0bc4b2d337
Currently Clang use int32 to represent sampler_t, which have been a source of issue for some backends, because in some backends sampler_t cannot be represented by int32. They have to depend on kernel argument metadata and use IPA to find the sampler arguments and global variables and transform them to target specific sampler type.
This patch uses opaque pointer type opencl.sampler_t* for sampler_t. For each use of file-scope sampler variable, it generates a function call of __translate_sampler_initializer. For each initialization of function-scope sampler variable, it generates a function call of __translate_sampler_initializer.
Each builtin library can implement its own __translate_sampler_initializer(). Since the real sampler type tends to be architecture dependent, allowing it to be initialized by a library function simplifies backend design. A typical implementation of __translate_sampler_initializer could be a table lookup of real sampler literal values. Since its argument is always a literal, the returned pointer is known at compile time and easily optimized to finally become some literal values directly put into image read instructions.
This patch is partially based on Alexey Sotkin's work in Khronos Clang (3d4eec6162).
Differential Revision: https://reviews.llvm.org/D21567
llvm-svn: 277024
58 lines
2.6 KiB
Common Lisp
58 lines
2.6 KiB
Common Lisp
// RUN: %clang_cc1 %s -emit-llvm -triple spir-unknown-unknown -o - -O0 | FileCheck %s
|
|
//
|
|
// This test covers 5 cases of sampler initialzation:
|
|
// 1. function argument passing
|
|
// 1a. argument is a file-scope variable
|
|
// 1b. argument is a function-scope variable
|
|
// 1c. argument is one of caller function's parameters
|
|
// 2. variable initialization
|
|
// 2a. initializing a file-scope variable
|
|
// 2b. initializing a function-scope variable
|
|
|
|
#define CLK_ADDRESS_CLAMP_TO_EDGE 2
|
|
#define CLK_NORMALIZED_COORDS_TRUE 1
|
|
#define CLK_FILTER_NEAREST 0x10
|
|
#define CLK_FILTER_LINEAR 0x20
|
|
|
|
// CHECK: %opencl.sampler_t = type opaque
|
|
|
|
// Case 2a
|
|
constant sampler_t glb_smp = CLK_ADDRESS_CLAMP_TO_EDGE | CLK_NORMALIZED_COORDS_TRUE | CLK_FILTER_LINEAR;
|
|
// CHECK-NOT: glb_smp
|
|
|
|
void fnc4smp(sampler_t s) {}
|
|
// CHECK: define spir_func void @fnc4smp(%opencl.sampler_t addrspace(2)* %
|
|
|
|
kernel void foo(sampler_t smp_par) {
|
|
// CHECK-LABEL: define spir_kernel void @foo(%opencl.sampler_t addrspace(2)* %smp_par)
|
|
// CHECK: [[smp_par_ptr:%[A-Za-z0-9_\.]+]] = alloca %opencl.sampler_t addrspace(2)*
|
|
|
|
// Case 2b
|
|
sampler_t smp = CLK_ADDRESS_CLAMP_TO_EDGE | CLK_NORMALIZED_COORDS_TRUE | CLK_FILTER_NEAREST;
|
|
// CHECK: [[smp_ptr:%[A-Za-z0-9_\.]+]] = alloca %opencl.sampler_t addrspace(2)*
|
|
// CHECK: [[SAMP:%[0-9]+]] = call %opencl.sampler_t addrspace(2)* @__translate_sampler_initializer(i32 19)
|
|
// CHECK: store %opencl.sampler_t addrspace(2)* [[SAMP]], %opencl.sampler_t addrspace(2)** [[smp_ptr]]
|
|
|
|
// Case 1b
|
|
fnc4smp(smp);
|
|
// CHECK-NOT: call %opencl.sampler_t addrspace(2)* @__translate_sampler_initializer(i32 19)
|
|
// CHECK: [[SAMP:%[0-9]+]] = load %opencl.sampler_t addrspace(2)*, %opencl.sampler_t addrspace(2)** [[smp_ptr]]
|
|
// CHECK: call spir_func void @fnc4smp(%opencl.sampler_t addrspace(2)* [[SAMP]])
|
|
|
|
// Case 1b
|
|
fnc4smp(smp);
|
|
// CHECK-NOT: call %opencl.sampler_t addrspace(2)* @__translate_sampler_initializer(i32 19)
|
|
// CHECK: [[SAMP:%[0-9]+]] = load %opencl.sampler_t addrspace(2)*, %opencl.sampler_t addrspace(2)** [[smp_ptr]]
|
|
// CHECK: call spir_func void @fnc4smp(%opencl.sampler_t addrspace(2)* [[SAMP]])
|
|
|
|
// Case 1a
|
|
fnc4smp(glb_smp);
|
|
// CHECK: [[SAMP:%[0-9]+]] = call %opencl.sampler_t addrspace(2)* @__translate_sampler_initializer(i32 35)
|
|
// CHECK: call spir_func void @fnc4smp(%opencl.sampler_t addrspace(2)* [[SAMP]])
|
|
|
|
// Case 1c
|
|
fnc4smp(smp_par);
|
|
// CHECK: [[SAMP:%[0-9]+]] = load %opencl.sampler_t addrspace(2)*, %opencl.sampler_t addrspace(2)** [[smp_par_ptr]]
|
|
// CHECK: call spir_func void @fnc4smp(%opencl.sampler_t addrspace(2)* [[SAMP]])
|
|
}
|