2a859b2014
The cost of vector instructions has always been high under AArch64, in order to add a high cost for inserts/extracts, shuffles and scalarization. This is a conservative approach to limit the scope of unusual SLP vectorization where the codegen ends up being quite poor, but has always been higher than the correct costs would be for any specific core. This relaxes that, reducing the vector insert/extract cost from 3 to 2. It is a generalization of D142359 to all AArch64 cpus. The ScalarizationOverhead is also overridden for integer vector at the same time, to remove the effect of lane 0 being considered free for integer vectors (something that should only be true for float when scalarizing). The lower insert/extract cost will reduce the cost of insert, extracts, shuffling and scalarization. The adjustments of ScalaizationOverhead will increase the cost on integer, especially for small vectors. The end result will be lower cost for float and long-integer types, some higher cost for some smaller vectors. This, along with the raw insert/extract cost being lower, will generally mean more vectorization from the Loop and SLP vectorizer. We may end up regretting this, as that vectorization is not always profitable. In all the benchmarking I have done this is generally an improvement in the overall performance, and I've attempted to address the places where it wasn't with other costmodel adjustments. Differential Revision: https://reviews.llvm.org/D155459
189 lines
14 KiB
LLVM
189 lines
14 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
|
|
; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output | FileCheck %s
|
|
; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -mcpu=neoverse-n1 | FileCheck %s
|
|
; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -mcpu=neoverse-n2 | FileCheck %s
|
|
; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -mcpu=neoverse-v1 | FileCheck %s
|
|
; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -mcpu=neoverse-v2 | FileCheck %s
|
|
; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -mcpu=kryo | FileCheck %s --check-prefix=KRYO
|
|
|
|
target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
|
|
target triple = "aarch64--linux-gnu"
|
|
|
|
define void @vectorInstrCost() {
|
|
; CHECK-LABEL: 'vectorInstrCost'
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %ta0 = extractelement <8 x i1> undef, i32 0
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %ta1 = extractelement <8 x i1> undef, i32 1
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t1 = extractelement <8 x i8> undef, i32 0
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t2 = extractelement <8 x i8> undef, i32 1
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t3 = extractelement <4 x i16> undef, i32 0
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t4 = extractelement <4 x i16> undef, i32 1
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t5 = extractelement <2 x i32> undef, i32 0
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t6 = extractelement <2 x i32> undef, i32 1
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t7 = extractelement <2 x i64> undef, i32 0
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t8 = extractelement <2 x i64> undef, i32 1
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %t9 = extractelement <4 x half> undef, i32 0
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t10 = extractelement <4 x half> undef, i32 1
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %t11 = extractelement <2 x float> undef, i32 0
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t12 = extractelement <2 x float> undef, i32 1
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %t13 = extractelement <2 x double> undef, i32 0
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t14 = extractelement <2 x double> undef, i32 1
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %t31 = insertelement <8 x i1> undef, i1 false, i32 0
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %t41 = insertelement <8 x i1> undef, i1 true, i32 1
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t30 = insertelement <8 x i8> undef, i8 0, i32 0
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t40 = insertelement <8 x i8> undef, i8 1, i32 1
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t50 = insertelement <4 x i16> undef, i16 2, i32 0
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t60 = insertelement <4 x i16> undef, i16 3, i32 1
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t70 = insertelement <2 x i32> undef, i32 4, i32 0
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t80 = insertelement <2 x i32> undef, i32 5, i32 1
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t90 = insertelement <2 x i64> undef, i64 6, i32 0
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t100 = insertelement <2 x i64> undef, i64 7, i32 1
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %t110 = insertelement <4 x half> zeroinitializer, half 0xH0000, i64 0
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t120 = insertelement <4 x half> zeroinitializer, half 0xH0000, i64 1
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %t130 = insertelement <2 x float> zeroinitializer, float 0.000000e+00, i64 0
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t140 = insertelement <2 x float> zeroinitializer, float 0.000000e+00, i64 1
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %t150 = insertelement <2 x double> zeroinitializer, double 0.000000e+00, i64 0
