Skip to content

Commit

Permalink
[CostModel][X86] Add SSE2/AVX1/AVX512BW test coverage for i16 interle…
Browse files Browse the repository at this point in the history 
…aved load/store
  • Loading branch information
@RKSimon
RKSimon committed Sep 28, 2021
1 parent 27a972a commit bddc04b
Show file tree
Hide file tree
Showing 10 changed files with 318 additions and 66 deletions.
40 changes: 33 additions & 7 deletions llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-2.ll
View file
@@ -1,4 +1,7 @@
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE2
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX1
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw,+avx512vl --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX512
; REQUIRES: asserts

target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
Expand All @@ -8,12 +11,35 @@ target triple = "x86_64-unknown-linux-gnu"
@B = global [1024 x i8] zeroinitializer, align 128

; CHECK: LV: Checking a loop in "test"
; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 3 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 7 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 11 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 22 for VF 32 For instruction: %v0 = load i16, i16* %in0, align 2
;
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2
; SSE2: LV: Found an estimated cost of 9 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
; SSE2: LV: Found an estimated cost of 17 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
; SSE2: LV: Found an estimated cost of 34 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2
; SSE2: LV: Found an estimated cost of 68 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2
;
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX1: LV: Found an estimated cost of 9 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX1: LV: Found an estimated cost of 17 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX1: LV: Found an estimated cost of 41 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX1: LV: Found an estimated cost of 114 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX1: LV: Found an estimated cost of 228 for VF 32 For instruction: %v0 = load i16, i16* %in0, align 2
;
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX2: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX2: LV: Found an estimated cost of 3 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX2: LV: Found an estimated cost of 7 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX2: LV: Found an estimated cost of 11 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX2: LV: Found an estimated cost of 22 for VF 32 For instruction: %v0 = load i16, i16* %in0, align 2
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX512: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX512: LV: Found an estimated cost of 3 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX512: LV: Found an estimated cost of 5 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX512: LV: Found an estimated cost of 5 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX512: LV: Found an estimated cost of 7 for VF 32 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX512: LV: Found an estimated cost of 34 for VF 64 For instruction: %v0 = load i16, i16* %in0, align 2
;
; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %v0 = load i16, i16* %in0, align 2

define void @test() {
Expand Down
40 changes: 33 additions & 7 deletions llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-3.ll
View file
@@ -1,4 +1,7 @@
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE2
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX1
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw,+avx512vl --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX512
; REQUIRES: asserts

target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
Expand All @@ -8,12 +11,35 @@ target triple = "x86_64-unknown-linux-gnu"
@B = global [1024 x i8] zeroinitializer, align 128

; CHECK: LV: Checking a loop in "test"
; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 15 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 31 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 58 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 171 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 342 for VF 32 For instruction: %v0 = load i16, i16* %in0, align 2
;
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2
; SSE2: LV: Found an estimated cost of 18 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
; SSE2: LV: Found an estimated cost of 26 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
; SSE2: LV: Found an estimated cost of 51 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2
; SSE2: LV: Found an estimated cost of 102 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2
;
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX1: LV: Found an estimated cost of 15 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX1: LV: Found an estimated cost of 31 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX1: LV: Found an estimated cost of 58 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX1: LV: Found an estimated cost of 171 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX1: LV: Found an estimated cost of 342 for VF 32 For instruction: %v0 = load i16, i16* %in0, align 2
;
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX2: LV: Found an estimated cost of 15 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX2: LV: Found an estimated cost of 31 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX2: LV: Found an estimated cost of 58 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX2: LV: Found an estimated cost of 171 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX2: LV: Found an estimated cost of 342 for VF 32 For instruction: %v0 = load i16, i16* %in0, align 2
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX512: LV: Found an estimated cost of 4 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX512: LV: Found an estimated cost of 7 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX512: LV: Found an estimated cost of 7 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX512: LV: Found an estimated cost of 9 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX512: LV: Found an estimated cost of 18 for VF 32 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX512: LV: Found an estimated cost of 81 for VF 64 For instruction: %v0 = load i16, i16* %in0, align 2
;
; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %v0 = load i16, i16* %in0, align 2

define void @test() {
Expand Down
40 changes: 33 additions & 7 deletions llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-4.ll
View file
@@ -1,4 +1,7 @@
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE2
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX1
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw,+avx512vl --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX512
; REQUIRES: asserts

target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
Expand All @@ -8,12 +11,35 @@ target triple = "x86_64-unknown-linux-gnu"
@B = global [1024 x i8] zeroinitializer, align 128

