6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-12-28 04:33:05 +00:00
Code Issues Projects Releases Wiki Activity
d8e2f1757d
llvm-6502/test/Transforms/SLPVectorizer/X86/saxpy.ll

62 lines
2.1 KiB
LLVM
Raw Normal View History

Add support for bottom-up SLP vectorization infrastructure. This commit adds the infrastructure for performing bottom-up SLP vectorization (and other optimizations) on parallel computations. The infrastructure has three potential users: 1. The loop vectorizer needs to be able to vectorize AOS data structures such as (sum += A[i] + A[i+1]). 2. The BB-vectorizer needs this infrastructure for bottom-up SLP vectorization, because bottom-up vectorization is faster to compute. 3. A loop-roller needs to be able to analyze consecutive chains and roll them into a loop, in order to reduce code size. A loop roller does not need to create vector instructions, and this infrastructure separates the chain analysis from the vectorization. This patch also includes a simple (100 LOC) bottom up SLP vectorizer that uses the infrastructure, and can vectorize this code: void SAXPY(int *x, int *y, int a, int i) { x[i] = a * x[i] + y[i]; x[i+1] = a * x[i+1] + y[i+1]; x[i+2] = a * x[i+2] + y[i+2]; x[i+3] = a * x[i+3] + y[i+3]; } git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179117 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-09 19:44:35 +00:00
; RUN: opt < %s -basicaa -slp-vectorizer -dce -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.8.0"
; SLP vectorization example from http://cs.stanford.edu/people/eschkufz/research/asplos291-schkufza.pdf
;CHECK: SAXPY
;CHECK: mul <4 x i32>
;CHECK: ret
Remove unused function attributes. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179476 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-14 05:47:04 +00:00
define void @SAXPY(i32* noalias nocapture %x, i32* noalias nocapture %y, i32 %a, i64 %i) {
Add support for bottom-up SLP vectorization infrastructure. This commit adds the infrastructure for performing bottom-up SLP vectorization (and other optimizations) on parallel computations. The infrastructure has three potential users: 1. The loop vectorizer needs to be able to vectorize AOS data structures such as (sum += A[i] + A[i+1]). 2. The BB-vectorizer needs this infrastructure for bottom-up SLP vectorization, because bottom-up vectorization is faster to compute. 3. A loop-roller needs to be able to analyze consecutive chains and roll them into a loop, in order to reduce code size. A loop roller does not need to create vector instructions, and this infrastructure separates the chain analysis from the vectorization. This patch also includes a simple (100 LOC) bottom up SLP vectorizer that uses the infrastructure, and can vectorize this code: void SAXPY(int *x, int *y, int a, int i) { x[i] = a * x[i] + y[i]; x[i+1] = a * x[i+1] + y[i+1]; x[i+2] = a * x[i+2] + y[i+2]; x[i+3] = a * x[i+3] + y[i+3]; } git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179117 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-09 19:44:35 +00:00
%1 = getelementptr inbounds i32* %x, i64 %i
Remove unused function attributes. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179476 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-14 05:47:04 +00:00
%2 = load i32* %1, align 4
Add support for bottom-up SLP vectorization infrastructure. This commit adds the infrastructure for performing bottom-up SLP vectorization (and other optimizations) on parallel computations. The infrastructure has three potential users: 1. The loop vectorizer needs to be able to vectorize AOS data structures such as (sum += A[i] + A[i+1]). 2. The BB-vectorizer needs this infrastructure for bottom-up SLP vectorization, because bottom-up vectorization is faster to compute. 3. A loop-roller needs to be able to analyze consecutive chains and roll them into a loop, in order to reduce code size. A loop roller does not need to create vector instructions, and this infrastructure separates the chain analysis from the vectorization. This patch also includes a simple (100 LOC) bottom up SLP vectorizer that uses the infrastructure, and can vectorize this code: void SAXPY(int *x, int *y, int a, int i) { x[i] = a * x[i] + y[i]; x[i+1] = a * x[i+1] + y[i+1]; x[i+2] = a * x[i+2] + y[i+2]; x[i+3] = a * x[i+3] + y[i+3]; } git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179117 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-09 19:44:35 +00:00
