forked from OSchip/llvm-project
Precommit analysis/etc tests for inselt poison placeholder
This adds tests in directories missing from https://reviews.llvm.org/rGdb7a2f347f132b3920415013d62d1adfb18d8d58
This commit is contained in:
Juneyoung Lee
parent
db7a2f347f
commit
3036547248
|
|
@ -0,0 +1,26 @@
|
|||
; RUN: opt < %s -cost-model -analyze -mcpu=kryo | FileCheck %s
|
||||
|
||||
target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
|
||||
target triple = "aarch64--linux-gnu"
|
||||
|
||||
; CHECK-LABEL: vectorInstrCost
|
||||
define void @vectorInstrCost() {
|
||||
|
||||
; Vector extracts - extracting the first element should have a zero cost;
|
||||
; all other elements should have a cost of two.
|
||||
;
|
||||
; CHECK: cost of 0 {{.*}} extractelement <2 x i64> undef, i32 0
|
||||
; CHECK: cost of 2 {{.*}} extractelement <2 x i64> undef, i32 1
|
||||
%t1 = extractelement <2 x i64> undef, i32 0
|
||||
%t2 = extractelement <2 x i64> undef, i32 1
|
||||
|
||||
; Vector inserts - inserting the first element should have a zero cost; all
|
||||
; other elements should have a cost of two.
|
||||
;
|
||||
; CHECK: cost of 0 {{.*}} insertelement <2 x i64> poison, i64 undef, i32 0
|
||||
; CHECK: cost of 2 {{.*}} insertelement <2 x i64> poison, i64 undef, i32 1
|
||||
%t3 = insertelement <2 x i64> poison, i64 undef, i32 0
|
||||
%t4 = insertelement <2 x i64> poison, i64 undef, i32 1
|
||||
|
||||
ret void
|
||||
}
|
||||
|
|
@ -0,0 +1,187 @@
|
|||
; 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 --check-prefix=CHECK-P7 %s
|
||||
; RUN: opt < %s -cost-model -analyze -mtriple=powerpc64le-unknown-linux-gnu -mcpu=pwr8 -mattr=+vsx | FileCheck --check-prefix=CHECK-P8LE %s
|
||||
; RUN: opt < %s -cost-model -analyze -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr9 -mattr=+vsx | FileCheck --check-prefix=CHECK-P9BE %s
|
||||
; RUN: opt < %s -cost-model -analyze -mtriple=powerpc64le-unknown-linux-gnu -mcpu=pwr9 -mattr=+vsx | FileCheck --check-prefix=CHECK-P9LE %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-f128:128:128-v128:128:128-n32:64"
|
||||
target triple = "powerpc64-unknown-linux-gnu"
|
||||
|
||||
define i32 @insert(i32 %arg) {
|
||||
; CHECK: cost of 10 {{.*}} insertelement
|
||||
; CHECK-P7-LABEL: 'insert'
|
||||
; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %x = insertelement <4 x i32> poison, i32 %arg, i32 0
|
||||
; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; CHECK-P8LE-LABEL: 'insert'
|
||||
; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %x = insertelement <4 x i32> poison, i32 %arg, i32 0
|
||||
; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; CHECK-P9BE-LABEL: 'insert'
|
||||
; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %x = insertelement <4 x i32> poison, i32 %arg, i32 0
|
||||
; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
; CHECK-P9LE-LABEL: 'insert'
|
||||
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %x = insertelement <4 x i32> poison, i32 %arg, i32 0
|
||||
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
||||
;
|
||||
%x = insertelement <4 x i32> poison, i32 %arg, i32 0
|
||||
ret i32 undef
|
||||
}
|
||||
|
||||
define i32 @extract(<4 x i32> %arg) {
|
||||
; CHECK: cost of 3 {{.*}} extractelement
|
||||
; CHECK-P7-LABEL: 'extract'
|
||||
; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %x = extractelement <4 x i32> %arg, i32 0
|
||||
; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %x
|
||||
;
|
||||
; CHECK-P8LE-LABEL: 'extract'
|
||||
; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %x = extractelement <4 x i32> %arg, i32 0
|
||||
; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %x
|
||||
;
|
||||
; CHECK-P9BE-LABEL: 'extract'
|
||||
; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <4 x i32> %arg, i32 0
|
||||
; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %x
|
||||
;
|
||||
; CHECK-P9LE-LABEL: 'extract'
|
||||
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %x = extractelement <4 x i32> %arg, i32 0
|
||||
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 %x
|
||||
;
|
||||
%x = extractelement <4 x i32> %arg, i32 0
|
||||
ret i32 %x
|
||||
}
|
||||
|
||||
define void @test2xdouble(<2 x double> %arg1) {
|
||||
; CHECK-P7-LABEL: 'test2xdouble'
|
||||
; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v1 = extractelement <2 x double> %arg1, i32 0
|
||||
; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v2 = extractelement <2 x double> %arg1, i32 1
|
||||
; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; CHECK-P8LE-LABEL: 'test2xdouble'
|
||||
; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %v1 = extractelement <2 x double> %arg1, i32 0
|
||||
; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v2 = extractelement <2 x double> %arg1, i32 1
|
||||
; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; CHECK-P9BE-LABEL: 'test2xdouble'
|
||||
; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v1 = extractelement <2 x double> %arg1, i32 0
|
||||
; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v2 = extractelement <2 x double> %arg1, i32 1
|
||||
; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; CHECK-P9LE-LABEL: 'test2xdouble'
|
||||
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %v1 = extractelement <2 x double> %arg1, i32 0
|
||||
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %v2 = extractelement <2 x double> %arg1, i32 1
|
||||
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
%v1 = extractelement <2 x double> %arg1, i32 0
|
||||
%v2 = extractelement <2 x double> %arg1, i32 1
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @test4xi32(<4 x i32> %v1, i32 %x1) {
|
||||
; CHECK-P7-LABEL: 'test4xi32'
|
||||
; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 10 for instruction: %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2
|
||||
; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; CHECK-P8LE-LABEL: 'test4xi32'
|
||||
; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2
|
||||
; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; CHECK-P9BE-LABEL: 'test4xi32'
|
||||
; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2
|
||||
; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; CHECK-P9LE-LABEL: 'test4xi32'
|
||||
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2
|
||||
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
%v2 = insertelement <4 x i32> %v1, i32 %x1, i32 2
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @vexti32(<4 x i32> %p1) {
|
||||
; CHECK-P7-LABEL: 'vexti32'
|
||||
; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i1 = extractelement <4 x i32> %p1, i32 0
|
||||
; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i2 = extractelement <4 x i32> %p1, i32 1
|
||||
; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i3 = extractelement <4 x i32> %p1, i32 2
|
||||
; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i4 = extractelement <4 x i32> %p1, i32 3
|
||||
; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; CHECK-P8LE-LABEL: 'vexti32'
|
||||
; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i1 = extractelement <4 x i32> %p1, i32 0
|
||||
; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i2 = extractelement <4 x i32> %p1, i32 1
|
||||
; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i3 = extractelement <4 x i32> %p1, i32 2
|
||||
; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i4 = extractelement <4 x i32> %p1, i32 3
|
||||
; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; CHECK-P9BE-LABEL: 'vexti32'
|
||||
; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i1 = extractelement <4 x i32> %p1, i32 0
|
||||
; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %i2 = extractelement <4 x i32> %p1, i32 1
|
||||
; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i3 = extractelement <4 x i32> %p1, i32 2
|
||||
; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i4 = extractelement <4 x i32> %p1, i32 3
|
||||
; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; CHECK-P9LE-LABEL: 'vexti32'
|
||||
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i1 = extractelement <4 x i32> %p1, i32 0
|
||||
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i2 = extractelement <4 x i32> %p1, i32 1
|
||||
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %i3 = extractelement <4 x i32> %p1, i32 2
|
||||
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i4 = extractelement <4 x i32> %p1, i32 3
|
||||
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
%i1 = extractelement <4 x i32> %p1, i32 0
|
||||
%i2 = extractelement <4 x i32> %p1, i32 1
|
||||
%i3 = extractelement <4 x i32> %p1, i32 2
|
||||
%i4 = extractelement <4 x i32> %p1, i32 3
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @vexti64(<2 x i64> %p1) {
|
||||
; CHECK-P7-LABEL: 'vexti64'
|
||||
; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i1 = extractelement <2 x i64> %p1, i32 0
|
||||
; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i2 = extractelement <2 x i64> %p1, i32 1
|
||||
; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; CHECK-P8LE-LABEL: 'vexti64'
|
||||
; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i1 = extractelement <2 x i64> %p1, i32 0
|
||||
; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i2 = extractelement <2 x i64> %p1, i32 1
|
||||
; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; CHECK-P9BE-LABEL: 'vexti64'
|
||||
; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %i1 = extractelement <2 x i64> %p1, i32 0
|
||||
; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i2 = extractelement <2 x i64> %p1, i32 1
|
||||
; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; CHECK-P9LE-LABEL: 'vexti64'
|
||||
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i1 = extractelement <2 x i64> %p1, i32 0
|
||||
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %i2 = extractelement <2 x i64> %p1, i32 1
|
||||
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
%i1 = extractelement <2 x i64> %p1, i32 0
|
||||
%i2 = extractelement <2 x i64> %p1, i32 1
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @vext(<8 x i16> %p1, <16 x i8> %p2) {
|
||||
; CHECK-P7-LABEL: 'vext'
|
||||
; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i1 = extractelement <8 x i16> %p1, i32 0
|
||||
; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i2 = extractelement <16 x i8> %p2, i32 0
|
||||
; CHECK-P7-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; CHECK-P8LE-LABEL: 'vext'
|
||||
; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i1 = extractelement <8 x i16> %p1, i32 0
|
||||
; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %i2 = extractelement <16 x i8> %p2, i32 0
|
||||
; CHECK-P8LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; CHECK-P9BE-LABEL: 'vext'
|
||||
; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i1 = extractelement <8 x i16> %p1, i32 0
|
||||
; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i2 = extractelement <16 x i8> %p2, i32 0
|
||||
; CHECK-P9BE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
; CHECK-P9LE-LABEL: 'vext'
|
||||
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i1 = extractelement <8 x i16> %p1, i32 0
|
||||
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %i2 = extractelement <16 x i8> %p2, i32 0
|
||||
; CHECK-P9LE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
||||
;
|
||||
%i1 = extractelement <8 x i16> %p1, i32 0
|
||||
%i2 = extractelement <16 x i8> %p2, i32 0
|
||||
ret void
|
||||
}
|
||||
|
|
@ -0,0 +1,56 @@
|
|||
; RUN: opt < %s -cost-model -analyze -mtriple=systemz-unknown -mcpu=z13 | FileCheck %s
|
||||
|
||||
; CHECK: vecinstrs
|
||||
define void @vecinstrs() {
|
||||
|
||||
;; Extract element is penalized somewhat with a cost of 2 for index 0.
