aboutsummaryrefslogtreecommitdiff
path: root/test/Transforms/LoadStoreVectorizer/AMDGPU/pointer-elements.ll
diff options
context:
space:
mode:
Diffstat (limited to 'test/Transforms/LoadStoreVectorizer/AMDGPU/pointer-elements.ll')
-rw-r--r--test/Transforms/LoadStoreVectorizer/AMDGPU/pointer-elements.ll38
1 files changed, 19 insertions, 19 deletions
diff --git a/test/Transforms/LoadStoreVectorizer/AMDGPU/pointer-elements.ll b/test/Transforms/LoadStoreVectorizer/AMDGPU/pointer-elements.ll
index 202e988ea5f1..65200b95d5e6 100644
--- a/test/Transforms/LoadStoreVectorizer/AMDGPU/pointer-elements.ll
+++ b/test/Transforms/LoadStoreVectorizer/AMDGPU/pointer-elements.ll
@@ -9,7 +9,7 @@ declare i32 @llvm.amdgcn.workitem.id.x() #1
; CHECK: inttoptr i64 %{{[^ ]+}} to i8 addrspace(1)*
; CHECK: inttoptr i64 %{{[^ ]+}} to i8 addrspace(1)*
; CHECK: store <2 x i64> zeroinitializer
-define void @merge_v2p1i8(i8 addrspace(1)* addrspace(1)* nocapture %a, i8 addrspace(1)* addrspace(1)* nocapture readonly %b) #0 {
+define amdgpu_kernel void @merge_v2p1i8(i8 addrspace(1)* addrspace(1)* nocapture %a, i8 addrspace(1)* addrspace(1)* nocapture readonly %b) #0 {
entry:
%a.1 = getelementptr inbounds i8 addrspace(1)*, i8 addrspace(1)* addrspace(1)* %a, i64 1
%b.1 = getelementptr inbounds i8 addrspace(1)*, i8 addrspace(1)* addrspace(1)* %b, i64 1
@@ -28,7 +28,7 @@ entry:
; CHECK: inttoptr i32 %{{[^ ]+}} to i8 addrspace(3)*
; CHECK: inttoptr i32 %{{[^ ]+}} to i8 addrspace(3)*
; CHECK: store <2 x i32> zeroinitializer
-define void @merge_v2p3i8(i8 addrspace(3)* addrspace(3)* nocapture %a, i8 addrspace(3)* addrspace(3)* nocapture readonly %b) #0 {
+define amdgpu_kernel void @merge_v2p3i8(i8 addrspace(3)* addrspace(3)* nocapture %a, i8 addrspace(3)* addrspace(3)* nocapture readonly %b) #0 {
entry:
%a.1 = getelementptr inbounds i8 addrspace(3)*, i8 addrspace(3)* addrspace(3)* %a, i64 1
%b.1 = getelementptr inbounds i8 addrspace(3)*, i8 addrspace(3)* addrspace(3)* %b, i64 1
@@ -46,7 +46,7 @@ entry:
; CHECK: load <2 x i64>
; CHECK: [[ELT1:%[^ ]+]] = extractelement <2 x i64> %{{[^ ]+}}, i32 1
; CHECK: inttoptr i64 [[ELT1]] to i8 addrspace(1)*
-define void @merge_load_i64_ptr64(i64 addrspace(1)* nocapture %a) #0 {
+define amdgpu_kernel void @merge_load_i64_ptr64(i64 addrspace(1)* nocapture %a) #0 {
entry:
%a.1 = getelementptr inbounds i64, i64 addrspace(1)* %a, i64 1
%a.1.cast = bitcast i64 addrspace(1)* %a.1 to i8 addrspace(1)* addrspace(1)*
@@ -61,7 +61,7 @@ entry:
; CHECK: load <2 x i64>
; CHECK: [[ELT0:%[^ ]+]] = extractelement <2 x i64> %{{[^ ]+}}, i32 0
; CHECK: inttoptr i64 [[ELT0]] to i8 addrspace(1)*
-define void @merge_load_ptr64_i64(i64 addrspace(1)* nocapture %a) #0 {
+define amdgpu_kernel void @merge_load_ptr64_i64(i64 addrspace(1)* nocapture %a) #0 {
