[clang][CodeGen][AMDGPU] Enable AMDGPU `printf` for `spirv64-amd-amdhsa` (#97132)

This enables the AMDGPU specific implementation of `printf` when
compiling for AMDGCN flavoured SPIR-V, the consequence being that the
expansion into ROCDL calls & friends gets expanded before "lowering" to
SPIR-V and gets carried through. The only relatively "novel" aspect is
that the `callAppendStringN` is simplified to take the type of the
passed in arguments, as opposed to querying them from the module. This
is a neutral change since the arguments were passed directly to the
call, without any attempt to cast them, hence the assumption that the
actual types match the formal ones was already baked in.

2 files changed, 210 insertions, 27 deletions

diff --git a/clang/test/CodeGenHIP/printf-builtin.hip b/clang/test/CodeGenHIP/printf-builtin.hip
index df1fbbb6..506bb6a 100644
--- a/clang/test/CodeGenHIP/printf-builtin.hip
+++ b/clang/test/CodeGenHIP/printf-builtin.hip
@@ -1,8 +1,12 @@
 // REQUIRES: amdgpu-registered-target
 // RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -emit-llvm -disable-llvm-optzns -mprintf-kind=hostcall -fno-builtin-printf -fcuda-is-device \
 // RUN:   -o - %s | FileCheck --check-prefixes=CHECK,HOSTCALL %s
+// RUN: %clang_cc1 -triple spirv64-amd-amdhsa -emit-llvm -disable-llvm-optzns -mprintf-kind=hostcall -fno-builtin-printf -fcuda-is-device \
+// RUN:   -o - %s | FileCheck --check-prefixes=CHECK-AMDGCNSPIRV,HOSTCALL-AMDGCNSPIRV %s
 // RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -emit-llvm -disable-llvm-optzns -mprintf-kind=buffered -fno-builtin-printf -fcuda-is-device \
 // RUN:   -o - %s | FileCheck --check-prefixes=CHECK,BUFFERED %s
+// RUN: %clang_cc1 -triple spirv64-amd-amdhsa -emit-llvm -disable-llvm-optzns -mprintf-kind=buffered -fno-builtin-printf -fcuda-is-device \
+// RUN:   -o - %s | FileCheck --check-prefixes=CHECK-AMDGCNSPIRV,BUFFERED-AMDGCNSPIRV %s
 
 #define __device__ __attribute__((device))
 
@@ -11,13 +15,17 @@ extern "C" __device__ int printf(const char *format, ...);
 // CHECK-LABEL: @_Z4foo1v()
 __device__ int foo1() {
   // HOSTCALL: call i64 @__ockl_printf_begin
+  // HOSTCALL-AMDGCNSPIRV: call addrspace(4) i64 @__ockl_printf_begin
   // BUFFERED: call ptr addrspace(1) @__printf_alloc
+  // BUFFERED-AMDGCNSPIRV: call addrspace(4) ptr addrspace(1) @__printf_alloc
   // CHECK-NOT: call i32 (ptr, ...) @printf
+  // CHECK-AMDGCNSPIRV-NOT: call i32 (ptr, ...) @printf
   return __builtin_printf("Hello World\n");
 }
 
 // CHECK-LABEL: @_Z4foo2v()
 __device__ int foo2() {
   // CHECK: call i32 (ptr, ...) @printf
+  // CHECK-AMDGCNSPIRV: call spir_func addrspace(4) i32 (ptr addrspace(4), ...) @printf
   return printf("Hello World\n");
 }
diff --git a/clang/test/CodeGenHIP/printf.cpp b/clang/test/CodeGenHIP/printf.cpp
index 8c8b801..2d814d6 100644