|
||||
extractelement <16 x i8> undef, i32 0
|
||||
extractelement <16 x i8> undef, i32 1
|
||||
|
||||
extractelement <8 x i16> undef, i32 0
|
||||
extractelement <8 x i16> undef, i32 1
|
||||
|
||||
extractelement <4 x i32> undef, i32 0
|
||||
extractelement <4 x i32> undef, i32 1
|
||||
|
||||
extractelement <2 x i64> undef, i32 0
|
||||
extractelement <2 x i64> undef, i32 1
|
||||
|
||||
extractelement <2 x double> undef, i32 0
|
||||
extractelement <2 x double> undef, i32 1
|
||||
|
||||
; Extraction of i1 means extract + test under mask before branch.
|
||||
extractelement <2 x i1> undef, i32 0
|
||||
extractelement <4 x i1> undef, i32 1
|
||||
extractelement <8 x i1> undef, i32 2
|
||||
|
||||
;; Insert element
|
||||
insertelement <16 x i8> poison, i8 undef, i32 0
|
||||
insertelement <8 x i16> poison, i16 undef, i32 0
|
||||
insertelement <4 x i32> poison, i32 undef, i32 0
|
||||
|
||||
; vlvgp will do two grs into a vector register: only add cost half of the time.
|
||||
insertelement <2 x i64> poison, i64 undef, i32 0
|
||||
insertelement <2 x i64> poison, i64 undef, i32 1
|
||||
|
||||
ret void
|
||||
|
||||
; CHECK: Cost Model: Found an estimated cost of 2 for instruction: %1 = extractelement <16 x i8> undef, i32 0
|
||||
; CHECK: Cost Model: Found an estimated cost of 1 for instruction: %2 = extractelement <16 x i8> undef, i32 1
|
||||
; CHECK: Cost Model: Found an estimated cost of 2 for instruction: %3 = extractelement <8 x i16> undef, i32 0
|
||||
; CHECK: Cost Model: Found an estimated cost of 1 for instruction: %4 = extractelement <8 x i16> undef, i32 1
|
||||
; CHECK: Cost Model: Found an estimated cost of 2 for instruction: %5 = extractelement <4 x i32> undef, i32 0
|
||||
; CHECK: Cost Model: Found an estimated cost of 1 for instruction: %6 = extractelement <4 x i32> undef, i32 1
|
||||
; CHECK: Cost Model: Found an estimated cost of 2 for instruction: %7 = extractelement <2 x i64> undef, i32 0
|
||||
; CHECK: Cost Model: Found an estimated cost of 1 for instruction: %8 = extractelement <2 x i64> undef, i32 1
|
||||
; CHECK: Cost Model: Found an estimated cost of 1 for instruction: %9 = extractelement <2 x double> undef, i32 0
|
||||
; CHECK: Cost Model: Found an estimated cost of 1 for instruction: %10 = extractelement <2 x double> undef, i32 1
|
||||
; CHECK: Cost Model: Found an estimated cost of 3 for instruction: %11 = extractelement <2 x i1> undef, i32 0
|
||||
; CHECK: Cost Model: Found an estimated cost of 2 for instruction: %12 = extractelement <4 x i1> undef, i32 1
|
||||
; CHECK: Cost Model: Found an estimated cost of 2 for instruction: %13 = extractelement <8 x i1> undef, i32 2
|
||||
; CHECK: Cost Model: Found an estimated cost of 1 for instruction: %14 = insertelement <16 x i8> poison, i8 undef, i32 0
|
||||
; CHECK: Cost Model: Found an estimated cost of 1 for instruction: %15 = insertelement <8 x i16> poison, i16 undef, i32 0
|
||||
; CHECK: Cost Model: Found an estimated cost of 1 for instruction: %16 = insertelement <4 x i32> poison, i32 undef, i32 0
|
||||
; CHECK: Cost Model: Found an estimated cost of 1 for instruction: %17 = insertelement <2 x i64> poison, i64 undef, i32 0
|
||||
; CHECK: Cost Model: Found an estimated cost of 0 for instruction: %18 = insertelement <2 x i64> poison, i64 undef, i32 1
|
||||
}
|
||||
|
|
@ -0,0 +1,40 @@
|
|||
; RUN: opt < %s -cost-model -analyze -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"
|
||||
|
||||
define i32 @insert-extract-at-zero-idx(i32 %arg, float %fl) {
|
||||
;CHECK: cost of 0 {{.*}} extract
|
||||
%A = extractelement <4 x float> undef, i32 0
|
||||
;CHECK: cost of 1 {{.*}} extract
|
||||
%B = extractelement <4 x i32> undef, i32 0
|
||||
;CHECK: cost of 1 {{.*}} extract
|
||||
%C = extractelement <4 x float> undef, i32 1
|
||||
|
||||
;CHECK: cost of 0 {{.*}} extract
|
||||
%D = extractelement <8 x float> undef, i32 0
|
||||
;CHECK: cost of 1 {{.*}} extract
