dd2dbf7ee2
As a followup to D95291, getOperandsScalarizationOverhead was still using a VF as a vector factor if the arguments were scalar, and would assert on certain matrix intrinsics with differently sized vector arguments. This patch removes the VF arg, instead passing the Types through directly. This should allow it to more accurately compute the cost without having to guess at which operands will be vectorized, something difficult with more complex intrinsics. This adjusts one SVE test as it is now calling the wrong intrinsic vs veccall. Without invalid InstructCosts the cost of the scalarized intrinsic is too low. This should get fixed when the cost of scalarization is accounted for with scalable types. Differential Revision: https://reviews.llvm.org/D96287
23 lines
1.4 KiB
LLVM
23 lines
1.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
|
|
; RUN: opt < %s -cost-model -analyze -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(i32* 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(i32* 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(i32* 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
|