[AMDGPU] Fix bug when calculating user_spgr_count for Code Object V3 assembler

Stop counting explicitly disabled user_spgr's in the user_sgpr_count field of the kernel descriptor.

Differential Revision: https://reviews.llvm.org/D66900

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@370250 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp b/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp
index bf90e36eec6e8c8186f091131ae2d1364e784d8b..77399e34af7edbcc3e8c0e44ec1e51c3ff172925 100644 (file)
--- a/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp
+++ b/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp
@@ -3617,37 +3617,44 @@ bool AMDGPUAsmParser::ParseDirectiveAMDHSAKernel() {
       PARSE_BITS_ENTRY(KD.kernel_code_properties,
                        KERNEL_CODE_PROPERTY_ENABLE_SGPR_PRIVATE_SEGMENT_BUFFER,
                        Val, ValRange);
-      UserSGPRCount += 4;
+      if (Val)
+        UserSGPRCount += 4;
     } else if (ID == ".amdhsa_user_sgpr_dispatch_ptr") {
       PARSE_BITS_ENTRY(KD.kernel_code_properties,
                        KERNEL_CODE_PROPERTY_ENABLE_SGPR_DISPATCH_PTR, Val,
                        ValRange);
-      UserSGPRCount += 2;
+      if (Val)
+        UserSGPRCount += 2;
     } else if (ID == ".amdhsa_user_sgpr_queue_ptr") {
       PARSE_BITS_ENTRY(KD.kernel_code_properties,
                        KERNEL_CODE_PROPERTY_ENABLE_SGPR_QUEUE_PTR, Val,
                        ValRange);
-      UserSGPRCount += 2;
+      if (Val)
+        UserSGPRCount += 2;
     } else if (ID == ".amdhsa_user_sgpr_kernarg_segment_ptr") {
       PARSE_BITS_ENTRY(KD.kernel_code_properties,
                        KERNEL_CODE_PROPERTY_ENABLE_SGPR_KERNARG_SEGMENT_PTR,
                        Val, ValRange);
-      UserSGPRCount += 2;
+      if (Val)
+        UserSGPRCount += 2;
     } else if (ID == ".amdhsa_user_sgpr_dispatch_id") {
       PARSE_BITS_ENTRY(KD.kernel_code_properties,
                        KERNEL_CODE_PROPERTY_ENABLE_SGPR_DISPATCH_ID, Val,
                        ValRange);
-      UserSGPRCount += 2;
+      if (Val)
+        UserSGPRCount += 2;
     } else if (ID == ".amdhsa_user_sgpr_flat_scratch_init") {
       PARSE_BITS_ENTRY(KD.kernel_code_properties,
                        KERNEL_CODE_PROPERTY_ENABLE_SGPR_FLAT_SCRATCH_INIT, Val,
                        ValRange);
-      UserSGPRCount += 2;
+      if (Val)
+        UserSGPRCount += 2;
     } else if (ID == ".amdhsa_user_sgpr_private_segment_size") {
       PARSE_BITS_ENTRY(KD.kernel_code_properties,
                        KERNEL_CODE_PROPERTY_ENABLE_SGPR_PRIVATE_SEGMENT_SIZE,
                        Val, ValRange);
-      UserSGPRCount += 1;
+      if (Val)
+        UserSGPRCount += 1;
     } else if (ID == ".amdhsa_wavefront_size32") {
       if (IVersion.Major < 10)
         return getParser().Error(IDRange.Start, "directive requires gfx10+",

diff --git a/test/MC/AMDGPU/hsa-v3.s b/test/MC/AMDGPU/hsa-v3.s
index 142774b61cd31eb5515eef66ae2c53a42b41209f..3c2ddecefcc132e4af620ccfa91355281127a025 100644 (file)
--- a/test/MC/AMDGPU/hsa-v3.s
+++ b/test/MC/AMDGPU/hsa-v3.s
@@ -8,16 +8,19 @@
 