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t160 = insertelement <2 x double> zeroinitializer, double 0.000000e+00, i64 1
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
|
;
|
|
; KRYO-LABEL: 'vectorInstrCost'
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %ta0 = extractelement <8 x i1> undef, i32 0
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %ta1 = extractelement <8 x i1> undef, i32 1
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t1 = extractelement <8 x i8> undef, i32 0
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t2 = extractelement <8 x i8> undef, i32 1
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t3 = extractelement <4 x i16> undef, i32 0
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t4 = extractelement <4 x i16> undef, i32 1
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t5 = extractelement <2 x i32> undef, i32 0
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t6 = extractelement <2 x i32> undef, i32 1
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t7 = extractelement <2 x i64> undef, i32 0
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t8 = extractelement <2 x i64> undef, i32 1
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %t9 = extractelement <4 x half> undef, i32 0
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t10 = extractelement <4 x half> undef, i32 1
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %t11 = extractelement <2 x float> undef, i32 0
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t12 = extractelement <2 x float> undef, i32 1
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %t13 = extractelement <2 x double> undef, i32 0
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t14 = extractelement <2 x double> undef, i32 1
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %t31 = insertelement <8 x i1> undef, i1 false, i32 0
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %t41 = insertelement <8 x i1> undef, i1 true, i32 1
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t30 = insertelement <8 x i8> undef, i8 0, i32 0
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t40 = insertelement <8 x i8> undef, i8 1, i32 1
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t50 = insertelement <4 x i16> undef, i16 2, i32 0
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t60 = insertelement <4 x i16> undef, i16 3, i32 1
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t70 = insertelement <2 x i32> undef, i32 4, i32 0
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t80 = insertelement <2 x i32> undef, i32 5, i32 1
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t90 = insertelement <2 x i64> undef, i64 6, i32 0
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t100 = insertelement <2 x i64> undef, i64 7, i32 1
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %t110 = insertelement <4 x half> zeroinitializer, half 0xH0000, i64 0
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t120 = insertelement <4 x half> zeroinitializer, half 0xH0000, i64 1
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %t130 = insertelement <2 x float> zeroinitializer, float 0.000000e+00, i64 0
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t140 = insertelement <2 x float> zeroinitializer, float 0.000000e+00, i64 1
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %t150 = insertelement <2 x double> zeroinitializer, double 0.000000e+00, i64 0
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %t160 = insertelement <2 x double> zeroinitializer, double 0.000000e+00, i64 1
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
|
;
|
|
|
|
%ta0 = extractelement <8 x i1> undef, i32 0
|
|
%ta1 = extractelement <8 x i1> undef, i32 1
|
|
%t1 = extractelement <8 x i8> undef, i32 0
|
|
%t2 = extractelement <8 x i8> undef, i32 1
|
|
%t3 = extractelement <4 x i16> undef, i32 0
|
|
%t4 = extractelement <4 x i16> undef, i32 1
|
|
%t5 = extractelement <2 x i32> undef, i32 0
|
|
%t6 = extractelement <2 x i32> undef, i32 1
|
|
%t7 = extractelement <2 x i64> undef, i32 0
|
|
%t8 = extractelement <2 x i64> undef, i32 1
|
|
%t9 = extractelement <4 x half> undef, i32 0
|
|
%t10 = extractelement <4 x half> undef, i32 1
|
|
%t11 = extractelement <2 x float> undef, i32 0
|
|
%t12 = extractelement <2 x float> undef, i32 1
|
|
%t13 = extractelement <2 x double> undef, i32 0
|
|
%t14 = extractelement <2 x double> undef, i32 1
|
|
|
|
%t31 = insertelement <8 x i1> undef, i1 0, i32 0
|
|
%t41 = insertelement <8 x i1> undef, i1 1, i32 1
|
|
%t30 = insertelement <8 x i8> undef, i8 0, i32 0
|
|
%t40 = insertelement <8 x i8> undef, i8 1, i32 1
|
|
%t50 = insertelement <4 x i16> undef, i16 2, i32 0
|
|
%t60 = insertelement <4 x i16> undef, i16 3, i32 1
|
|
%t70 = insertelement <2 x i32> undef, i32 4, i32 0
|
|
%t80 = insertelement <2 x i32> undef, i32 5, i32 1
|
|
%t90 = insertelement <2 x i64> undef, i64 6, i32 0
|
|
%t100 = insertelement <2 x i64> undef, i64 7, i32 1
|
|
%t110 = insertelement <4 x half> zeroinitializer, half 0.000000e+00, i64 0
|
|
%t120 = insertelement <4 x half> zeroinitializer, half 0.000000e+00, i64 1
|
|
%t130 = insertelement <2 x float> zeroinitializer, float 0.000000e+00, i64 0
|
|
%t140 = insertelement <2 x float> zeroinitializer, float 0.000000e+00, i64 1
|
|
%t150 = insertelement <2 x double> zeroinitializer, double 0.000000e+00, i64 0
|
|
%t160 = insertelement <2 x double> zeroinitializer, double 0.000000e+00, i64 1
|
|
ret void
|
|
}
|
|
|
|
;; LD1: Load one single-element structure to one lane of one register.