; CHECK: LV: Checking a loop in "test"
; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 7 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 18 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 35 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 79 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 158 for VF 32 For instruction: %v0 = load i16, i16* %in0, align 2
;
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2
; SSE2: LV: Found an estimated cost of 17 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
; SSE2: LV: Found an estimated cost of 34 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
; SSE2: LV: Found an estimated cost of 68 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2
; SSE2: LV: Found an estimated cost of 136 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2
;
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX1: LV: Found an estimated cost of 17 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX1: LV: Found an estimated cost of 41 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX1: LV: Found an estimated cost of 82 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX1: LV: Found an estimated cost of 228 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX1: LV: Found an estimated cost of 456 for VF 32 For instruction: %v0 = load i16, i16* %in0, align 2
;
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX2: LV: Found an estimated cost of 7 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX2: LV: Found an estimated cost of 18 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX2: LV: Found an estimated cost of 35 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX2: LV: Found an estimated cost of 79 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX2: LV: Found an estimated cost of 158 for VF 32 For instruction: %v0 = load i16, i16* %in0, align 2
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX512: LV: Found an estimated cost of 5 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX512: LV: Found an estimated cost of 9 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX512: LV: Found an estimated cost of 9 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX512: LV: Found an estimated cost of 12 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX512: LV: Found an estimated cost of 34 for VF 32 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX512: LV: Found an estimated cost of 148 for VF 64 For instruction: %v0 = load i16, i16* %in0, align 2
;
; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %v0 = load i16, i16* %in0, align 2

define void @test() {
Expand Down
36 changes: 30 additions & 6 deletions llvm/test/Analysis/CostModel/X86/interleaved-load-i16-stride-5.ll
View file
@@ -1,4 +1,7 @@
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE2
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX1
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw,+avx512vl --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX512
; REQUIRES: asserts

target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
Expand All @@ -8,11 +11,32 @@ target triple = "x86_64-unknown-linux-gnu"
@B = global [1024 x i8] zeroinitializer, align 128

; CHECK: LV: Checking a loop in "test"
; CHECK: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 26 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 50 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 99 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2
; CHECK: LV: Found an estimated cost of 285 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2
;
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2
; SSE2: LV: Found an estimated cost of 22 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
; SSE2: LV: Found an estimated cost of 43 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
; SSE2: LV: Found an estimated cost of 85 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2
;
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX1: LV: Found an estimated cost of 26 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX1: LV: Found an estimated cost of 50 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX1: LV: Found an estimated cost of 99 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX1: LV: Found an estimated cost of 285 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2
;
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX2: LV: Found an estimated cost of 26 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX2: LV: Found an estimated cost of 50 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX2: LV: Found an estimated cost of 99 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX2: LV: Found an estimated cost of 285 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX512: LV: Found an estimated cost of 11 for VF 2 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX512: LV: Found an estimated cost of 11 for VF 4 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX512: LV: Found an estimated cost of 14 for VF 8 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX512: LV: Found an estimated cost of 28 for VF 16 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX512: LV: Found an estimated cost of 55 for VF 32 For instruction: %v0 = load i16, i16* %in0, align 2
; AVX512: LV: Found an estimated cost of 235 for VF 64 For instruction: %v0 = load i16, i16* %in0, align 2
;
; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %v0 = load i16, i16* %in0, align 2

define void @test() {
Expand Down

0 comments on commit bddc04b

Please sign in to comment.