%3 = mul nsw i32 %2, %a
%4 = getelementptr inbounds i32* %y, i64 %i
Remove unused function attributes. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179476 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-14 05:47:04 +00:00
%5 = load i32* %4, align 4
Add support for bottom-up SLP vectorization infrastructure. This commit adds the infrastructure for performing bottom-up SLP vectorization (and other optimizations) on parallel computations. The infrastructure has three potential users: 1. The loop vectorizer needs to be able to vectorize AOS data structures such as (sum += A[i] + A[i+1]). 2. The BB-vectorizer needs this infrastructure for bottom-up SLP vectorization, because bottom-up vectorization is faster to compute. 3. A loop-roller needs to be able to analyze consecutive chains and roll them into a loop, in order to reduce code size. A loop roller does not need to create vector instructions, and this infrastructure separates the chain analysis from the vectorization. This patch also includes a simple (100 LOC) bottom up SLP vectorizer that uses the infrastructure, and can vectorize this code: void SAXPY(int *x, int *y, int a, int i) { x[i] = a * x[i] + y[i]; x[i+1] = a * x[i+1] + y[i+1]; x[i+2] = a * x[i+2] + y[i+2]; x[i+3] = a * x[i+3] + y[i+3]; } git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179117 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-09 19:44:35 +00:00
%6 = add nsw i32 %3, %5
Remove unused function attributes. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179476 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-14 05:47:04 +00:00
store i32 %6, i32* %1, align 4
Add support for bottom-up SLP vectorization infrastructure. This commit adds the infrastructure for performing bottom-up SLP vectorization (and other optimizations) on parallel computations. The infrastructure has three potential users: 1. The loop vectorizer needs to be able to vectorize AOS data structures such as (sum += A[i] + A[i+1]). 2. The BB-vectorizer needs this infrastructure for bottom-up SLP vectorization, because bottom-up vectorization is faster to compute. 3. A loop-roller needs to be able to analyze consecutive chains and roll them into a loop, in order to reduce code size. A loop roller does not need to create vector instructions, and this infrastructure separates the chain analysis from the vectorization. This patch also includes a simple (100 LOC) bottom up SLP vectorizer that uses the infrastructure, and can vectorize this code: void SAXPY(int *x, int *y, int a, int i) { x[i] = a * x[i] + y[i]; x[i+1] = a * x[i+1] + y[i+1]; x[i+2] = a * x[i+2] + y[i+2]; x[i+3] = a * x[i+3] + y[i+3]; } git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179117 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-09 19:44:35 +00:00
%7 = add i64 %i, 1
%8 = getelementptr inbounds i32* %x, i64 %7
Remove unused function attributes. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179476 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-14 05:47:04 +00:00
%9 = load i32* %8, align 4
Add support for bottom-up SLP vectorization infrastructure. This commit adds the infrastructure for performing bottom-up SLP vectorization (and other optimizations) on parallel computations. The infrastructure has three potential users: 1. The loop vectorizer needs to be able to vectorize AOS data structures such as (sum += A[i] + A[i+1]). 2. The BB-vectorizer needs this infrastructure for bottom-up SLP vectorization, because bottom-up vectorization is faster to compute. 3. A loop-roller needs to be able to analyze consecutive chains and roll them into a loop, in order to reduce code size. A loop roller does not need to create vector instructions, and this infrastructure separates the chain analysis from the vectorization. This patch also includes a simple (100 LOC) bottom up SLP vectorizer that uses the infrastructure, and can vectorize this code: void SAXPY(int *x, int *y, int a, int i) { x[i] = a * x[i] + y[i]; x[i+1] = a * x[i+1] + y[i+1]; x[i+2] = a * x[i+2] + y[i+2]; x[i+3] = a * x[i+3] + y[i+3]; } git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179117 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-09 19:44:35 +00:00