|
||||
%E = extractelement <8 x float> undef, i32 1
|
||||
|
||||
;CHECK: cost of 1 {{.*}} extract
|
||||
%F = extractelement <8 x float> undef, i32 %arg
|
||||
|
||||
;CHECK: cost of 0 {{.*}} insert
|
||||
%G = insertelement <4 x float> poison, float %fl, i32 0
|
||||
;CHECK: cost of 1 {{.*}} insert
|
||||
%H = insertelement <4 x float> poison, float %fl, i32 1
|
||||
;CHECK: cost of 1 {{.*}} insert
|
||||
%I = insertelement <4 x i32> poison, i32 %arg, i32 0
|
||||
|
||||
;CHECK: cost of 0 {{.*}} insert
|
||||
%J = insertelement <4 x double> poison, double undef, i32 0
|
||||
|
||||
;CHECK: cost of 0 {{.*}} insert
|
||||
%K = insertelement <8 x double> poison, double undef, i32 4
|
||||
;CHECK: cost of 0 {{.*}} insert
|
||||
%L = insertelement <16 x double> poison, double undef, i32 8
|
||||
;CHECK: cost of 1 {{.*}} insert
|
||||
%M = insertelement <16 x double> poison, double undef, i32 9
|
||||
ret i32 0
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,39 @@
|
|||
; RUN: opt < %s -cost-model -analyze -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-macosx10.9.0"
|
||||
|
||||
define i32 @foo(i32* nocapture %A) nounwind uwtable readonly ssp {
|
||||
vector.ph:
|
||||
br label %vector.body
|
||||
|
||||
vector.body: ; preds = %vector.body, %vector.ph
|
||||
%index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
|
||||
%vec.phi = phi <2 x i32> [ zeroinitializer, %vector.ph ], [ %12, %vector.body ]
|
||||
%0 = getelementptr inbounds i32, i32* %A, i64 %index
|
||||
%1 = bitcast i32* %0 to <2 x i32>*
|
||||
%2 = load <2 x i32>, <2 x i32>* %1, align 4
|
||||
%3 = sext <2 x i32> %2 to <2 x i64>
|
||||
;CHECK: cost of 1 {{.*}} extract
|
||||
%4 = extractelement <2 x i64> %3, i32 0
|
||||
%5 = getelementptr inbounds i32, i32* %A, i64 %4
|
||||
;CHECK: cost of 1 {{.*}} extract
|
||||
%6 = extractelement <2 x i64> %3, i32 1
|
||||
%7 = getelementptr inbounds i32, i32* %A, i64 %6
|
||||
%8 = load i32, i32* %5, align 4
|
||||
;CHECK: cost of 1 {{.*}} insert
|
||||
%9 = insertelement <2 x i32> poison, i32 %8, i32 0
|
||||
%10 = load i32, i32* %7, align 4
|
||||
;CHECK: cost of 1 {{.*}} insert
|
||||
%11 = insertelement <2 x i32> %9, i32 %10, i32 1
|
||||
%12 = add nsw <2 x i32> %11, %vec.phi
|
||||
%index.next = add i64 %index, 2
|
||||
%13 = icmp eq i64 %index.next, 192
|
||||
br i1 %13, label %for.end, label %vector.body
|
||||
|
||||
for.end: ; preds = %vector.body
|
||||
%14 = extractelement <2 x i32> %12, i32 0
|
||||
%15 = extractelement <2 x i32> %12, i32 1
|
||||
%16 = add i32 %14, %15
|
||||
ret i32 %16
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,39 @@
|
|||
; RUN: llc -mtriple=x86_64-apple-darwin -mattr=+sse2 < %s | FileCheck --check-prefix=SSE2-CODEGEN %s
|
||||
; RUN: opt -mtriple=x86_64-apple-darwin -mattr=+sse2 -cost-model -analyze < %s | FileCheck --check-prefix=SSE2 %s
|
||||
|
||||
define <4 x i32> @shl(<4 x i32> %vector, i32 %scalar) {
|
||||
entry:
|
||||
; SSE2: 'shl'
|
||||
; SSE2: cost of 1 {{.*}} shl
|
||||
; SSE2-CODEGEN: movd %edi, %xmm1
|
||||
; SSE2-CODEGEN: pslld %xmm1, %xmm0
|
||||
%insert = insertelement <4 x i32> poison, i32 %scalar, i32 0
|
||||
%splat = shufflevector <4 x i32> %insert, <4 x i32> undef, <4 x i32> zeroinitializer
|
||||
%ret = shl <4 x i32> %vector , %splat
|
||||
ret <4 x i32> %ret
|
||||
}
|
||||
|
||||
define <4 x i32> @ashr(<4 x i32> %vector, i32 %scalar) {
|
||||
entry:
|
||||
; SSE2: 'ashr'
|
||||
; SSE2: cost of 1 {{.*}} ashr
|
||||
; SSE2-CODEGEN: movd %edi, %xmm1
|
||||
; SSE2-CODEGEN: psrad %xmm1, %xmm0
|
||||
%insert = insertelement <4 x i32> poison, i32 %scalar, i32 0
|
||||
%splat = shufflevector <4 x i32> %insert, <4 x i32> undef, <4 x i32> zeroinitializer
|
||||
%ret = ashr <4 x i32> %vector , %splat
|
||||
ret <4 x i32> %ret
|
||||
}
|
||||
|
||||
define <4 x i32> @lshr(<4 x i32> %vector, i32 %scalar) {
|
||||
entry:
|
||||
; SSE2: 'lshr'
|
||||
; SSE2: cost of 1 {{.*}} lshr