|
|
|
|
define <8 x i8> @LD1_B(<8 x i8> %vec, ptr noundef %i) {
|
|
; CHECK-LABEL: 'LD1_B'
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v1 = load i8, ptr %i, align 1
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2 = insertelement <8 x i8> %vec, i8 %v1, i32 1
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i8> %v2
|
|
;
|
|
; KRYO-LABEL: 'LD1_B'
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v1 = load i8, ptr %i, align 1
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2 = insertelement <8 x i8> %vec, i8 %v1, i32 1
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <8 x i8> %v2
|
|
;
|
|
entry:
|
|
%v1 = load i8, ptr %i, align 1
|
|
%v2 = insertelement <8 x i8> %vec, i8 %v1, i32 1
|
|
ret <8x i8> %v2
|
|
}
|
|
|
|
define <4 x i16> @LD1_H(<4 x i16> %vec, ptr noundef %i) {
|
|
; CHECK-LABEL: 'LD1_H'
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v1 = load i16, ptr %i, align 2
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2 = insertelement <4 x i16> %vec, i16 %v1, i32 2
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i16> %v2
|
|
;
|
|
; KRYO-LABEL: 'LD1_H'
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v1 = load i16, ptr %i, align 2
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2 = insertelement <4 x i16> %vec, i16 %v1, i32 2
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i16> %v2
|
|
;
|
|
entry:
|
|
%v1 = load i16, ptr %i, align 2
|
|
%v2 = insertelement <4 x i16> %vec, i16 %v1, i32 2
|
|
ret <4 x i16> %v2
|
|
}
|
|
|
|
define <4 x i32> @LD1_W(<4 x i32> %vec, ptr noundef %i) {
|
|
; CHECK-LABEL: 'LD1_W'
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v1 = load i32, ptr %i, align 4
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2 = insertelement <4 x i32> %vec, i32 %v1, i32 3
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %v2
|
|
;
|
|
; KRYO-LABEL: 'LD1_W'
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v1 = load i32, ptr %i, align 4
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2 = insertelement <4 x i32> %vec, i32 %v1, i32 3
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <4 x i32> %v2
|
|
;
|
|
entry:
|
|
%v1 = load i32, ptr %i, align 4
|
|
%v2 = insertelement <4 x i32> %vec, i32 %v1, i32 3
|
|
ret <4 x i32> %v2
|
|
}
|
|
|
|
define <2 x i64> @LD1_X(<2 x i64> %vec, ptr noundef %i) {
|
|
; CHECK-LABEL: 'LD1_X'
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v1 = load i64, ptr %i, align 8
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2 = insertelement <2 x i64> %vec, i64 %v1, i32 0
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %v2
|
|
;
|
|
; KRYO-LABEL: 'LD1_X'
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v1 = load i64, ptr %i, align 8
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2 = insertelement <2 x i64> %vec, i64 %v1, i32 0
|
|
; KRYO-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret <2 x i64> %v2
|
|
;
|
|
entry:
|
|
%v1 = load i64, ptr %i, align 8
|
|
%v2 = insertelement <2 x i64> %vec, i64 %v1, i32 0
|
|
ret <2 x i64> %v2
|
|
}
|