AMDGPU: Print all kernel descriptor directives (including the ones with default values)

[kzhuravl]

Summary

Change by @t-tye

[scott.linder]

LGTM, but adding Matt because I think he was the one to originally request eliding defaulted fields. From what Tony described I agree we can't do this generally because of options which depend on attributes, e.g. -mattr=+/-xnack changes the "default".

lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp

bool AMDGPUTargetAsmStreamer::EmitPALMetadata(
   OS << '\t' << PALMD::AssemblerDirective << PALMetadataString << '\n';
   return true;
 }
 
 void AMDGPUTargetAsmStreamer::EmitAmdhsaKernelDescriptor(
     const MCSubtargetInfo &STI, StringRef KernelName,
     const amdhsa::kernel_descriptor_t &KD, uint64_t NextVGPR, uint64_t NextSGPR,
     bool ReserveVCC, bool ReserveFlatScr, bool ReserveXNACK) {
-  amdhsa::kernel_descriptor_t DefaultKD = getDefaultAmdhsaKernelDescriptor();
-
   IsaVersion IVersion = getIsaVersion(STI.getCPU());
 
   OS << "\t.amdhsa_kernel " << KernelName << '\n';
 
-#define PRINT_IF_NOT_DEFAULT(STREAM, DIRECTIVE, KERNEL_DESC,                   \
-                             DEFAULT_KERNEL_DESC, MEMBER_NAME, FIELD_NAME)     \
-  if (AMDHSA_BITS_GET(KERNEL_DESC.MEMBER_NAME, FIELD_NAME) !=                  \
-      AMDHSA_BITS_GET(DEFAULT_KERNEL_DESC.MEMBER_NAME, FIELD_NAME))            \
-    STREAM << "\t\t" << DIRECTIVE << " "                                       \
-           << AMDHSA_BITS_GET(KERNEL_DESC.MEMBER_NAME, FIELD_NAME) << '\n';
+#define PRINT_FIELD(STREAM, DIRECTIVE, KERNEL_DESC, MEMBER_NAME, FIELD_NAME)   \
+  STREAM << "\t\t" << DIRECTIVE << " "                                         \
 
-  if (KD.group_segment_fixed_size != DefaultKD.group_segment_fixed_size)
-    OS << "\t\t.amdhsa_group_segment_fixed_size " << KD.group_segment_fixed_size
-       << '\n';
-  if (KD.private_segment_fixed_size != DefaultKD.private_segment_fixed_size)
-    OS << "\t\t.amdhsa_private_segment_fixed_size "
-       << KD.private_segment_fixed_size << '\n';
 