--- a/clang/test/CodeGenHIP/printf.cpp
+++ b/clang/test/CodeGenHIP/printf.cpp
@@ -1,44 +1,219 @@
+// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 5
 // REQUIRES: amdgpu-registered-target
 // RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -x hip -emit-llvm -fcuda-is-device \
-// RUN:   -o - %s | FileCheck --enable-var-scope %s
+// RUN:   -o - %s | FileCheck --check-prefix=AMDGCN --enable-var-scope %s
+// RUN: %clang_cc1 -triple spirv64-amd-amdhsa -x hip -emit-llvm -fcuda-is-device \
+// RUN:   -o - %s | FileCheck --check-prefix=AMDGCNSPIRV --enable-var-scope %s
 
 #define __device__ __attribute__((device))
 
 extern "C" __device__ int printf(const char *format, ...);
 
+// AMDGCN-LABEL: define dso_local noundef i32 @_Z4foo1v(
+// AMDGCN-SAME: ) #[[ATTR0:[0-9]+]] {
+// AMDGCN-NEXT:  [[ENTRY:.*]]:
+// AMDGCN-NEXT:    [[RETVAL:%.*]] = alloca i32, align 4, addrspace(5)
+// AMDGCN-NEXT:    [[S:%.*]] = alloca ptr, align 8, addrspace(5)
+// AMDGCN-NEXT:    [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
+// AMDGCN-NEXT:    [[S_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[S]] to ptr
+// AMDGCN-NEXT:    store ptr addrspacecast (ptr addrspace(4) @.str to ptr), ptr [[S_ASCAST]], align 8
+// AMDGCN-NEXT:    [[TMP0:%.*]] = load ptr, ptr [[S_ASCAST]], align 8
+// AMDGCN-NEXT:    [[TMP1:%.*]] = load ptr, ptr [[S_ASCAST]], align 8
+// AMDGCN-NEXT:    [[TMP2:%.*]] = call i64 @__ockl_printf_begin(i64 0)
+// AMDGCN-NEXT:    [[TMP3:%.*]] = icmp eq ptr addrspacecast (ptr addrspace(4) @.str.1 to ptr), null
+// AMDGCN-NEXT:    br i1 [[TMP3]], label %[[STRLEN_JOIN:.*]], label %[[STRLEN_WHILE:.*]]
+// AMDGCN:       [[STRLEN_WHILE]]:
+// AMDGCN-NEXT:    [[TMP4:%.*]] = phi ptr [ addrspacecast (ptr addrspace(4) @.str.1 to ptr), %[[ENTRY]] ], [ [[TMP5:%.*]], %[[STRLEN_WHILE]] ]
+// AMDGCN-NEXT:    [[TMP5]] = getelementptr i8, ptr [[TMP4]], i64 1
+// AMDGCN-NEXT:    [[TMP6:%.*]] = load i8, ptr [[TMP4]], align 1
+// AMDGCN-NEXT:    [[TMP7:%.*]] = icmp eq i8 [[TMP6]], 0
+// AMDGCN-NEXT:    br i1 [[TMP7]], label %[[STRLEN_WHILE_DONE:.*]], label %[[STRLEN_WHILE]]
+// AMDGCN:       [[STRLEN_WHILE_DONE]]:
+// AMDGCN-NEXT:    [[TMP8:%.*]] = ptrtoint ptr [[TMP4]] to i64
+// AMDGCN-NEXT:    [[TMP9:%.*]] = sub i64 [[TMP8]], ptrtoint (ptr addrspacecast (ptr addrspace(4) @.str.1 to ptr) to i64)
+// AMDGCN-NEXT:    [[TMP10:%.*]] = add i64 [[TMP9]], 1
+// AMDGCN-NEXT:    br label %[[STRLEN_JOIN]]
+// AMDGCN:       [[STRLEN_JOIN]]:
+// AMDGCN-NEXT:    [[TMP11:%.*]] = phi i64 [ [[TMP10]], %[[STRLEN_WHILE_DONE]] ], [ 0, %[[ENTRY]] ]
+// AMDGCN-NEXT:    [[TMP12:%.*]] = call i64 @__ockl_printf_append_string_n(i64 [[TMP2]], ptr addrspacecast (ptr addrspace(4) @.str.1 to ptr), i64 [[TMP11]], i32 0)
+// AMDGCN-NEXT:    [[TMP13:%.*]] = call i64 @__ockl_printf_append_args(i64 [[TMP12]], i32 1, i64 8, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i32 0)