|
||||
; SSE2-CODEGEN: movd %edi, %xmm1
|
||||
; SSE2-CODEGEN: psrld %xmm1, %xmm0
|
||||
%insert = insertelement <4 x i32> poison, i32 %scalar, i32 0
|
||||
%splat = shufflevector <4 x i32> %insert, <4 x i32> undef, <4 x i32> zeroinitializer
|
||||
%ret = lshr <4 x i32> %vector , %splat
|
||||
ret <4 x i32> %ret
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,17 @@
|
|||
; RUN: opt < %s -cost-model -analyze -mtriple=x86_64-linux-unknown-unknown -mattr=+avx512f | FileCheck %s
|
||||
|
||||
%struct.S = type { [1000 x i32] }
|
||||
|
||||
|
||||
declare <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*>, i32, <4 x i1>, <4 x i32>)
|
||||
|
||||
define <4 x i32> @foov(<4 x %struct.S*> %s, i64 %base){
|
||||
%temp = insertelement <4 x i64> poison, i64 %base, i32 0
|
||||
%vector = shufflevector <4 x i64> %temp, <4 x i64> undef, <4 x i32> zeroinitializer
|
||||
;CHECK: cost of 0 for instruction: {{.*}} getelementptr inbounds %struct.S
|
||||
%B = getelementptr inbounds %struct.S, <4 x %struct.S*> %s, <4 x i32> zeroinitializer, <4 x i32> zeroinitializer
|
||||
;CHECK: cost of 0 for instruction: {{.*}} getelementptr inbounds [1000 x i32]
|
||||
%arrayidx = getelementptr inbounds [1000 x i32], <4 x [1000 x i32]*> %B, <4 x i64> zeroinitializer, <4 x i64> %vector
|
||||
%res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %arrayidx, i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> undef)
|
||||
ret <4 x i32> %res
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,136 @@
|
|||
; RUN: opt -S -demanded-bits -analyze -enable-new-pm=0 < %s | FileCheck %s
|
||||
; RUN: opt -S -disable-output -passes="print<demanded-bits>" < %s 2>&1 | FileCheck %s
|
||||
|
||||
; CHECK-DAG: DemandedBits: 0xff00 for %x = or <2 x i32> %a, zeroinitializer
|
||||
; CHECK-DAG: DemandedBits: 0xff00 for %y = or <2 x i32> %b, zeroinitializer
|
||||
; CHECK-DAG: DemandedBits: 0xff00 for %z = or <2 x i32> %x, %y
|
||||
; CHECK-DAG: DemandedBits: 0xff for %u = lshr <2 x i32> %z, <i32 8, i32 8>
|
||||
; CHECK-DAG: DemandedBits: 0xff for %r = trunc <2 x i32> %u to <2 x i8>
|
||||
define <2 x i8> @test_basic(<2 x i32> %a, <2 x i32> %b) {
|
||||
%x = or <2 x i32> %a, zeroinitializer
|
||||
%y = or <2 x i32> %b, zeroinitializer
|
||||
%z = or <2 x i32> %x, %y
|
||||
%u = lshr <2 x i32> %z, <i32 8, i32 8>
|
||||
%r = trunc <2 x i32> %u to <2 x i8>
|
||||
ret <2 x i8> %r
|
||||
}
|
||||
|
||||
; Vector-specific instructions
|
||||
|
||||
; CHECK-DAG: DemandedBits: 0xff for %x = or <2 x i32> %a, zeroinitializer
|
||||
; CHECK-DAG: DemandedBits: 0xf0 for %z = extractelement <2 x i32> %x, i32 1
|
||||
; CHECK-DAG: DemandedBits: 0xf for %y = extractelement <2 x i32> %x, i32 0
|
||||
; CHECK-DAG: DemandedBits: 0xffffffff for %u = and i32 %y, 15
|
||||
; CHECK-DAG: DemandedBits: 0xffffffff for %v = and i32 %z, 240
|
||||
; CHECK-DAG: DemandedBits: 0xffffffff for %r = or i32 %u, %v
|
||||
define i32 @test_extractelement(<2 x i32> %a) {
|
||||
%x = or <2 x i32> %a, zeroinitializer
|
||||
%y = extractelement <2 x i32> %x, i32 0
|
||||
%z = extractelement <2 x i32> %x, i32 1
|
||||
%u = and i32 %y, 15
|
||||
%v = and i32 %z, 240
|
||||
%r = or i32 %u, %v
|
||||
ret i32 %r
|
||||
}
|
||||
|
||||
; CHECK-DAG: DemandedBits: 0xff for %x = or i32 %a, 0
|
||||
; CHECK-DAG: DemandedBits: 0xff for %y = or i32 %b, 0
|
||||
; CHECK-DAG: DemandedBits: 0xff for %z = insertelement <2 x i32> poison, i32 %x, i32 0
|
||||
; CHECK-DAG: DemandedBits: 0xff for %u = insertelement <2 x i32> %z, i32 %y, i32 1
|
||||
; CHECK-DAG: DemandedBits: 0xffffffff for %r = and <2 x i32> %u, <i32 255, i32 127>
|
||||
define <2 x i32> @test_insertelement(i32 %a, i32 %b) {
|
||||
%x = or i32 %a, 0
|
||||
%y = or i32 %b, 0
|
||||
%z = insertelement <2 x i32> poison, i32 %x, i32 0
|
||||
%u = insertelement <2 x i32> %z, i32 %y, i32 1
|
||||
%r = and <2 x i32> %u, <i32 255, i32 127>
|
||||
ret <2 x i32> %r
|
||||
}
|
||||