entry:
%a.cast = bitcast i64 addrspace(1)* %a to i8 addrspace(1)* addrspace(1)*
%a.1 = getelementptr inbounds i64, i64 addrspace(1)* %a, i64 1
@@ -76,7 +76,7 @@ entry:
; CHECK: [[ELT0:%[^ ]+]] = ptrtoint i8 addrspace(1)* %ptr0 to i64
; CHECK: insertelement <2 x i64> undef, i64 [[ELT0]], i32 0
; CHECK: store <2 x i64>
-define void @merge_store_ptr64_i64(i64 addrspace(1)* nocapture %a, i8 addrspace(1)* %ptr0, i64 %val1) #0 {
+define amdgpu_kernel void @merge_store_ptr64_i64(i64 addrspace(1)* nocapture %a, i8 addrspace(1)* %ptr0, i64 %val1) #0 {
entry:
%a.cast = bitcast i64 addrspace(1)* %a to i8 addrspace(1)* addrspace(1)*
%a.1 = getelementptr inbounds i64, i64 addrspace(1)* %a, i64 1
@@ -92,7 +92,7 @@ entry:
; CHECK: [[ELT1:%[^ ]+]] = ptrtoint i8 addrspace(1)* %ptr1 to i64
; CHECK: insertelement <2 x i64> %{{[^ ]+}}, i64 [[ELT1]], i32 1
; CHECK: store <2 x i64>
-define void @merge_store_i64_ptr64(i8 addrspace(1)* addrspace(1)* nocapture %a, i64 %val0, i8 addrspace(1)* %ptr1) #0 {
+define amdgpu_kernel void @merge_store_i64_ptr64(i8 addrspace(1)* addrspace(1)* nocapture %a, i64 %val0, i8 addrspace(1)* %ptr1) #0 {
entry:
%a.1 = getelementptr inbounds i8 addrspace(1)*, i8 addrspace(1)* addrspace(1)* %a, i64 1
%a.cast = bitcast i8 addrspace(1)* addrspace(1)* %a to i64 addrspace(1)*
@@ -107,7 +107,7 @@ entry:
; CHECK: load <2 x i32>
; CHECK: [[ELT1:%[^ ]+]] = extractelement <2 x i32> %{{[^ ]+}}, i32 1
; CHECK: inttoptr i32 [[ELT1]] to i8 addrspace(3)*
-define void @merge_load_i32_ptr32(i32 addrspace(3)* nocapture %a) #0 {
+define amdgpu_kernel void @merge_load_i32_ptr32(i32 addrspace(3)* nocapture %a) #0 {
entry:
%a.1 = getelementptr inbounds i32, i32 addrspace(3)* %a, i32 1
%a.1.cast = bitcast i32 addrspace(3)* %a.1 to i8 addrspace(3)* addrspace(3)*
@@ -122,7 +122,7 @@ entry:
; CHECK: load <2 x i32>
; CHECK: [[ELT0:%[^ ]+]] = extractelement <2 x i32> %{{[^ ]+}}, i32 0
; CHECK: inttoptr i32 [[ELT0]] to i8 addrspace(3)*
-define void @merge_load_ptr32_i32(i32 addrspace(3)* nocapture %a) #0 {
+define amdgpu_kernel void @merge_load_ptr32_i32(i32 addrspace(3)* nocapture %a) #0 {
entry:
%a.cast = bitcast i32 addrspace(3)* %a to i8 addrspace(3)* addrspace(3)*
%a.1 = getelementptr inbounds i32, i32 addrspace(3)* %a, i32 1
@@ -137,7 +137,7 @@ entry:
; CHECK: [[ELT0:%[^ ]+]] = ptrtoint i8 addrspace(3)* %ptr0 to i32
; CHECK: insertelement <2 x i32> undef, i32 [[ELT0]], i32 0
; CHECK: store <2 x i32>
-define void @merge_store_ptr32_i32(i32 addrspace(3)* nocapture %a, i8 addrspace(3)* %ptr0, i32 %val1) #0 {
+define amdgpu_kernel void @merge_store_ptr32_i32(i32 addrspace(3)* nocapture %a, i8 addrspace(3)* %ptr0, i32 %val1) #0 {
entry:
%a.cast = bitcast i32 addrspace(3)* %a to i8 addrspace(3)* addrspace(3)*
%a.1 = getelementptr inbounds i32, i32 addrspace(3)* %a, i32 1