+// AMDGCN-NEXT:    [[TMP14:%.*]] = call i64 @__ockl_printf_append_args(i64 [[TMP13]], i32 1, i64 4614256650576692846, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i32 0)
+// AMDGCN-NEXT:    [[TMP15:%.*]] = call i64 @__ockl_printf_append_args(i64 [[TMP14]], i32 1, i64 8, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i32 0)
+// AMDGCN-NEXT:    [[TMP16:%.*]] = call i64 @__ockl_printf_append_args(i64 [[TMP15]], i32 1, i64 4, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i32 0)
+// AMDGCN-NEXT:    [[TMP17:%.*]] = icmp eq ptr [[TMP0]], null
+// AMDGCN-NEXT:    br i1 [[TMP17]], label %[[STRLEN_JOIN1:.*]], label %[[STRLEN_WHILE2:.*]]
+// AMDGCN:       [[STRLEN_WHILE2]]:
+// AMDGCN-NEXT:    [[TMP18:%.*]] = phi ptr [ [[TMP0]], %[[STRLEN_JOIN]] ], [ [[TMP19:%.*]], %[[STRLEN_WHILE2]] ]
+// AMDGCN-NEXT:    [[TMP19]] = getelementptr i8, ptr [[TMP18]], i64 1
+// AMDGCN-NEXT:    [[TMP20:%.*]] = load i8, ptr [[TMP18]], align 1
+// AMDGCN-NEXT:    [[TMP21:%.*]] = icmp eq i8 [[TMP20]], 0
+// AMDGCN-NEXT:    br i1 [[TMP21]], label %[[STRLEN_WHILE_DONE3:.*]], label %[[STRLEN_WHILE2]]
+// AMDGCN:       [[STRLEN_WHILE_DONE3]]:
+// AMDGCN-NEXT:    [[TMP22:%.*]] = ptrtoint ptr [[TMP0]] to i64
+// AMDGCN-NEXT:    [[TMP23:%.*]] = ptrtoint ptr [[TMP18]] to i64
+// AMDGCN-NEXT:    [[TMP24:%.*]] = sub i64 [[TMP23]], [[TMP22]]
+// AMDGCN-NEXT:    [[TMP25:%.*]] = add i64 [[TMP24]], 1
+// AMDGCN-NEXT:    br label %[[STRLEN_JOIN1]]
+// AMDGCN:       [[STRLEN_JOIN1]]:
+// AMDGCN-NEXT:    [[TMP26:%.*]] = phi i64 [ [[TMP25]], %[[STRLEN_WHILE_DONE3]] ], [ 0, %[[STRLEN_JOIN]] ]
+// AMDGCN-NEXT:    [[TMP27:%.*]] = call i64 @__ockl_printf_append_string_n(i64 [[TMP16]], ptr [[TMP0]], i64 [[TMP26]], i32 0)
+// AMDGCN-NEXT:    [[TMP28:%.*]] = ptrtoint ptr [[TMP1]] to i64
+// AMDGCN-NEXT:    [[TMP29:%.*]] = call i64 @__ockl_printf_append_args(i64 [[TMP27]], i32 1, i64 [[TMP28]], i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i32 1)
+// AMDGCN-NEXT:    [[TMP30:%.*]] = trunc i64 [[TMP29]] to i32
+// AMDGCN-NEXT:    ret i32 [[TMP30]]
+//
+// AMDGCNSPIRV-LABEL: define spir_func noundef i32 @_Z4foo1v(
+// AMDGCNSPIRV-SAME: ) addrspace(4) #[[ATTR0:[0-9]+]] {
+// AMDGCNSPIRV-NEXT:  [[ENTRY:.*]]:
+// AMDGCNSPIRV-NEXT:    [[RETVAL:%.*]] = alloca i32, align 4
+// AMDGCNSPIRV-NEXT:    [[S:%.*]] = alloca ptr addrspace(4), align 8
+// AMDGCNSPIRV-NEXT:    [[RETVAL_ASCAST:%.*]] = addrspacecast ptr [[RETVAL]] to ptr addrspace(4)
+// AMDGCNSPIRV-NEXT:    [[S_ASCAST:%.*]] = addrspacecast ptr [[S]] to ptr addrspace(4)
+// AMDGCNSPIRV-NEXT:    store ptr addrspace(4) addrspacecast (ptr addrspace(1) @.str to ptr addrspace(4)), ptr addrspace(4) [[S_ASCAST]], align 8
+// AMDGCNSPIRV-NEXT:    [[TMP0:%.*]] = load ptr addrspace(4), ptr addrspace(4) [[S_ASCAST]], align 8