|
||||
; CHECK-DAG: DemandedBits: 0xff for %x = or <2 x i32> %a, zeroinitializer
|
||||
; CHECK-DAG: DemandedBits: 0xff for %y = or <2 x i32> %b, zeroinitializer
|
||||
; CHECK-DAG: DemandedBits: 0xff for %z = shufflevector <2 x i32> %x, <2 x i32> %y, <3 x i32> <i32 0, i32 3, i32 1>
|
||||
; CHECK-DAG: DemandedBits: 0xffffffff for %r = and <3 x i32> %z, <i32 255, i32 127, i32 0>
|
||||
define <3 x i32> @test_shufflevector(<2 x i32> %a, <2 x i32> %b) {
|
||||
%x = or <2 x i32> %a, zeroinitializer
|
||||
%y = or <2 x i32> %b, zeroinitializer
|
||||
%z = shufflevector <2 x i32> %x, <2 x i32> %y, <3 x i32> <i32 0, i32 3, i32 1>
|
||||
%r = and <3 x i32> %z, <i32 255, i32 127, i32 0>
|
||||
ret <3 x i32> %r
|
||||
}
|
||||
|
||||
; Shifts with splat shift amounts
|
||||
|
||||
; CHECK-DAG: DemandedBits: 0xf for %x = or <2 x i32> %a, zeroinitializer
|
||||
; CHECK-DAG: DemandedBits: 0xf0 for %y = shl <2 x i32> %x, <i32 4, i32 4>
|
||||
; CHECK-DAG: DemandedBits: 0xffffffff for %r = and <2 x i32> %y, <i32 240, i32 240>
|
||||
define <2 x i32> @test_shl(<2 x i32> %a) {
|
||||
%x = or <2 x i32> %a, zeroinitializer
|
||||
%y = shl <2 x i32> %x, <i32 4, i32 4>
|
||||
%r = and <2 x i32> %y, <i32 240, i32 240>
|
||||
ret <2 x i32> %r
|
||||
}
|
||||
|
||||
; CHECK-DAG: DemandedBits: 0xf00 for %x = or <2 x i32> %a, zeroinitializer
|
||||
; CHECK-DAG: DemandedBits: 0xf0 for %y = ashr <2 x i32> %x, <i32 4, i32 4>
|
||||
; CHECK-DAG: DemandedBits: 0xffffffff for %r = and <2 x i32> %y, <i32 240, i32 240>
|
||||
define <2 x i32> @test_ashr(<2 x i32> %a) {
|
||||
%x = or <2 x i32> %a, zeroinitializer
|
||||
%y = ashr <2 x i32> %x, <i32 4, i32 4>
|
||||
%r = and <2 x i32> %y, <i32 240, i32 240>
|
||||
ret <2 x i32> %r
|
||||
}
|
||||
|
||||
; CHECK-DAG: DemandedBits: 0xf00 for %x = or <2 x i32> %a, zeroinitializer
|
||||
; CHECK-DAG: DemandedBits: 0xf0 for %y = lshr <2 x i32> %x, <i32 4, i32 4>
|
||||
; CHECK-DAG: DemandedBits: 0xffffffff for %r = and <2 x i32> %y, <i32 240, i32 240>
|
||||
define <2 x i32> @test_lshr(<2 x i32> %a) {
|
||||
%x = or <2 x i32> %a, zeroinitializer
|
||||
%y = lshr <2 x i32> %x, <i32 4, i32 4>
|
||||
%r = and <2 x i32> %y, <i32 240, i32 240>
|
||||
ret <2 x i32> %r
|
||||
}
|
||||
|
||||
declare <2 x i32> @llvm.fshl.i32(<2 x i32>, <2 x i32>, <2 x i32>)
|
||||
declare <2 x i32> @llvm.fshr.i32(<2 x i32>, <2 x i32>, <2 x i32>)
|
||||
|
||||
; CHECK-DAG: DemandedBits: 0xf for %x = or <2 x i32> %a, zeroinitializer
|
||||
; CHECK-DAG: DemandedBits: 0xf0000000 for %y = or <2 x i32> %b, zeroinitializer
|
||||
; CHECK-DAG: DemandedBits: 0xff for %z = call <2 x i32> @llvm.fshl.v2i32(<2 x i32> %x, <2 x i32> %y, <2 x i32> <i32 4, i32 4>)
|
||||
; CHECK-DAG: DemandedBits: 0xffffffff for %r = and <2 x i32> %z, <i32 255, i32 255>
|
||||
define <2 x i32> @test_fshl(<2 x i32> %a, <2 x i32> %b) {
|
||||
%x = or <2 x i32> %a, zeroinitializer
|
||||
%y = or <2 x i32> %b, zeroinitializer
|
||||
%z = call <2 x i32> @llvm.fshl.i32(<2 x i32> %x, <2 x i32> %y, <2 x i32> <i32 4, i32 4>)
|
||||
%r = and <2 x i32> %z, <i32 255, i32 255>
|
||||
ret <2 x i32> %r
|
||||
}
|
||||
|
||||
; CHECK-DAG: DemandedBits: 0xf for %x = or <2 x i32> %a, zeroinitializer
|
||||
; CHECK-DAG: DemandedBits: 0xf0000000 for %y = or <2 x i32> %b, zeroinitializer
|
||||
; CHECK-DAG: DemandedBits: 0xff for %z = call <2 x i32> @llvm.fshr.v2i32(<2 x i32> %x, <2 x i32> %y, <2 x i32> <i32 28, i32 28>)
|
||||
; CHECK-DAG: DemandedBits: 0xffffffff for %r = and <2 x i32> %z, <i32 255, i32 255>
|
||||
define <2 x i32> @test_fshr(<2 x i32> %a, <2 x i32> %b) {
|
||||
%x = or <2 x i32> %a, zeroinitializer
|
||||
%y = or <2 x i32> %b, zeroinitializer
|
||||
%z = call <2 x i32> @llvm.fshr.i32(<2 x i32> %x, <2 x i32> %y, <2 x i32> <i32 28, i32 28>)
|
||||
%r = and <2 x i32> %z, <i32 255, i32 255>
|
||||
ret <2 x i32> %r
|
||||
}
|
||||
|
||||
; FP / Int conversion. These have different input / output types.