-  PRINT_IF_NOT_DEFAULT(
-      OS, ".amdhsa_user_sgpr_private_segment_buffer", KD, DefaultKD,
+  PRINT_FIELD(OS, ".amdhsa_user_sgpr_private_segment_buffer", KD,
               kernel_code_properties,
               amdhsa::KERNEL_CODE_PROPERTY_ENABLE_SGPR_PRIVATE_SEGMENT_BUFFER);
-  PRINT_IF_NOT_DEFAULT(OS, ".amdhsa_user_sgpr_dispatch_ptr", KD, DefaultKD,
-                       kernel_code_properties,
-                       amdhsa::KERNEL_CODE_PROPERTY_ENABLE_SGPR_DISPATCH_PTR);
-  PRINT_IF_NOT_DEFAULT(OS, ".amdhsa_user_sgpr_queue_ptr", KD, DefaultKD,
-                       kernel_code_properties,
-                       amdhsa::KERNEL_CODE_PROPERTY_ENABLE_SGPR_QUEUE_PTR);
-  PRINT_IF_NOT_DEFAULT(
-      OS, ".amdhsa_user_sgpr_kernarg_segment_ptr", KD, DefaultKD,
+  PRINT_FIELD(OS, ".amdhsa_user_sgpr_dispatch_ptr", KD,
+  PRINT_FIELD(OS, ".amdhsa_user_sgpr_queue_ptr", KD,
+  PRINT_FIELD(OS, ".amdhsa_user_sgpr_kernarg_segment_ptr", KD,
               kernel_code_properties,
               amdhsa::KERNEL_CODE_PROPERTY_ENABLE_SGPR_KERNARG_SEGMENT_PTR);
-  PRINT_IF_NOT_DEFAULT(OS, ".amdhsa_user_sgpr_dispatch_id", KD, DefaultKD,
-                       kernel_code_properties,
-                       amdhsa::KERNEL_CODE_PROPERTY_ENABLE_SGPR_DISPATCH_ID);
-  PRINT_IF_NOT_DEFAULT(
-      OS, ".amdhsa_user_sgpr_flat_scratch_init", KD, DefaultKD,
+  PRINT_FIELD(OS, ".amdhsa_user_sgpr_dispatch_id", KD,
+  PRINT_FIELD(OS, ".amdhsa_user_sgpr_flat_scratch_init", KD,
               kernel_code_properties,
               amdhsa::KERNEL_CODE_PROPERTY_ENABLE_SGPR_FLAT_SCRATCH_INIT);
-  PRINT_IF_NOT_DEFAULT(
-      OS, ".amdhsa_user_sgpr_private_segment_size", KD, DefaultKD,
+  PRINT_FIELD(OS, ".amdhsa_user_sgpr_private_segment_size", KD,
               kernel_code_properties,
               amdhsa::KERNEL_CODE_PROPERTY_ENABLE_SGPR_PRIVATE_SEGMENT_SIZE);
-  PRINT_IF_NOT_DEFAULT(
-      OS, ".amdhsa_system_sgpr_private_segment_wavefront_offset", KD, DefaultKD,
+  PRINT_FIELD(
+      OS, ".amdhsa_system_sgpr_private_segment_wavefront_offset", KD,
       compute_pgm_rsrc2,
       amdhsa::COMPUTE_PGM_RSRC2_ENABLE_SGPR_PRIVATE_SEGMENT_WAVEFRONT_OFFSET);
-  PRINT_IF_NOT_DEFAULT(OS, ".amdhsa_system_sgpr_workgroup_id_x", KD, DefaultKD,
-                       compute_pgm_rsrc2,
-                       amdhsa::COMPUTE_PGM_RSRC2_ENABLE_SGPR_WORKGROUP_ID_X);
-  PRINT_IF_NOT_DEFAULT(OS, ".amdhsa_system_sgpr_workgroup_id_y", KD, DefaultKD,
-                       compute_pgm_rsrc2,
-                       amdhsa::COMPUTE_PGM_RSRC2_ENABLE_SGPR_WORKGROUP_ID_Y);
-  PRINT_IF_NOT_DEFAULT(OS, ".amdhsa_system_sgpr_workgroup_id_z", KD, DefaultKD,
-                       compute_pgm_rsrc2,
-                       amdhsa::COMPUTE_PGM_RSRC2_ENABLE_SGPR_WORKGROUP_ID_Z);
-  PRINT_IF_NOT_DEFAULT(OS, ".amdhsa_system_sgpr_workgroup_info", KD, DefaultKD,
-                       compute_pgm_rsrc2,
-                       amdhsa::COMPUTE_PGM_RSRC2_ENABLE_SGPR_WORKGROUP_INFO);
-  PRINT_IF_NOT_DEFAULT(OS, ".amdhsa_system_vgpr_workitem_id", KD, DefaultKD,
-                       compute_pgm_rsrc2,
-                       amdhsa::COMPUTE_PGM_RSRC2_ENABLE_VGPR_WORKITEM_ID);
+  PRINT_FIELD(OS, ".amdhsa_system_sgpr_workgroup_id_x", KD,
+  PRINT_FIELD(OS, ".amdhsa_system_sgpr_workgroup_id_y", KD,
+  PRINT_FIELD(OS, ".amdhsa_system_sgpr_workgroup_id_z", KD,
+  PRINT_FIELD(OS, ".amdhsa_system_sgpr_workgroup_info", KD,
+  PRINT_FIELD(OS, ".amdhsa_system_vgpr_workitem_id", KD,
 
   // These directives are required.
   OS << "\t\t.amdhsa_next_free_vgpr " << NextVGPR << '\n';
   OS << "\t\t.amdhsa_next_free_sgpr " << NextSGPR << '\n';
 
   if (!ReserveVCC)
     OS << "\t\t.amdhsa_reserve_vcc " << ReserveVCC << '\n';
   if (IVersion.Major >= 7 && !ReserveFlatScr)
     OS << "\t\t.amdhsa_reserve_flat_scratch " << ReserveFlatScr << '\n';
   if (IVersion.Major >= 8 && ReserveXNACK != hasXNACK(STI))
     OS << "\t\t.amdhsa_reserve_xnack_mask " << ReserveXNACK << '\n';
 