%10 = mul nsw i32 %9, %a
%11 = getelementptr inbounds i32* %y, i64 %7
Remove unused function attributes. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179476 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-14 05:47:04 +00:00
%12 = load i32* %11, align 4
Add support for bottom-up SLP vectorization infrastructure. This commit adds the infrastructure for performing bottom-up SLP vectorization (and other optimizations) on parallel computations. The infrastructure has three potential users: 1. The loop vectorizer needs to be able to vectorize AOS data structures such as (sum += A[i] + A[i+1]). 2. The BB-vectorizer needs this infrastructure for bottom-up SLP vectorization, because bottom-up vectorization is faster to compute. 3. A loop-roller needs to be able to analyze consecutive chains and roll them into a loop, in order to reduce code size. A loop roller does not need to create vector instructions, and this infrastructure separates the chain analysis from the vectorization. This patch also includes a simple (100 LOC) bottom up SLP vectorizer that uses the infrastructure, and can vectorize this code: void SAXPY(int *x, int *y, int a, int i) { x[i] = a * x[i] + y[i]; x[i+1] = a * x[i+1] + y[i+1]; x[i+2] = a * x[i+2] + y[i+2]; x[i+3] = a * x[i+3] + y[i+3]; } git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179117 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-09 19:44:35 +00:00
%13 = add nsw i32 %10, %12
Remove unused function attributes. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179476 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-14 05:47:04 +00:00
store i32 %13, i32* %8, align 4
Add support for bottom-up SLP vectorization infrastructure. This commit adds the infrastructure for performing bottom-up SLP vectorization (and other optimizations) on parallel computations. The infrastructure has three potential users: 1. The loop vectorizer needs to be able to vectorize AOS data structures such as (sum += A[i] + A[i+1]). 2. The BB-vectorizer needs this infrastructure for bottom-up SLP vectorization, because bottom-up vectorization is faster to compute. 3. A loop-roller needs to be able to analyze consecutive chains and roll them into a loop, in order to reduce code size. A loop roller does not need to create vector instructions, and this infrastructure separates the chain analysis from the vectorization. This patch also includes a simple (100 LOC) bottom up SLP vectorizer that uses the infrastructure, and can vectorize this code: void SAXPY(int *x, int *y, int a, int i) { x[i] = a * x[i] + y[i]; x[i+1] = a * x[i+1] + y[i+1]; x[i+2] = a * x[i+2] + y[i+2]; x[i+3] = a * x[i+3] + y[i+3]; } git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179117 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-09 19:44:35 +00:00
%14 = add i64 %i, 2
%15 = getelementptr inbounds i32* %x, i64 %14
Remove unused function attributes. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179476 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-14 05:47:04 +00:00
%16 = load i32* %15, align 4
Add support for bottom-up SLP vectorization infrastructure. This commit adds the infrastructure for performing bottom-up SLP vectorization (and other optimizations) on parallel computations. The infrastructure has three potential users: 1. The loop vectorizer needs to be able to vectorize AOS data structures such as (sum += A[i] + A[i+1]). 2. The BB-vectorizer needs this infrastructure for bottom-up SLP vectorization, because bottom-up vectorization is faster to compute. 3. A loop-roller needs to be able to analyze consecutive chains and roll them into a loop, in order to reduce code size. A loop roller does not need to create vector instructions, and this infrastructure separates the chain analysis from the vectorization. This patch also includes a simple (100 LOC) bottom up SLP vectorizer that uses the infrastructure, and can vectorize this code: void SAXPY(int *x, int *y, int a, int i) { x[i] = a * x[i] + y[i]; x[i+1] = a * x[i+1] + y[i+1]; x[i+2] = a * x[i+2] + y[i+2]; x[i+3] = a * x[i+3] + y[i+3]; } git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179117 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-09 19:44:35 +00:00