|
||||
|
||||
; CHECK-DAG: DemandedBits: 0xffffffff for %x = or <2 x i32> %a, zeroinitializer
|
||||
define <2 x float> @test_uitofp(<2 x i32> %a) {
|
||||
%x = or <2 x i32> %a, zeroinitializer
|
||||
%r = uitofp <2 x i32> %x to <2 x float>
|
||||
ret <2 x float> %r
|
||||
}
|
||||
|
||||
; CHECK-DAG: DemandedBits: 0xffffffff for %y = fptoui <2 x float> %x to <2 x i32>
|
||||
define <2 x i32> @test_fptoui(<2 x float> %a) {
|
||||
%x = fadd <2 x float> %a, <float 1.0, float 1.0>
|
||||
%y = fptoui <2 x float> %x to <2 x i32>
|
||||
%r = and <2 x i32> %y, <i32 255, i32 255>
|
||||
ret <2 x i32> %y
|
||||
}
|
||||
|
|
@ -0,0 +1,114 @@
|
|||
; RUN: llc %s -filetype=obj -o - | llvm-dwarfdump -debug-info -debug-loc - | FileCheck %s
|
||||
; Test that DW_OP_piece is emitted for constants.
|
||||
;
|
||||
; // Generated from:
|
||||
; typedef struct { int a, b; } I;
|
||||
; I i(int i) {
|
||||
; I r = {i, 0};
|
||||
; return r;
|
||||
; }
|
||||
;
|
||||
; typedef struct { float a, b; } F;
|
||||
; F f(float f) {
|
||||
; F r = {f, 0};
|
||||
; return r;
|
||||
; }
|
||||
|
||||
; CHECK: .debug_info contents:
|
||||
; CHECK: DW_TAG_subprogram
|
||||
; CHECK: DW_AT_name ("i")
|
||||
; CHECK: DW_TAG_variable
|
||||
; CHECK-NEXT: DW_AT_location ([[I:0x[0-9a-f]+]]
|
||||
; CHECK-NEXT: [{{.*}}, {{.*}}): DW_OP_reg5 RDI, DW_OP_piece 0x4, DW_OP_lit0, DW_OP_stack_value, DW_OP_piece 0x4)
|
||||
; CHECK-NEXT: DW_AT_name ("r")
|
||||
;
|
||||
; CHECK: DW_TAG_subprogram
|
||||
; CHECK: DW_AT_name ("f")
|
||||
; CHECK: DW_TAG_variable
|
||||
; CHECK-NEXT: DW_AT_location ([[F:0x[0-9a-f]+]]
|
||||
; CHECK-NEXT: [{{.*}}, {{.*}}): DW_OP_reg17 XMM0, DW_OP_piece 0x4, {{(DW_OP_lit0, DW_OP_stack_value, DW_OP_piece 0x4|DW_OP_implicit_value 0x4 0x00 0x00 0x00 0x00)}}
|
||||
; CHECK-NEXT: [{{.*}}, {{.*}}): DW_OP_piece 0x4, {{(DW_OP_lit0, DW_OP_stack_value, DW_OP_piece 0x4|DW_OP_implicit_value 0x4 0x00 0x00 0x00 0x00)}})
|
||||
; CHECK-NEXT: DW_AT_name ("r")
|
||||
;
|
||||
; CHECK: .debug_loc contents:
|
||||
; CHECK: [[I]]:
|
||||
; CHECK-NEXT: ({{.*}}, {{.*}}): DW_OP_reg5 RDI, DW_OP_piece 0x4, DW_OP_lit0, DW_OP_stack_value, DW_OP_piece 0x4
|
||||
; CHECK: [[F]]:
|
||||
; CHECK-NEXT: ({{.*}}, {{.*}}): DW_OP_reg17 XMM0, DW_OP_piece 0x4, {{DW_OP_lit0, DW_OP_stack_value, DW_OP_piece 0x4|DW_OP_implicit_value 0x4 0x00 0x00 0x00 0x00}}
|
||||
|
||||
source_filename = "stack-value-piece.c"
|
||||
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
|
||||
target triple = "x86_64-apple-macosx10.12.0"
|
||||
|
||||
%struct.I = type { i32, i32 }
|
||||
%struct.F = type { float, float }
|
||||
|
||||
; Function Attrs: nounwind readnone ssp uwtable
|
||||
define i64 @i(i32 %i) local_unnamed_addr #0 !dbg !7 {
|
||||
entry:
|
||||
tail call void @llvm.dbg.value(metadata i32 %i, metadata !18, metadata !22), !dbg !21
|
||||
tail call void @llvm.dbg.value(metadata i32 0, metadata !18, metadata !23), !dbg !21
|
||||
%retval.sroa.0.0.insert.ext = zext i32 %i to i64, !dbg !24
|
||||
ret i64 %retval.sroa.0.0.insert.ext, !dbg !24
|
||||
}
|
||||
|
||||
; Function Attrs: nounwind readnone
|
||||
declare void @llvm.dbg.declare(metadata, metadata, metadata) #1
|
||||
|
||||
; Function Attrs: nounwind readnone ssp uwtable
|
||||
define <2 x float> @f(float %f) local_unnamed_addr #0 !dbg !25 {
|
||||
entry:
|
||||
tail call void @llvm.dbg.value(metadata float %f, metadata !36, metadata !22), !dbg !38
|
||||
tail call void @llvm.dbg.value(metadata float 0.000000e+00, metadata !36, metadata !23), !dbg !38
|
||||
%retval.sroa.0.0.vec.insert = insertelement <2 x float> poison, float %f, i32 0, !dbg !39
|
||||
%retval.sroa.0.4.vec.insert = insertelement <2 x float> %retval.sroa.0.0.vec.insert, float 0.000000e+00, i32 1, !dbg !39
|
||||
ret <2 x float> %retval.sroa.0.4.vec.insert, !dbg !40
|
||||
}
|
||||
|
||||
; Function Attrs: nounwind readnone
|
||||
declare void @llvm.dbg.value(metadata, metadata, metadata) #1
|
||||
|
||||
