radv/gfx10: use the correct target machine for Wave32

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>

diff --git a/src/amd/vulkan/radv_llvm_helper.cpp b/src/amd/vulkan/radv_llvm_helper.cpp
index 2b14ddcf1844a61a1b489e682e99d8d4c58fecc8..612548e4219427151dcf736bcf1ff41d9df8c136 100644 (file)
--- a/src/amd/vulkan/radv_llvm_helper.cpp
+++ b/src/amd/vulkan/radv_llvm_helper.cpp
@@ -28,8 +28,10 @@
 class radv_llvm_per_thread_info {
 public:
        radv_llvm_per_thread_info(enum radeon_family arg_family,
-                               enum ac_target_machine_options arg_tm_options)
-               : family(arg_family), tm_options(arg_tm_options), passes(NULL) {}
+                               enum ac_target_machine_options arg_tm_options,
+                               unsigned arg_wave_size)
+               : family(arg_family), tm_options(arg_tm_options),
+                 wave_size(arg_wave_size), passes(NULL), passes_wave32(NULL) {}
 
        ~radv_llvm_per_thread_info()
        {
@@ -47,19 +49,28 @@ public:
                if (!passes)
                        return false;
 
+               if (llvm_info.tm_wave32) {
+                       passes_wave32 = ac_create_llvm_passes(llvm_info.tm_wave32);
+                       if (!passes_wave32)
+                               return false;
+               }
+
                return true;
        }
 
        bool compile_to_memory_buffer(LLVMModuleRef module,
                                      char **pelf_buffer, size_t *pelf_size)
        {
-               return ac_compile_module_to_elf(passes, module, pelf_buffer, pelf_size);
+               struct ac_compiler_passes *p = wave_size == 32 ? passes_wave32 : passes;
+               return ac_compile_module_to_elf(p, module, pelf_buffer, pelf_size);
        }
 
        bool is_same(enum radeon_family arg_family,
-                    enum ac_target_machine_options arg_tm_options) {
+                    enum ac_target_machine_options arg_tm_options,
+                    unsigned arg_wave_size) {
                if (arg_family == family &&
-                   arg_tm_options == tm_options)
+                   arg_tm_options == tm_options &&
+                   arg_wave_size == wave_size)
                        return true;
                return false;
        }
@@ -67,7 +78,9 @@ public:
 private:
        enum radeon_family family;
        enum ac_target_machine_options tm_options;
+       unsigned wave_size;
        struct ac_compiler_passes *passes;
+       struct ac_compiler_passes *passes_wave32;
 };
 
 /* we have to store a linked list per thread due to the possiblity of multiple gpus being required */
@@ -99,17 +112,18 @@ bool radv_compile_to_elf(struct ac_llvm_compiler *info,
 bool radv_init_llvm_compiler(struct ac_llvm_compiler *info,
                             bool thread_compiler,
                             enum radeon_family family,
-                            enum ac_target_machine_options tm_options)
+                            enum ac_target_machine_options tm_options,
+                            unsigned wave_size)
 {
        if (thread_compiler) {
                for (auto &I : radv_llvm_per_thread_list) {
-                       if (I.is_same(family, tm_options)) {
+                       if (I.is_same(family, tm_options, wave_size)) {
                                *info = I.llvm_info;
                                return true;
                        }
                }
 
-               radv_llvm_per_thread_list.emplace_back(family, tm_options);
+               radv_llvm_per_thread_list.emplace_back(family, tm_options, wave_size);
                radv_llvm_per_thread_info &tinfo = radv_llvm_per_thread_list.back();
 
                if (!tinfo.init()) {

diff --git a/src/amd/vulkan/radv_shader.c b/src/amd/vulkan/radv_shader.c
index 97fa80b348c19f6582d558e26f9381650f605c09..d0f6895f148ee73fd9cb1f5262b4f60a6a3b1208 100644 (file)
--- a/src/amd/vulkan/radv_shader.c
+++ b/src/amd/vulkan/radv_shader.c
@@ -1159,7 +1159,8 @@ shader_variant_compile(struct radv_device *device,
        radv_init_llvm_once();
        radv_init_llvm_compiler(&ac_llvm,
                                thread_compiler,
-                               chip_family, tm_options);
+                               chip_family, tm_options,
+                               radv_get_shader_wave_size(device->physical_device, stage));
        if (gs_copy_shader) {
                assert(shader_count == 1);
                radv_compile_gs_copy_shader(&ac_llvm, *shaders, &binary,

diff --git a/src/amd/vulkan/radv_shader_helper.h b/src/amd/vulkan/radv_shader_helper.h
index d9dace0b495588ee20c46c943e27a18bd2871d2d..c64d2df676ba36a067a160751a368e6e0ac2b479 100644 (file)
--- a/src/amd/vulkan/radv_shader_helper.h
+++ b/src/amd/vulkan/radv_shader_helper.h
@@ -29,7 +29,8 @@ extern "C" {
 bool radv_init_llvm_compiler(struct ac_llvm_compiler *info,
                             bool thread_compiler,
                             enum radeon_family family,
-                            enum ac_target_machine_options tm_options);
+                            enum ac_target_machine_options tm_options,
+                            unsigned wave_size);
 void radv_destroy_llvm_compiler(struct ac_llvm_compiler *info,
                                bool thread_compiler);