0 = call <10 x i32> @llvm.matrix.multiply.v10i32.v10i32.v1i32(<10 x i32> undef, <1 x i32> %matrix1, i32 10, i32 1, i32 1)
ret void
}
declare <1 x i32> @llvm.matrix.column.major.load.v1i32.i64(ptr nocapture, i64, i1 immarg, i32 immarg, i32 immarg) #2
declare <10 x i32> @llvm.matrix.multiply.v10i32.v10i32.v1i32(<10 x i32>, <1 x i32>, i32 immarg, i32 immarg, i32 immarg) #3
|