%17 = mul nsw i32 %16, %a
%18 = getelementptr inbounds i32* %y, i64 %14
Remove unused function attributes. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179476 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-14 05:47:04 +00:00
%19 = load i32* %18, align 4
Add support for bottom-up SLP vectorization infrastructure. This commit adds the infrastructure for performing bottom-up SLP vectorization (and other optimizations) on parallel computations. The infrastructure has three potential users: 1. The loop vectorizer needs to be able to vectorize AOS data structures such as (sum += A[i] + A[i+1]). 2. The BB-vectorizer needs this infrastructure for bottom-up SLP vectorization, because bottom-up vectorization is faster to compute. 3. A loop-roller needs to be able to analyze consecutive chains and roll them into a loop, in order to reduce code size. A loop roller does not need to create vector instructions, and this infrastructure separates the chain analysis from the vectorization. This patch also includes a simple (100 LOC) bottom up SLP vectorizer that uses the infrastructure, and can vectorize this code: void SAXPY(int *x, int *y, int a, int i) { x[i] = a * x[i] + y[i]; x[i+1] = a * x[i+1] + y[i+1]; x[i+2] = a * x[i+2] + y[i+2]; x[i+3] = a * x[i+3] + y[i+3]; } git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179117 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-09 19:44:35 +00:00
%20 = add nsw i32 %17, %19
Remove unused function attributes. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179476 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-14 05:47:04 +00:00
store i32 %20, i32* %15, align 4
Add support for bottom-up SLP vectorization infrastructure. This commit adds the infrastructure for performing bottom-up SLP vectorization (and other optimizations) on parallel computations. The infrastructure has three potential users: 1. The loop vectorizer needs to be able to vectorize AOS data structures such as (sum += A[i] + A[i+1]). 2. The BB-vectorizer needs this infrastructure for bottom-up SLP vectorization, because bottom-up vectorization is faster to compute. 3. A loop-roller needs to be able to analyze consecutive chains and roll them into a loop, in order to reduce code size. A loop roller does not need to create vector instructions, and this infrastructure separates the chain analysis from the vectorization. This patch also includes a simple (100 LOC) bottom up SLP vectorizer that uses the infrastructure, and can vectorize this code: void SAXPY(int *x, int *y, int a, int i) { x[i] = a * x[i] + y[i]; x[i+1] = a * x[i+1] + y[i+1]; x[i+2] = a * x[i+2] + y[i+2]; x[i+3] = a * x[i+3] + y[i+3]; } git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179117 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-09 19:44:35 +00:00
%21 = add i64 %i, 3
%22 = getelementptr inbounds i32* %x, i64 %21
Remove unused function attributes. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179476 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-14 05:47:04 +00:00
%23 = load i32* %22, align 4
Add support for bottom-up SLP vectorization infrastructure. This commit adds the infrastructure for performing bottom-up SLP vectorization (and other optimizations) on parallel computations. The infrastructure has three potential users: 1. The loop vectorizer needs to be able to vectorize AOS data structures such as (sum += A[i] + A[i+1]). 2. The BB-vectorizer needs this infrastructure for bottom-up SLP vectorization, because bottom-up vectorization is faster to compute. 3. A loop-roller needs to be able to analyze consecutive chains and roll them into a loop, in order to reduce code size. A loop roller does not need to create vector instructions, and this infrastructure separates the chain analysis from the vectorization. This patch also includes a simple (100 LOC) bottom up SLP vectorizer that uses the infrastructure, and can vectorize this code: void SAXPY(int *x, int *y, int a, int i) { x[i] = a * x[i] + y[i]; x[i+1] = a * x[i+1] + y[i+1]; x[i+2] = a * x[i+2] + y[i+2]; x[i+3] = a * x[i+3] + y[i+3]; } git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179117 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-09 19:44:35 +00:00