@@ -152,7 +152,7 @@ entry:
; CHECK: [[ELT1:%[^ ]+]] = ptrtoint i8 addrspace(3)* %ptr1 to i32
; CHECK: insertelement <2 x i32> %{{[^ ]+}}, i32 [[ELT1]], i32 1
; CHECK: store <2 x i32>
-define void @merge_store_i32_ptr32(i8 addrspace(3)* addrspace(3)* nocapture %a, i32 %val0, i8 addrspace(3)* %ptr1) #0 {
+define amdgpu_kernel void @merge_store_i32_ptr32(i8 addrspace(3)* addrspace(3)* nocapture %a, i32 %val0, i8 addrspace(3)* %ptr1) #0 {
entry:
%a.1 = getelementptr inbounds i8 addrspace(3)*, i8 addrspace(3)* addrspace(3)* %a, i32 1
%a.cast = bitcast i8 addrspace(3)* addrspace(3)* %a to i32 addrspace(3)*
@@ -166,7 +166,7 @@ entry:
; CHECK-LABEL: @no_merge_store_ptr32_i64(
; CHECK: store i8 addrspace(3)*
; CHECK: store i64
-define void @no_merge_store_ptr32_i64(i64 addrspace(1)* nocapture %a, i8 addrspace(3)* %ptr0, i64 %val1) #0 {
+define amdgpu_kernel void @no_merge_store_ptr32_i64(i64 addrspace(1)* nocapture %a, i8 addrspace(3)* %ptr0, i64 %val1) #0 {
entry:
%a.cast = bitcast i64 addrspace(1)* %a to i8 addrspace(3)* addrspace(1)*
%a.1 = getelementptr inbounds i64, i64 addrspace(1)* %a, i64 1
@@ -181,7 +181,7 @@ entry:
; CHECK-LABEL: @no_merge_store_i64_ptr32(
; CHECK: store i64
; CHECK: store i8 addrspace(3)*
-define void @no_merge_store_i64_ptr32(i8 addrspace(3)* addrspace(1)* nocapture %a, i64 %val0, i8 addrspace(3)* %ptr1) #0 {
+define amdgpu_kernel void @no_merge_store_i64_ptr32(i8 addrspace(3)* addrspace(1)* nocapture %a, i64 %val0, i8 addrspace(3)* %ptr1) #0 {
entry:
%a.1 = getelementptr inbounds i8 addrspace(3)*, i8 addrspace(3)* addrspace(1)* %a, i64 1
%a.cast = bitcast i8 addrspace(3)* addrspace(1)* %a to i64 addrspace(1)*
@@ -195,7 +195,7 @@ entry:
; CHECK-LABEL: @no_merge_load_i64_ptr32(
; CHECK: load i64,
; CHECK: load i8 addrspace(3)*,
-define void @no_merge_load_i64_ptr32(i64 addrspace(1)* nocapture %a) #0 {
+define amdgpu_kernel void @no_merge_load_i64_ptr32(i64 addrspace(1)* nocapture %a) #0 {
entry:
%a.1 = getelementptr inbounds i64, i64 addrspace(1)* %a, i64 1
%a.1.cast = bitcast i64 addrspace(1)* %a.1 to i8 addrspace(3)* addrspace(1)*
@@ -209,7 +209,7 @@ entry:
; CHECK-LABEL: @no_merge_load_ptr32_i64(
; CHECK: load i8 addrspace(3)*,
; CHECK: load i64,
-define void @no_merge_load_ptr32_i64(i64 addrspace(1)* nocapture %a) #0 {
+define amdgpu_kernel void @no_merge_load_ptr32_i64(i64 addrspace(1)* nocapture %a) #0 {
entry:
%a.cast = bitcast i64 addrspace(1)* %a to i8 addrspace(3)* addrspace(1)*
%a.1 = getelementptr inbounds i64, i64 addrspace(1)* %a, i64 1
@@ -226,7 +226,7 @@ entry:
; CHECK: load <2 x i8 addrspace(1)*>
; CHECK: store <2 x i8 addrspace(1)*>
; CHECK: store <2 x i8 addrspace(1)*>
-define void @merge_v2p1i8_v2p1i8(<2 x i8 addrspace(1)*> addrspace(1)* nocapture noalias %a, <2 x i8 addrspace(1)*> addrspace(1)* nocapture readonly noalias %b) #0 {