+// AMDGCNSPIRV-NEXT:    [[TMP1:%.*]] = load ptr addrspace(4), ptr addrspace(4) [[S_ASCAST]], align 8
+// AMDGCNSPIRV-NEXT:    [[TMP2:%.*]] = call addrspace(4) i64 @__ockl_printf_begin(i64 0)
+// AMDGCNSPIRV-NEXT:    [[TMP3:%.*]] = icmp eq ptr addrspace(4) addrspacecast (ptr addrspace(1) @.str.1 to ptr addrspace(4)), null
+// AMDGCNSPIRV-NEXT:    br i1 [[TMP3]], label %[[STRLEN_JOIN:.*]], label %[[STRLEN_WHILE:.*]]
+// AMDGCNSPIRV:       [[STRLEN_WHILE]]:
+// AMDGCNSPIRV-NEXT:    [[TMP4:%.*]] = phi ptr addrspace(4) [ addrspacecast (ptr addrspace(1) @.str.1 to ptr addrspace(4)), %[[ENTRY]] ], [ [[TMP5:%.*]], %[[STRLEN_WHILE]] ]
+// AMDGCNSPIRV-NEXT:    [[TMP5]] = getelementptr i8, ptr addrspace(4) [[TMP4]], i64 1
+// AMDGCNSPIRV-NEXT:    [[TMP6:%.*]] = load i8, ptr addrspace(4) [[TMP4]], align 1
+// AMDGCNSPIRV-NEXT:    [[TMP7:%.*]] = icmp eq i8 [[TMP6]], 0
+// AMDGCNSPIRV-NEXT:    br i1 [[TMP7]], label %[[STRLEN_WHILE_DONE:.*]], label %[[STRLEN_WHILE]]
+// AMDGCNSPIRV:       [[STRLEN_WHILE_DONE]]:
+// AMDGCNSPIRV-NEXT:    [[TMP8:%.*]] = ptrtoint ptr addrspace(4) [[TMP4]] to i64
+// AMDGCNSPIRV-NEXT:    [[TMP9:%.*]] = sub i64 [[TMP8]], ptrtoint (ptr addrspace(4) addrspacecast (ptr addrspace(1) @.str.1 to ptr addrspace(4)) to i64)
+// AMDGCNSPIRV-NEXT:    [[TMP10:%.*]] = add i64 [[TMP9]], 1
+// AMDGCNSPIRV-NEXT:    br label %[[STRLEN_JOIN]]
+// AMDGCNSPIRV:       [[STRLEN_JOIN]]:
+// AMDGCNSPIRV-NEXT:    [[TMP11:%.*]] = phi i64 [ [[TMP10]], %[[STRLEN_WHILE_DONE]] ], [ 0, %[[ENTRY]] ]
+// AMDGCNSPIRV-NEXT:    [[TMP12:%.*]] = call addrspace(4) i64 @__ockl_printf_append_string_n(i64 [[TMP2]], ptr addrspace(4) addrspacecast (ptr addrspace(1) @.str.1 to ptr addrspace(4)), i64 [[TMP11]], i32 0)
+// AMDGCNSPIRV-NEXT:    [[TMP13:%.*]] = call addrspace(4) i64 @__ockl_printf_append_args(i64 [[TMP12]], i32 1, i64 8, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i32 0)
+// AMDGCNSPIRV-NEXT:    [[TMP14:%.*]] = call addrspace(4) i64 @__ockl_printf_append_args(i64 [[TMP13]], i32 1, i64 4614256650576692846, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i32 0)
+// AMDGCNSPIRV-NEXT:    [[TMP15:%.*]] = call addrspace(4) i64 @__ockl_printf_append_args(i64 [[TMP14]], i32 1, i64 8, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i32 0)
+// AMDGCNSPIRV-NEXT:    [[TMP16:%.*]] = call addrspace(4) i64 @__ockl_printf_append_args(i64 [[TMP15]], i32 1, i64 4, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i32 0)
+// AMDGCNSPIRV-NEXT:    [[TMP17:%.*]] = icmp eq ptr addrspace(4) [[TMP0]], null
+// AMDGCNSPIRV-NEXT:    br i1 [[TMP17]], label %[[STRLEN_JOIN1:.*]], label %[[STRLEN_WHILE2:.*]]
+// AMDGCNSPIRV:       [[STRLEN_WHILE2]]:
+// AMDGCNSPIRV-NEXT:    [[TMP18:%.*]] = phi ptr addrspace(4) [ [[TMP0]], %[[STRLEN_JOIN]] ], [ [[TMP19:%.*]], %[[STRLEN_WHILE2]] ]
