mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2025-01-31 20:51:52 +01:00
2e1b0642c7
With custom lowering for vector MULLH{S,U}, it is now profitable to
vectorize a divide by constant loop for the custom types (v16i8, v8i16,
and v4i32). The cost if based on TargetLowering::Build{S,U}DIV which
uses a multiply by constant plus adjustment to express a divide by
constant.
Both {u,s}mull{2} are expressed as Instruction::Mul and shifts by
Instruction::AShr.
llvm-svn: 331873
46 lines
2.3 KiB
LLVM
46 lines
2.3 KiB
LLVM
; RUN: opt -cost-model -analyze -mtriple=aarch64-linux-gnu -mattr=+neon < %s | FileCheck %s
|
|
|
|
; Verify the cost of integer division by constant.
|
|
|
|
define <16 x i8> @sdiv8xi16(<16 x i8> %x) {
|
|
; CHECK-LABEL: 'Cost Model Analysis' for function 'sdiv8xi16':
|
|
; CHECK: Found an estimated cost of 9 for instruction: %div = sdiv <16 x i8> %x, <i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9>
|
|
%div = sdiv <16 x i8> %x, <i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9>
|
|
ret <16 x i8> %div
|
|
}
|
|
|
|
define <8 x i16> @sdiv16xi8(<8 x i16> %x) {
|
|
; CHECK-LABEL: 'Cost Model Analysis' for function 'sdiv16xi8':
|
|
; CHECK: Found an estimated cost of 9 for instruction: %div = sdiv <8 x i16> %x, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
|
|
%div = sdiv <8 x i16> %x, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
|
|
ret <8 x i16> %div
|
|
}
|
|
|
|
define <4 x i32> @sdiv32xi4(<4 x i32> %x) {
|
|
; CHECK-LABEL: 'Cost Model Analysis' for function 'sdiv32xi4':
|
|
; CHECK: Found an estimated cost of 9 for instruction: %div = sdiv <4 x i32> %x, <i32 9, i32 9, i32 9, i32 9>
|
|
%div = sdiv <4 x i32> %x, <i32 9, i32 9, i32 9, i32 9>
|
|
ret <4 x i32> %div
|
|
}
|
|
|
|
define <16 x i8> @udiv8xi16(<16 x i8> %x) {
|
|
; CHECK-LABEL: 'Cost Model Analysis' for function 'udiv8xi16':
|
|
; CHECK: Found an estimated cost of 9 for instruction: %div = udiv <16 x i8> %x, <i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9>
|
|
%div = udiv <16 x i8> %x, <i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9, i8 9>
|
|
ret <16 x i8> %div
|
|
}
|
|
|
|
define <8 x i16> @udiv16xi8(<8 x i16> %x) {
|
|
; CHECK-LABEL: 'Cost Model Analysis' for function 'udiv16xi8':
|
|
; CHECK: Found an estimated cost of 9 for instruction: %div = udiv <8 x i16> %x, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
|
|
%div = udiv <8 x i16> %x, <i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9, i16 9>
|
|
ret <8 x i16> %div
|
|
}
|
|
|
|
define <4 x i32> @udiv32xi4(<4 x i32> %x) {
|
|
; CHECK-LABEL: Printing analysis 'Cost Model Analysis' for function 'udiv32xi4':
|
|
; CHECK: Found an estimated cost of 9 for instruction: %div = udiv <4 x i32> %x, <i32 9, i32 9, i32 9, i32 9>
|
|
%div = udiv <4 x i32> %x, <i32 9, i32 9, i32 9, i32 9>
|
|
ret <4 x i32> %div
|
|
}
|