 // READOBJ: Section Headers
 // READOBJ: .text   PROGBITS {{[0-9a-f]+}} {{[0-9a-f]+}} {{[0-9a-f]+}} {{[0-9]+}} AX {{[0-9]+}} {{[0-9]+}} 256
-// READOBJ: .rodata PROGBITS {{[0-9a-f]+}} {{[0-9a-f]+}}        0000c0 {{[0-9]+}}  A {{[0-9]+}} {{[0-9]+}} 64
+// READOBJ: .rodata PROGBITS {{[0-9a-f]+}} {{[0-9a-f]+}}        000100 {{[0-9]+}}  A {{[0-9]+}} {{[0-9]+}} 64
 
 // READOBJ: Relocation section '.rela.rodata' at offset
 // READOBJ: 0000000000000010 {{[0-9a-f]+}}00000005 R_AMDGPU_REL64 0000000000000000 .text + 10
 // READOBJ: 0000000000000050 {{[0-9a-f]+}}00000005 R_AMDGPU_REL64 0000000000000000 .text + 110
 // READOBJ: 0000000000000090 {{[0-9a-f]+}}00000005 R_AMDGPU_REL64 0000000000000000 .text + 210
+// READOBJ: 00000000000000d0 {{[0-9a-f]+}}00000005 R_AMDGPU_REL64 0000000000000000 .text + 310
 
 // READOBJ: Symbol table '.symtab' contains {{[0-9]+}} entries:
 // READOBJ: {{[0-9]+}}: 0000000000000100  0 FUNC    LOCAL  PROTECTED 2 complete
 // READOBJ: {{[0-9]+}}: 0000000000000040 64 OBJECT  LOCAL  DEFAULT   3 complete.kd
+// READOBJ: {{[0-9]+}}: 0000000000000300  0 FUNC    LOCAL  PROTECTED 2 disabled_user_sgpr
+// READOBJ: {{[0-9]+}}: 00000000000000c0 64 OBJECT  LOCAL  DEFAULT   3 disabled_user_sgpr.kd
 // READOBJ: {{[0-9]+}}: 0000000000000000  0 FUNC    LOCAL  PROTECTED 2 minimal
 // READOBJ: {{[0-9]+}}: 0000000000000000 64 OBJECT  LOCAL  DEFAULT   3 minimal.kd
 // READOBJ: {{[0-9]+}}: 0000000000000200  0 FUNC    LOCAL  PROTECTED 2 special_sgpr
@@ -40,6 +43,11 @@
 // OBJDUMP-NEXT: 0090 00000000 00000000 00000000 00000000
 // OBJDUMP-NEXT: 00a0 00000000 00000000 00000000 00000000
 // OBJDUMP-NEXT: 00b0 00010000 80000000 00000000 00000000
+// disabled_user_sgpr
+// OBJDUMP-NEXT: 00c0 00000000 00000000 00000000 00000000
+// OBJDUMP-NEXT: 00d0 00000000 00000000 00000000 00000000
+// OBJDUMP-NEXT: 00e0 00000000 00000000 00000000 00000000
+// OBJDUMP-NEXT: 00f0 0000ac00 80000000 00000000 00000000
 
 .text
 // ASM: .text
@@ -62,6 +70,11 @@ complete:
 special_sgpr:
   s_endpgm
 
+.p2align 8
+.type disabled_user_sgpr,@function
+disabled_user_sgpr:
+  s_endpgm
+
 .rodata
 // ASM: .rodata
 
@@ -182,6 +195,20 @@ special_sgpr:
 // ASM-NEXT: .amdhsa_ieee_mode 0
 // ASM: .end_amdhsa_kernel
 
+// Test that explicitly disabling user_sgpr's does not affect the user_sgpr
+// count, i.e. this should produce the same descriptor as minimal.
+.p2align 6
+.amdhsa_kernel disabled_user_sgpr
+  .amdhsa_user_sgpr_private_segment_buffer 0
+  .amdhsa_next_free_vgpr 0
+  .amdhsa_next_free_sgpr 0
+.end_amdhsa_kernel
+
+// ASM: .amdhsa_kernel disabled_user_sgpr
+// ASM: .amdhsa_next_free_vgpr 0
+// ASM-NEXT: .amdhsa_next_free_sgpr 0
+// ASM: .end_amdhsa_kernel
+
 .section .foo
 
 .byte .amdgcn.gfx_generation_number