+define amdgpu_kernel void @merge_v2p1i8_v2p1i8(<2 x i8 addrspace(1)*> addrspace(1)* nocapture noalias %a, <2 x i8 addrspace(1)*> addrspace(1)* nocapture readonly noalias %b) #0 {
entry:
%a.1 = getelementptr inbounds <2 x i8 addrspace(1)*>, <2 x i8 addrspace(1)*> addrspace(1)* %a, i64 1
%b.1 = getelementptr inbounds <2 x i8 addrspace(1)*>, <2 x i8 addrspace(1)*> addrspace(1)* %b, i64 1
@@ -245,7 +245,7 @@ entry:
; CHECK: [[ELT0_INT:%[^ ]+]] = inttoptr i64 [[ELT0]] to i8 addrspace(1)*
; CHECK: [[ELT1_INT:%[^ ]+]] = extractelement <2 x i64> %{{[^ ]+}}, i32 1
; CHECK: bitcast i64 [[ELT1_INT]] to double
-define void @merge_load_ptr64_f64(double addrspace(1)* nocapture %a) #0 {
+define amdgpu_kernel void @merge_load_ptr64_f64(double addrspace(1)* nocapture %a) #0 {
entry:
%a.cast = bitcast double addrspace(1)* %a to i8 addrspace(1)* addrspace(1)*
%a.1 = getelementptr inbounds double, double addrspace(1)* %a, i64 1
@@ -262,7 +262,7 @@ entry:
; CHECK: bitcast i64 [[ELT0]] to double
; CHECK: [[ELT1:%[^ ]+]] = extractelement <2 x i64> %{{[^ ]+}}, i32 1
; CHECK: inttoptr i64 [[ELT1]] to i8 addrspace(1)*
-define void @merge_load_f64_ptr64(double addrspace(1)* nocapture %a) #0 {
+define amdgpu_kernel void @merge_load_f64_ptr64(double addrspace(1)* nocapture %a) #0 {
entry:
%a.1 = getelementptr inbounds double, double addrspace(1)* %a, i64 1
%a.1.cast = bitcast double addrspace(1)* %a.1 to i8 addrspace(1)* addrspace(1)*
@@ -279,7 +279,7 @@ entry:
; CHECK: [[ELT1_INT:%[^ ]+]] = bitcast double %val1 to i64
; CHECK: insertelement <2 x i64> %{{[^ ]+}}, i64 [[ELT1_INT]], i32 1
; CHECK: store <2 x i64>
-define void @merge_store_ptr64_f64(double addrspace(1)* nocapture %a, i8 addrspace(1)* %ptr0, double %val1) #0 {
+define amdgpu_kernel void @merge_store_ptr64_f64(double addrspace(1)* nocapture %a, i8 addrspace(1)* %ptr0, double %val1) #0 {
entry:
%a.cast = bitcast double addrspace(1)* %a to i8 addrspace(1)* addrspace(1)*
%a.1 = getelementptr inbounds double, double addrspace(1)* %a, i64 1
@@ -296,7 +296,7 @@ entry:
; CHECK: [[ELT1_INT:%[^ ]+]] = ptrtoint i8 addrspace(1)* %ptr1 to i64
; CHECK: insertelement <2 x i64> %{{[^ ]+}}, i64 [[ELT1_INT]], i32 1
; CHECK: store <2 x i64>
-define void @merge_store_f64_ptr64(i8 addrspace(1)* addrspace(1)* nocapture %a, double %val0, i8 addrspace(1)* %ptr1) #0 {
+define amdgpu_kernel void @merge_store_f64_ptr64(i8 addrspace(1)* addrspace(1)* nocapture %a, double %val0, i8 addrspace(1)* %ptr1) #0 {
entry:
%a.1 = getelementptr inbounds i8 addrspace(1)*, i8 addrspace(1)* addrspace(1)* %a, i64 1
%a.cast = bitcast i8 addrspace(1)* addrspace(1)* %a to double addrspace(1)*
generated by cgit v1.2.3 (git 2.25.1) at 2025-08-10 18:21:21 +0000