-  PRINT_IF_NOT_DEFAULT(OS, ".amdhsa_float_round_mode_32", KD, DefaultKD,
-                       compute_pgm_rsrc1,
-                       amdhsa::COMPUTE_PGM_RSRC1_FLOAT_ROUND_MODE_32);
-  PRINT_IF_NOT_DEFAULT(OS, ".amdhsa_float_round_mode_16_64", KD, DefaultKD,
-                       compute_pgm_rsrc1,
-                       amdhsa::COMPUTE_PGM_RSRC1_FLOAT_ROUND_MODE_16_64);
-  PRINT_IF_NOT_DEFAULT(OS, ".amdhsa_float_denorm_mode_32", KD, DefaultKD,
-                       compute_pgm_rsrc1,
-                       amdhsa::COMPUTE_PGM_RSRC1_FLOAT_DENORM_MODE_32);
-  PRINT_IF_NOT_DEFAULT(OS, ".amdhsa_float_denorm_mode_16_64", KD, DefaultKD,
-                       compute_pgm_rsrc1,
-                       amdhsa::COMPUTE_PGM_RSRC1_FLOAT_DENORM_MODE_16_64);
-  PRINT_IF_NOT_DEFAULT(OS, ".amdhsa_dx10_clamp", KD, DefaultKD,
-                       compute_pgm_rsrc1,
-                       amdhsa::COMPUTE_PGM_RSRC1_ENABLE_DX10_CLAMP);
-  PRINT_IF_NOT_DEFAULT(OS, ".amdhsa_ieee_mode", KD, DefaultKD,
-                       compute_pgm_rsrc1,
-                       amdhsa::COMPUTE_PGM_RSRC1_ENABLE_IEEE_MODE);
+  PRINT_FIELD(OS, ".amdhsa_float_round_mode_32", KD,
+  PRINT_FIELD(OS, ".amdhsa_float_round_mode_16_64", KD,
+  PRINT_FIELD(OS, ".amdhsa_float_denorm_mode_32", KD,
+  PRINT_FIELD(OS, ".amdhsa_float_denorm_mode_16_64", KD,
+  PRINT_FIELD(OS, ".amdhsa_dx10_clamp", KD,
+  PRINT_FIELD(OS, ".amdhsa_ieee_mode", KD,
   if (IVersion.Major >= 9)
-    PRINT_IF_NOT_DEFAULT(OS, ".amdhsa_fp16_overflow", KD, DefaultKD,
-                         compute_pgm_rsrc1,
-                         amdhsa::COMPUTE_PGM_RSRC1_FP16_OVFL);
-  PRINT_IF_NOT_DEFAULT(
-      OS, ".amdhsa_exception_fp_ieee_invalid_op", KD, DefaultKD,
+    PRINT_FIELD(OS, ".amdhsa_fp16_overflow", KD,
+  PRINT_FIELD(
+      OS, ".amdhsa_exception_fp_ieee_invalid_op", KD,
       compute_pgm_rsrc2,
       amdhsa::COMPUTE_PGM_RSRC2_ENABLE_EXCEPTION_IEEE_754_FP_INVALID_OPERATION);
-  PRINT_IF_NOT_DEFAULT(
-      OS, ".amdhsa_exception_fp_denorm_src", KD, DefaultKD, compute_pgm_rsrc2,
+  PRINT_FIELD(OS, ".amdhsa_exception_fp_denorm_src", KD,
+              compute_pgm_rsrc2,
               amdhsa::COMPUTE_PGM_RSRC2_ENABLE_EXCEPTION_FP_DENORMAL_SOURCE);
-  PRINT_IF_NOT_DEFAULT(
-      OS, ".amdhsa_exception_fp_ieee_div_zero", KD, DefaultKD,
+  PRINT_FIELD(
+      OS, ".amdhsa_exception_fp_ieee_div_zero", KD,
       compute_pgm_rsrc2,
       amdhsa::COMPUTE_PGM_RSRC2_ENABLE_EXCEPTION_IEEE_754_FP_DIVISION_BY_ZERO);
-  PRINT_IF_NOT_DEFAULT(
-      OS, ".amdhsa_exception_fp_ieee_overflow", KD, DefaultKD,
+  PRINT_FIELD(OS, ".amdhsa_exception_fp_ieee_overflow", KD,
               compute_pgm_rsrc2,
               amdhsa::COMPUTE_PGM_RSRC2_ENABLE_EXCEPTION_IEEE_754_FP_OVERFLOW);
-  PRINT_IF_NOT_DEFAULT(
-      OS, ".amdhsa_exception_fp_ieee_underflow", KD, DefaultKD,
+  PRINT_FIELD(OS, ".amdhsa_exception_fp_ieee_underflow", KD,
               compute_pgm_rsrc2,
               amdhsa::COMPUTE_PGM_RSRC2_ENABLE_EXCEPTION_IEEE_754_FP_UNDERFLOW);
-  PRINT_IF_NOT_DEFAULT(
-      OS, ".amdhsa_exception_fp_ieee_inexact", KD, DefaultKD, compute_pgm_rsrc2,
+  PRINT_FIELD(OS, ".amdhsa_exception_fp_ieee_inexact", KD,
+              compute_pgm_rsrc2,
               amdhsa::COMPUTE_PGM_RSRC2_ENABLE_EXCEPTION_IEEE_754_FP_INEXACT);
-  PRINT_IF_NOT_DEFAULT(
-      OS, ".amdhsa_exception_int_div_zero", KD, DefaultKD, compute_pgm_rsrc2,
+  PRINT_FIELD(OS, ".amdhsa_exception_int_div_zero", KD,
+              compute_pgm_rsrc2,
               amdhsa::COMPUTE_PGM_RSRC2_ENABLE_EXCEPTION_INT_DIVIDE_BY_ZERO);
-#undef PRINT_IF_NOT_DEFAULT
+#undef PRINT_FIELD
 
