[AMDGPU] Set GRANULATED_WAVEFRONT_SGPR_COUNT of compute_pgm_rsrc1 to 0 for gfx10+ (#154666)

According to `llvm-project/llvm/docs/AMDGPUUsage.rst::L5212` the
`GRANULATED_WAVEFRONT_SGPR_COUNT`, which is `compute_pgm_rsrc1[6:9]` has
to be 0 for gfx10+ arch

---------

Co-authored-by: Matt Arsenault <[email protected]>

Author: Shoreshen

llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp

@@ -1143,9 +1143,13 @@ void AMDGPUAsmPrinter::getSIProgramInfo(SIProgramInfo &ProgInfo,
     const MCExpr *SubGPR = MCBinaryExpr::createSub(DivGPR, OneConst, Ctx);
     return SubGPR;
   };
-
-  ProgInfo.SGPRBlocks = GetNumGPRBlocks(ProgInfo.NumSGPRsForWavesPerEU,
-                                        IsaInfo::getSGPREncodingGranule(&STM));
+  // GFX10+ will always allocate 128 SGPRs and this field must be 0
+  if (STM.getGeneration() >= AMDGPUSubtarget::GFX10) {
+    ProgInfo.SGPRBlocks = CreateExpr(0ul);
+  } else {
+    ProgInfo.SGPRBlocks = GetNumGPRBlocks(
+        ProgInfo.NumSGPRsForWavesPerEU, IsaInfo::getSGPREncodingGranule(&STM));
+  }
   ProgInfo.VGPRBlocks = GetNumGPRBlocks(ProgInfo.NumVGPRsForWavesPerEU,
                                         IsaInfo::getVGPREncodingGranule(&STM));
 

llvm/test/CodeGen/AMDGPU/GlobalISel/extractelement.ll

@@ -3202,7 +3202,7 @@ define amdgpu_kernel void @dyn_extract_v5f64_s_s(ptr addrspace(1) %out, i32 %sel
 ; GFX10-NEXT:     kernel_code_entry_byte_offset = 256
 ; GFX10-NEXT:     kernel_code_prefetch_byte_size = 0
 ; GFX10-NEXT:     granulated_workitem_vgpr_count = 0
-; GFX10-NEXT:     granulated_wavefront_sgpr_count = 1
+; GFX10-NEXT:     granulated_wavefront_sgpr_count = 0
 ; GFX10-NEXT:     priority = 0
 ; GFX10-NEXT:     float_mode = 240
 ; GFX10-NEXT:     priv = 0
@@ -4206,7 +4206,7 @@ define amdgpu_kernel void @dyn_extract_v4f32_s_s_s(ptr addrspace(1) %out, i32 %s
 ; GFX10-NEXT:     kernel_code_entry_byte_offset = 256
 ; GFX10-NEXT:     kernel_code_prefetch_byte_size = 0
 ; GFX10-NEXT:     granulated_workitem_vgpr_count = 0
-; GFX10-NEXT:     granulated_wavefront_sgpr_count = 1
+; GFX10-NEXT:     granulated_wavefront_sgpr_count = 0
 ; GFX10-NEXT:     priority = 0
 ; GFX10-NEXT:     float_mode = 240
 ; GFX10-NEXT:     priv = 0
@@ -4560,7 +4560,7 @@ define amdgpu_kernel void @dyn_extract_v4f64_s_s_s(ptr addrspace(1) %out, i32 %s
 ; GFX10-NEXT:     kernel_code_entry_byte_offset = 256
 ; GFX10-NEXT:     kernel_code_prefetch_byte_size = 0
 ; GFX10-NEXT:     granulated_workitem_vgpr_count = 0
-; GFX10-NEXT:     granulated_wavefront_sgpr_count = 1
+; GFX10-NEXT:     granulated_wavefront_sgpr_count = 0
 ; GFX10-NEXT:     priority = 0
 ; GFX10-NEXT:     float_mode = 240
 ; GFX10-NEXT:     priv = 0

llvm/test/CodeGen/AMDGPU/gfx10plus-wavefront-sgpr-count.ll

@@ -0,0 +1,11 @@
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1250 -filetype=obj < %s 2>&1 | llvm-objdump -d --section=.rodata - | FileCheck %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1200 -filetype=obj < %s 2>&1 | llvm-objdump -d --section=.rodata - | FileCheck %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 -filetype=obj < %s 2>&1 | llvm-objdump -d --section=.rodata - | FileCheck %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -filetype=obj < %s 2>&1 | llvm-objdump -d --section=.rodata - | FileCheck %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1030 -filetype=obj < %s 2>&1 | llvm-objdump -d --section=.rodata - | FileCheck %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1031 -filetype=obj < %s 2>&1 | llvm-objdump -d --section=.rodata - | FileCheck %s
+
+; CHECK-NOT: error
+define amdgpu_kernel void @test(i128 inreg) { 
+  ret void 
+}