%24 = mul nsw i32 %23, %a
%25 = getelementptr inbounds i32* %y, i64 %21
Remove unused function attributes. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179476 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-14 05:47:04 +00:00
%26 = load i32* %25, align 4
Add support for bottom-up SLP vectorization infrastructure. This commit adds the infrastructure for performing bottom-up SLP vectorization (and other optimizations) on parallel computations. The infrastructure has three potential users: 1. The loop vectorizer needs to be able to vectorize AOS data structures such as (sum += A[i] + A[i+1]). 2. The BB-vectorizer needs this infrastructure for bottom-up SLP vectorization, because bottom-up vectorization is faster to compute. 3. A loop-roller needs to be able to analyze consecutive chains and roll them into a loop, in order to reduce code size. A loop roller does not need to create vector instructions, and this infrastructure separates the chain analysis from the vectorization. This patch also includes a simple (100 LOC) bottom up SLP vectorizer that uses the infrastructure, and can vectorize this code: void SAXPY(int *x, int *y, int a, int i) { x[i] = a * x[i] + y[i]; x[i+1] = a * x[i+1] + y[i+1]; x[i+2] = a * x[i+2] + y[i+2]; x[i+3] = a * x[i+3] + y[i+3]; } git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179117 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-09 19:44:35 +00:00
%27 = add nsw i32 %24, %26
Remove unused function attributes. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179476 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-14 05:47:04 +00:00
store i32 %27, i32* %22, align 4
Add support for bottom-up SLP vectorization infrastructure. This commit adds the infrastructure for performing bottom-up SLP vectorization (and other optimizations) on parallel computations. The infrastructure has three potential users: 1. The loop vectorizer needs to be able to vectorize AOS data structures such as (sum += A[i] + A[i+1]). 2. The BB-vectorizer needs this infrastructure for bottom-up SLP vectorization, because bottom-up vectorization is faster to compute. 3. A loop-roller needs to be able to analyze consecutive chains and roll them into a loop, in order to reduce code size. A loop roller does not need to create vector instructions, and this infrastructure separates the chain analysis from the vectorization. This patch also includes a simple (100 LOC) bottom up SLP vectorizer that uses the infrastructure, and can vectorize this code: void SAXPY(int *x, int *y, int a, int i) { x[i] = a * x[i] + y[i]; x[i+1] = a * x[i+1] + y[i+1]; x[i+2] = a * x[i+2] + y[i+2]; x[i+3] = a * x[i+3] + y[i+3]; } git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179117 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-09 19:44:35 +00:00
ret void
}
SLPVectorizer: Implement DCE as part of vectorization. This is a complete re-write if the bottom-up vectorization class. Before this commit we scanned the instruction tree 3 times. First in search of merge points for the trees. Second, for estimating the cost. And finally for vectorization. There was a lot of code duplication and adding the DCE exposed bugs. The new design is simpler and DCE was a part of the design. In this implementation we build the tree once. After that we estimate the cost by scanning the different entries in the constructed tree (in any order). The vectorization phase also works on the built tree. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@185774 91177308-0d34-0410-b5e6-96231b3b80d8
2013-07-07 06:57:07 +00:00
; Make sure we don't crash on this one.
define void @SAXPY_crash(i32* noalias nocapture %x, i32* noalias nocapture %y, i64 %i) {
%1 = add i64 %i, 1
%2 = getelementptr inbounds i32* %x, i64 %1
%3 = getelementptr inbounds i32* %y, i64 %1
%4 = load i32* %3, align 4
%5 = add nsw i32 undef, %4
store i32 %5, i32* %2, align 4
%6 = add i64 %i, 2
%7 = getelementptr inbounds i32* %x, i64 %6
%8 = getelementptr inbounds i32* %y, i64 %6
%9 = load i32* %8, align 4
%10 = add nsw i32 undef, %9
store i32 %10, i32* %7, align 4
ret void
}
Reference in New Issue Copy Permalink