   OS << "\t.end_amdhsa_kernel\n";
 }
 
 //===----------------------------------------------------------------------===//
 // AMDGPUTargetELFStreamer
 //===----------------------------------------------------------------------===//
 

test/MC/AMDGPU/hsa-v3.s

 // values are omitted.
 .p2align 6
 .amdhsa_kernel minimal
   .amdhsa_next_free_vgpr 0
   .amdhsa_next_free_sgpr 0
 .end_amdhsa_kernel
 
 // ASM: .amdhsa_kernel minimal
-// ASM-NEXT: .amdhsa_next_free_vgpr 0
+// ASM: .amdhsa_next_free_vgpr 0
 // ASM-NEXT: .amdhsa_next_free_sgpr 0
-// ASM-NEXT: .end_amdhsa_kernel
+// ASM: .end_amdhsa_kernel
 
 // Test that we can specify all available directives with non-default values.
 .p2align 6
 .amdhsa_kernel complete
   .amdhsa_group_segment_fixed_size 1
   .amdhsa_private_segment_fixed_size 1
   .amdhsa_user_sgpr_private_segment_buffer 1
   .amdhsa_user_sgpr_dispatch_ptr 1
.amdhsa_kernel special_sgpr
 
   .amdhsa_float_denorm_mode_16_64 0
   .amdhsa_dx10_clamp 0
   .amdhsa_ieee_mode 0
   .amdhsa_next_free_vgpr 0
 .end_amdhsa_kernel
 
 // ASM: .amdhsa_kernel special_sgpr
-// ASM-NEXT: .amdhsa_next_free_vgpr 0
+// ASM: .amdhsa_next_free_vgpr 0
 // ASM-NEXT: .amdhsa_next_free_sgpr 27
 // ASM-NEXT: .amdhsa_reserve_vcc 0
 // ASM-NEXT: .amdhsa_reserve_xnack_mask 0
-// ASM-NEXT: .amdhsa_float_denorm_mode_16_64 0
+// ASM: .amdhsa_float_denorm_mode_16_64 0
 // ASM-NEXT: .amdhsa_dx10_clamp 0
 // ASM-NEXT: .amdhsa_ieee_mode 0
-// ASM-NEXT: .end_amdhsa_kernel
+// ASM: .end_amdhsa_kernel
 
 .section .foo
 
 .byte .amdgcn.gfx_generation_number
 // ASM: .byte 9
 
 .byte .amdgcn.next_free_vgpr
 // ASM: .byte 0