+// AMDGCNSPIRV-NEXT:    [[TMP19]] = getelementptr i8, ptr addrspace(4) [[TMP18]], i64 1
+// AMDGCNSPIRV-NEXT:    [[TMP20:%.*]] = load i8, ptr addrspace(4) [[TMP18]], align 1
+// AMDGCNSPIRV-NEXT:    [[TMP21:%.*]] = icmp eq i8 [[TMP20]], 0
+// AMDGCNSPIRV-NEXT:    br i1 [[TMP21]], label %[[STRLEN_WHILE_DONE3:.*]], label %[[STRLEN_WHILE2]]
+// AMDGCNSPIRV:       [[STRLEN_WHILE_DONE3]]:
+// AMDGCNSPIRV-NEXT:    [[TMP22:%.*]] = ptrtoint ptr addrspace(4) [[TMP0]] to i64
+// AMDGCNSPIRV-NEXT:    [[TMP23:%.*]] = ptrtoint ptr addrspace(4) [[TMP18]] to i64
+// AMDGCNSPIRV-NEXT:    [[TMP24:%.*]] = sub i64 [[TMP23]], [[TMP22]]
+// AMDGCNSPIRV-NEXT:    [[TMP25:%.*]] = add i64 [[TMP24]], 1
+// AMDGCNSPIRV-NEXT:    br label %[[STRLEN_JOIN1]]
+// AMDGCNSPIRV:       [[STRLEN_JOIN1]]:
+// AMDGCNSPIRV-NEXT:    [[TMP26:%.*]] = phi i64 [ [[TMP25]], %[[STRLEN_WHILE_DONE3]] ], [ 0, %[[STRLEN_JOIN]] ]
+// AMDGCNSPIRV-NEXT:    [[TMP27:%.*]] = call addrspace(4) i64 @__ockl_printf_append_string_n(i64 [[TMP16]], ptr addrspace(4) [[TMP0]], i64 [[TMP26]], i32 0)
+// AMDGCNSPIRV-NEXT:    [[TMP28:%.*]] = ptrtoint ptr addrspace(4) [[TMP1]] to i64
+// AMDGCNSPIRV-NEXT:    [[TMP29:%.*]] = call addrspace(4) i64 @__ockl_printf_append_args(i64 [[TMP27]], i32 1, i64 [[TMP28]], i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i32 1)
+// AMDGCNSPIRV-NEXT:    [[TMP30:%.*]] = trunc i64 [[TMP29]] to i32
+// AMDGCNSPIRV-NEXT:    ret i32 [[TMP30]]
+//
 __device__ int foo1() {
   const char *s = "hello world";
   return printf("%.*f %*.*s %p\n", 8, 3.14159, 8, 4, s, s);
 }
 
-// CHECK-LABEL: @_Z4foo1v()
-// CHECK: [[BEGIN:%.*]]   = call i64 @__ockl_printf_begin(i64 0)
-// CHECK: [[STRLEN1:%.*]] = phi i64 [ %{{[^,]*}}, %{{[^ ]*}} ], [ 0, %{{[^ ]*}} ]
-// CHECK: [[APPEND1:%.*]] = call i64 @__ockl_printf_append_string_n(i64 [[BEGIN]], {{.*}}, i64 [[STRLEN1]], i32 0)
-// CHECK: [[APPEND2:%.*]] = call i64 @__ockl_printf_append_args(i64 [[APPEND1]], i32 1, i64 8, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i32 0)
-// CHECK: [[APPEND3:%.*]] = call i64 @__ockl_printf_append_args(i64 [[APPEND2]], i32 1, i64 4614256650576692846, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i32 0)
-// CHECK: [[APPEND4:%.*]] = call i64 @__ockl_printf_append_args(i64 [[APPEND3]], i32 1, i64 8, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i32 0)
-// CHECK: [[APPEND5:%.*]] = call i64 @__ockl_printf_append_args(i64 [[APPEND4]], i32 1, i64 4, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i32 0)
-// CHECK: [[STRLEN2:%.*]] = phi i64 [ %{{[^,]*}}, %{{[^ ]*}} ], [ 0, %{{[^ ]*}} ]
-// CHECK: [[APPEND6:%.*]] = call i64 @__ockl_printf_append_string_n(i64 [[APPEND5]], {{.*}}, i64 [[STRLEN2]], i32 0)
-// CHECK: [[PTR2INT:%.*]] = ptrtoint ptr %{{.*}} to i64
-// CHECK: [[APPEND7:%.*]] = call i64 @__ockl_printf_append_args(i64 [[APPEND6]], i32 1, i64 [[PTR2INT]], i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i32 1)
