[AMDGPU] update LDS block size for gfx1250

  Should be 2056 bytes (512 dwords) based on current spec.

Author: changpeng

llvm/docs/AMDGPUUsage.rst

@@ -5855,7 +5855,7 @@ The fields used by CP for code objects before V3 also match those specified in
                                                      GFX950
                                                        roundup(lds-size / (320 * 4))
                                                      GFX125*
-                                                       roundup(lds-size / (256 * 4))
+                                                       roundup(lds-size / (512 * 4))
 
      24      1 bit   ENABLE_EXCEPTION_IEEE_754_FP    Wavefront starts execution
                      _INVALID_OPERATION              with specified exceptions

llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp

@@ -1161,12 +1161,9 @@ void AMDGPUAsmPrinter::getSIProgramInfo(SIProgramInfo &ProgInfo,
   ProgInfo.DX10Clamp = Mode.DX10Clamp;
 
   unsigned LDSAlignShift;
-  if (STM.getFeatureBits().test(FeatureAddressableLocalMemorySize327680)) {
-    // LDS is allocated in 256 dword blocks.
-    LDSAlignShift = 10;
-  } else if (STM.getFeatureBits().test(
-                 FeatureAddressableLocalMemorySize163840)) {
-    // LDS is allocated in 320 dword blocks.
+  if (STM.getFeatureBits().test(FeatureAddressableLocalMemorySize327680) ||
+      STM.getFeatureBits().test(FeatureAddressableLocalMemorySize163840)) {
+    // LDS is allocated in 512 or 320 dword blocks.
     LDSAlignShift = 11;
   } else if (STM.getFeatureBits().test(
                  FeatureAddressableLocalMemorySize65536)) {

llvm/test/CodeGen/AMDGPU/extra-lds-size.ll

@@ -31,10 +31,10 @@
 ; GFX1200-MESA: .long 45100
 ; GFX1200-MESA-NEXT: .long 1024
 
-; GFX1250-PAL: '0x2c0b (SPI_SHADER_PGM_RSRC2_PS)': 0x200
+; GFX1250-PAL: '0x2c0b (SPI_SHADER_PGM_RSRC2_PS)': 0x100
 
 ; GFX1250-MESA: .long 45100
-; GFX1250-MESA-NEXT: .long 512
+; GFX1250-MESA-NEXT: .long 256
 
 @lds = internal addrspace(3) global [4096 x i8] poison
 

llvm/test/CodeGen/AMDGPU/lds-size-hsa-gfx1250.ll

@@ -41,7 +41,7 @@ define amdgpu_kernel void @test_lds_i32(i32 %val) {
 ; GCN-LABEL: test_lds_array_i8:
 ; GCN: .amdhsa_group_segment_fixed_size 327680
 ; GCN: ; LDSByteSize: 327680 bytes/workgroup
-; MESA: granulated_lds_size = 320
+; MESA: granulated_lds_size = 160
 define amdgpu_kernel void @test_lds_array_i8() {
   %gep = getelementptr inbounds [327679 x i8], ptr addrspace(3) @lds.array.i8, i32 0, i32 5
   %val = load i8, ptr addrspace(3) %gep
@@ -52,7 +52,7 @@ define amdgpu_kernel void @test_lds_array_i8() {
 ; GCN-LABEL: test_lds_array_i16:
 ; GCN: .amdhsa_group_segment_fixed_size 327680
 ; GCN: ; LDSByteSize: 327680 bytes/workgroup
-; MESA: granulated_lds_size = 320
+; MESA: granulated_lds_size = 160
 define amdgpu_kernel void @test_lds_array_i16() {
   %gep = getelementptr inbounds [163839 x i16], ptr addrspace(3) @lds.array.i16, i32 0, i32 10
   %val = load i16, ptr addrspace(3) %gep
@@ -63,7 +63,7 @@ define amdgpu_kernel void @test_lds_array_i16() {
 ; GCN-LABEL: test_lds_array_i32:
 ; GCN: .amdhsa_group_segment_fixed_size 327680
 ; GCN: ; LDSByteSize: 327680 bytes/workgroup
-; MESA: granulated_lds_size = 320
+; MESA: granulated_lds_size = 160
 define amdgpu_kernel void @test_lds_array_i32() {
   %gep = getelementptr inbounds [81919 x i32], ptr addrspace(3) @lds.array.i32, i32 0, i32 20
   %val = load i32, ptr addrspace(3) %gep

llvm/test/CodeGen/AMDGPU/pal-metadata-3.0.gfx1250.ll

@@ -126,7 +126,7 @@
 ; CHECK-NEXT:        .entry_point:    _amdgpu_hs
 ; CHECK-NEXT:        .entry_point_symbol:    hs_shader
 ; CHECK-NEXT:        .forward_progress: true
-; CHECK-NEXT:        .lds_size:       0x1000
+; CHECK-NEXT:        .lds_size:       0x800
 ; CHECK-NEXT:        .mem_ordered:    true
 ; CHECK-NEXT:        .scratch_en:     false
 ; CHECK-NEXT:        .scratch_memory_size: 0