attributes #0 = { nounwind readnone ssp uwtable }
|
||||
attributes #1 = { nounwind readnone }
|
||||
|
||||
!llvm.dbg.cu = !{!0}
|
||||
!llvm.module.flags = !{!3, !4, !5}
|
||||
!llvm.ident = !{!6}
|
||||
|
||||
!0 = distinct !DICompileUnit(language: DW_LANG_C99, file: !1, producer: "clang version 4.0.0 (trunk 285655) (llvm/trunk 285654)", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, enums: !2)
|
||||
!1 = !DIFile(filename: "stack-value-piece.c", directory: "/")
|
||||
!2 = !{}
|
||||
!3 = !{i32 2, !"Dwarf Version", i32 4}
|
||||
!4 = !{i32 2, !"Debug Info Version", i32 3}
|
||||
!5 = !{i32 1, !"PIC Level", i32 2}
|
||||
!6 = !{!"clang version 4.0.0 (trunk 285655) (llvm/trunk 285654)"}
|
||||
!7 = distinct !DISubprogram(name: "i", scope: !1, file: !1, line: 2, type: !8, isLocal: false, isDefinition: true, scopeLine: 2, flags: DIFlagPrototyped, isOptimized: true, unit: !0)
|
||||
!8 = !DISubroutineType(types: !9)
|
||||
!9 = !{!10, !14}
|
||||
!10 = !DIDerivedType(tag: DW_TAG_typedef, name: "I", file: !1, line: 1, baseType: !11)
|
||||
!11 = distinct !DICompositeType(tag: DW_TAG_structure_type, file: !1, line: 1, size: 64, elements: !12)
|
||||
!12 = !{!13, !15}
|
||||
!13 = !DIDerivedType(tag: DW_TAG_member, name: "a", scope: !11, file: !1, line: 1, baseType: !14, size: 32)
|
||||
!14 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
|
||||
!15 = !DIDerivedType(tag: DW_TAG_member, name: "b", scope: !11, file: !1, line: 1, baseType: !14, size: 32, offset: 32)
|
||||
!18 = !DILocalVariable(name: "r", scope: !7, file: !1, line: 3, type: !10)
|
||||
!19 = !DIExpression()
|
||||
!20 = !DILocation(line: 2, column: 9, scope: !7)
|
||||
!21 = !DILocation(line: 3, column: 5, scope: !7)
|
||||
!22 = !DIExpression(DW_OP_LLVM_fragment, 0, 32)
|
||||
!23 = !DIExpression(DW_OP_LLVM_fragment, 32, 32)
|
||||
!24 = !DILocation(line: 5, column: 1, scope: !7)
|
||||
!25 = distinct !DISubprogram(name: "f", scope: !1, file: !1, line: 8, type: !26, isLocal: false, isDefinition: true, scopeLine: 8, flags: DIFlagPrototyped, isOptimized: true, unit: !0)
|
||||
!26 = !DISubroutineType(types: !27)
|
||||
!27 = !{!28, !32}
|
||||
!28 = !DIDerivedType(tag: DW_TAG_typedef, name: "F", file: !1, line: 7, baseType: !29)
|
||||
!29 = distinct !DICompositeType(tag: DW_TAG_structure_type, file: !1, line: 7, size: 64, elements: !30)
|
||||
!30 = !{!31, !33}
|
||||
!31 = !DIDerivedType(tag: DW_TAG_member, name: "a", scope: !29, file: !1, line: 7, baseType: !32, size: 32)
|
||||
!32 = !DIBasicType(name: "float", size: 32, encoding: DW_ATE_float)
|
||||
!33 = !DIDerivedType(tag: DW_TAG_member, name: "b", scope: !29, file: !1, line: 7, baseType: !32, size: 32, offset: 32)
|
||||
!36 = !DILocalVariable(name: "r", scope: !25, file: !1, line: 9, type: !28)
|
||||
!37 = !DILocation(line: 8, column: 11, scope: !25)
|
||||
!38 = !DILocation(line: 9, column: 5, scope: !25)
|
||||
!39 = !DILocation(line: 10, column: 10, scope: !25)
|
||||
!40 = !DILocation(line: 11, column: 1, scope: !25)
|
||||
|
|
@ -200,6 +200,16 @@ define <vscale x 8 x half> @shufflevector(half %val) {
|
|||
ret <vscale x 8 x half> %r
|
||||
}
|
||||
|
||||
define <vscale x 8 x half> @shufflevector2(half %val) {
|
||||
; CHECK-LABEL: @shufflevector
|
||||
; CHECK: %insvec = insertelement <vscale x 8 x half> poison, half %val, i32 0
|
||||
; CHECK-NEXT: %r = shufflevector <vscale x 8 x half> %insvec, <vscale x 8 x half> undef, <vscale x 8 x i32> zeroinitializer
|
||||
; CHECK-NEXT: ret <vscale x 8 x half> %r
|
||||
%insvec = insertelement <vscale x 8 x half> poison, half %val, i32 0
|
||||
%r = shufflevector <vscale x 8 x half> %insvec, <vscale x 8 x half> undef, <vscale x 8 x i32> zeroinitializer
|
||||
ret <vscale x 8 x half> %r
|
||||
}
|
||||
|
||||
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
|
||||
;; Memory Access and Addressing Operations
|
||||
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
|
||||
|
|
|
|||
Loading…
Reference in New Issue