-// CHECK: [[RETURN:%.*]]  = trunc i64 [[APPEND7]] to i32
-// CHECK: ret i32 [[RETURN]]
-
 __device__ char *dstr;
 
+// AMDGCN-LABEL: define dso_local noundef i32 @_Z4foo2v(
+// AMDGCN-SAME: ) #[[ATTR0:[0-9]+]] {
+// AMDGCN-NEXT:  [[ENTRY:.*]]:
+// AMDGCN-NEXT:    [[RETVAL:%.*]] = alloca i32, align 4, addrspace(5)
+// AMDGCN-NEXT:    [[RETVAL_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL]] to ptr
+// AMDGCN-NEXT:    [[TMP0:%.*]] = load ptr, ptr addrspacecast (ptr addrspace(1) @dstr to ptr), align 8
+// AMDGCN-NEXT:    [[TMP1:%.*]] = load ptr, ptr addrspacecast (ptr addrspace(1) @dstr to ptr), align 8
+// AMDGCN-NEXT:    [[TMP2:%.*]] = call i64 @__ockl_printf_begin(i64 0)
+// AMDGCN-NEXT:    [[TMP3:%.*]] = icmp eq ptr addrspacecast (ptr addrspace(4) @.str.2 to ptr), null
+// AMDGCN-NEXT:    br i1 [[TMP3]], label %[[STRLEN_JOIN:.*]], label %[[STRLEN_WHILE:.*]]
+// AMDGCN:       [[STRLEN_WHILE]]:
+// AMDGCN-NEXT:    [[TMP4:%.*]] = phi ptr [ addrspacecast (ptr addrspace(4) @.str.2 to ptr), %[[ENTRY]] ], [ [[TMP5:%.*]], %[[STRLEN_WHILE]] ]
+// AMDGCN-NEXT:    [[TMP5]] = getelementptr i8, ptr [[TMP4]], i64 1
+// AMDGCN-NEXT:    [[TMP6:%.*]] = load i8, ptr [[TMP4]], align 1
+// AMDGCN-NEXT:    [[TMP7:%.*]] = icmp eq i8 [[TMP6]], 0
+// AMDGCN-NEXT:    br i1 [[TMP7]], label %[[STRLEN_WHILE_DONE:.*]], label %[[STRLEN_WHILE]]
+// AMDGCN:       [[STRLEN_WHILE_DONE]]:
+// AMDGCN-NEXT:    [[TMP8:%.*]] = ptrtoint ptr [[TMP4]] to i64
+// AMDGCN-NEXT:    [[TMP9:%.*]] = sub i64 [[TMP8]], ptrtoint (ptr addrspacecast (ptr addrspace(4) @.str.2 to ptr) to i64)
+// AMDGCN-NEXT:    [[TMP10:%.*]] = add i64 [[TMP9]], 1
+// AMDGCN-NEXT:    br label %[[STRLEN_JOIN]]
+// AMDGCN:       [[STRLEN_JOIN]]:
+// AMDGCN-NEXT:    [[TMP11:%.*]] = phi i64 [ [[TMP10]], %[[STRLEN_WHILE_DONE]] ], [ 0, %[[ENTRY]] ]
+// AMDGCN-NEXT:    [[TMP12:%.*]] = call i64 @__ockl_printf_append_string_n(i64 [[TMP2]], ptr addrspacecast (ptr addrspace(4) @.str.2 to ptr), i64 [[TMP11]], i32 0)
+// AMDGCN-NEXT:    [[TMP13:%.*]] = icmp eq ptr [[TMP0]], null
+// AMDGCN-NEXT:    br i1 [[TMP13]], label %[[STRLEN_JOIN1:.*]], label %[[STRLEN_WHILE2:.*]]
+// AMDGCN:       [[STRLEN_WHILE2]]:
+// AMDGCN-NEXT:    [[TMP14:%.*]] = phi ptr [ [[TMP0]], %[[STRLEN_JOIN]] ], [ [[TMP15:%.*]], %[[STRLEN_WHILE2]] ]
+// AMDGCN-NEXT:    [[TMP15]] = getelementptr i8, ptr [[TMP14]], i64 1
+// AMDGCN-NEXT:    [[TMP16:%.*]] = load i8, ptr [[TMP14]], align 1
+// AMDGCN-NEXT:    [[TMP17:%.*]] = icmp eq i8 [[TMP16]], 0
+// AMDGCN-NEXT:    br i1 [[TMP17]], label %[[STRLEN_WHILE_DONE3:.*]], label %[[STRLEN_WHILE2]]
+// AMDGCN:       [[STRLEN_WHILE_DONE3]]:
+// AMDGCN-NEXT:    [[TMP18:%.*]] = ptrtoint ptr [[TMP0]] to i64
+// AMDGCN-NEXT:    [[TMP19:%.*]] = ptrtoint ptr [[TMP14]] to i64
+// AMDGCN-NEXT:    [[TMP20:%.*]] = sub i64 [[TMP19]], [[TMP18]]
+// AMDGCN-NEXT:    [[TMP21:%.*]] = add i64 [[TMP20]], 1
+// AMDGCN-NEXT:    br label %[[STRLEN_JOIN1]]
+// AMDGCN:       [[STRLEN_JOIN1]]:
+// AMDGCN-NEXT:    [[TMP22:%.*]] = phi i64 [ [[TMP21]], %[[STRLEN_WHILE_DONE3]] ], [ 0, %[[STRLEN_JOIN]] ]
+// AMDGCN-NEXT:    [[TMP23:%.*]] = call i64 @__ockl_printf_append_string_n(i64 [[TMP12]], ptr [[TMP0]], i64 [[TMP22]], i32 0)
+// AMDGCN-NEXT:    [[TMP24:%.*]] = ptrtoint ptr [[TMP1]] to i64
+// AMDGCN-NEXT:    [[TMP25:%.*]] = call i64 @__ockl_printf_append_args(i64 [[TMP23]], i32 1, i64 [[TMP24]], i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i32 1)
+// AMDGCN-NEXT:    [[TMP26:%.*]] = trunc i64 [[TMP25]] to i32
+// AMDGCN-NEXT:    ret i32 [[TMP26]]
+//
+// AMDGCNSPIRV-LABEL: define spir_func noundef i32 @_Z4foo2v(
+// AMDGCNSPIRV-SAME: ) addrspace(4) #[[ATTR0:[0-9]+]] {
+// AMDGCNSPIRV-NEXT:  [[ENTRY:.*]]:
+// AMDGCNSPIRV-NEXT:    [[RETVAL:%.*]] = alloca i32, align 4
+// AMDGCNSPIRV-NEXT:    [[RETVAL_ASCAST:%.*]] = addrspacecast ptr [[RETVAL]] to ptr addrspace(4)
+// AMDGCNSPIRV-NEXT:    [[TMP0:%.*]] = load ptr addrspace(4), ptr addrspace(4) addrspacecast (ptr addrspace(1) @dstr to ptr addrspace(4)), align 8
+// AMDGCNSPIRV-NEXT:    [[TMP1:%.*]] = load ptr addrspace(4), ptr addrspace(4) addrspacecast (ptr addrspace(1) @dstr to ptr addrspace(4)), align 8
+// AMDGCNSPIRV-NEXT:    [[TMP2:%.*]] = call addrspace(4) i64 @__ockl_printf_begin(i64 0)
+// AMDGCNSPIRV-NEXT:    [[TMP3:%.*]] = icmp eq ptr addrspace(4) addrspacecast (ptr addrspace(1) @.str.2 to ptr addrspace(4)), null
+// AMDGCNSPIRV-NEXT:    br i1 [[TMP3]], label %[[STRLEN_JOIN:.*]], label %[[STRLEN_WHILE:.*]]
+// AMDGCNSPIRV:       [[STRLEN_WHILE]]:
+// AMDGCNSPIRV-NEXT:    [[TMP4:%.*]] = phi ptr addrspace(4) [ addrspacecast (ptr addrspace(1) @.str.2 to ptr addrspace(4)), %[[ENTRY]] ], [ [[TMP5:%.*]], %[[STRLEN_WHILE]] ]
+// AMDGCNSPIRV-NEXT:    [[TMP5]] = getelementptr i8, ptr addrspace(4) [[TMP4]], i64 1
+// AMDGCNSPIRV-NEXT:    [[TMP6:%.*]] = load i8, ptr addrspace(4) [[TMP4]], align 1
+// AMDGCNSPIRV-NEXT:    [[TMP7:%.*]] = icmp eq i8 [[TMP6]], 0
+// AMDGCNSPIRV-NEXT:    br i1 [[TMP7]], label %[[STRLEN_WHILE_DONE:.*]], label %[[STRLEN_WHILE]]
+// AMDGCNSPIRV:       [[STRLEN_WHILE_DONE]]:
+// AMDGCNSPIRV-NEXT:    [[TMP8:%.*]] = ptrtoint ptr addrspace(4) [[TMP4]] to i64
+// AMDGCNSPIRV-NEXT:    [[TMP9:%.*]] = sub i64 [[TMP8]], ptrtoint (ptr addrspace(4) addrspacecast (ptr addrspace(1) @.str.2 to ptr addrspace(4)) to i64)
+// AMDGCNSPIRV-NEXT:    [[TMP10:%.*]] = add i64 [[TMP9]], 1
+// AMDGCNSPIRV-NEXT:    br label %[[STRLEN_JOIN]]
+// AMDGCNSPIRV:       [[STRLEN_JOIN]]:
+// AMDGCNSPIRV-NEXT:    [[TMP11:%.*]] = phi i64 [ [[TMP10]], %[[STRLEN_WHILE_DONE]] ], [ 0, %[[ENTRY]] ]
+// AMDGCNSPIRV-NEXT:    [[TMP12:%.*]] = call addrspace(4) i64 @__ockl_printf_append_string_n(i64 [[TMP2]], ptr addrspace(4) addrspacecast (ptr addrspace(1) @.str.2 to ptr addrspace(4)), i64 [[TMP11]], i32 0)
+// AMDGCNSPIRV-NEXT:    [[TMP13:%.*]] = icmp eq ptr addrspace(4) [[TMP0]], null
+// AMDGCNSPIRV-NEXT:    br i1 [[TMP13]], label %[[STRLEN_JOIN1:.*]], label %[[STRLEN_WHILE2:.*]]
+// AMDGCNSPIRV:       [[STRLEN_WHILE2]]:
+// AMDGCNSPIRV-NEXT:    [[TMP14:%.*]] = phi ptr addrspace(4) [ [[TMP0]], %[[STRLEN_JOIN]] ], [ [[TMP15:%.*]], %[[STRLEN_WHILE2]] ]
+// AMDGCNSPIRV-NEXT:    [[TMP15]] = getelementptr i8, ptr addrspace(4) [[TMP14]], i64 1
+// AMDGCNSPIRV-NEXT:    [[TMP16:%.*]] = load i8, ptr addrspace(4) [[TMP14]], align 1
+// AMDGCNSPIRV-NEXT:    [[TMP17:%.*]] = icmp eq i8 [[TMP16]], 0
+// AMDGCNSPIRV-NEXT:    br i1 [[TMP17]], label %[[STRLEN_WHILE_DONE3:.*]], label %[[STRLEN_WHILE2]]
+// AMDGCNSPIRV:       [[STRLEN_WHILE_DONE3]]:
+// AMDGCNSPIRV-NEXT:    [[TMP18:%.*]] = ptrtoint ptr addrspace(4) [[TMP0]] to i64
+// AMDGCNSPIRV-NEXT:    [[TMP19:%.*]] = ptrtoint ptr addrspace(4) [[TMP14]] to i64
+// AMDGCNSPIRV-NEXT:    [[TMP20:%.*]] = sub i64 [[TMP19]], [[TMP18]]
+// AMDGCNSPIRV-NEXT:    [[TMP21:%.*]] = add i64 [[TMP20]], 1
+// AMDGCNSPIRV-NEXT:    br label %[[STRLEN_JOIN1]]
+// AMDGCNSPIRV:       [[STRLEN_JOIN1]]:
+// AMDGCNSPIRV-NEXT:    [[TMP22:%.*]] = phi i64 [ [[TMP21]], %[[STRLEN_WHILE_DONE3]] ], [ 0, %[[STRLEN_JOIN]] ]
+// AMDGCNSPIRV-NEXT:    [[TMP23:%.*]] = call addrspace(4) i64 @__ockl_printf_append_string_n(i64 [[TMP12]], ptr addrspace(4) [[TMP0]], i64 [[TMP22]], i32 0)
+// AMDGCNSPIRV-NEXT:    [[TMP24:%.*]] = ptrtoint ptr addrspace(4) [[TMP1]] to i64
+// AMDGCNSPIRV-NEXT:    [[TMP25:%.*]] = call addrspace(4) i64 @__ockl_printf_append_args(i64 [[TMP23]], i32 1, i64 [[TMP24]], i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i32 1)
+// AMDGCNSPIRV-NEXT:    [[TMP26:%.*]] = trunc i64 [[TMP25]] to i32
+// AMDGCNSPIRV-NEXT:    ret i32 [[TMP26]]
+//
 __device__ int foo2() {
   return printf("%s %p\n", dstr, dstr);
 }
-
-// CHECK-LABEL: @_Z4foo2v()
-// CHECK: [[BEGIN:%.*]]   = call i64 @__ockl_printf_begin(i64 0)
-// CHECK: [[STRLEN1:%.*]] = phi i64 [ %{{[^,]*}}, %{{[^ ]*}} ], [ 0, %{{[^ ]*}} ]
-// CHECK: [[APPEND1:%.*]] = call i64 @__ockl_printf_append_string_n(i64 [[BEGIN]], {{.*}}, i64 [[STRLEN1]], i32 0)
-// CHECK: [[STRLEN2:%.*]] = phi i64 [ %{{[^,]*}}, %{{[^ ]*}} ], [ 0, %{{[^ ]*}} ]
-// CHECK: [[APPEND2:%.*]] = call i64 @__ockl_printf_append_string_n(i64 [[APPEND1]], {{.*}}, i64 [[STRLEN2]], i32 0)
-// CHECK: [[PTR2INT:%.*]] = ptrtoint ptr %{{.*}} to i64
-// CHECK: [[APPEND3:%.*]] = call i64 @__ockl_printf_append_args(i64 [[APPEND2]], i32 1, i64 [[PTR2INT]], i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i32 1)
-// CHECK: [[RETURN:%.*]]  = trunc i64 [[APPEND3]] to i32
-// CHECK: ret i32 [[RETURN]]