AMDGPU: Update more tests to use modern buffer intrinsics

diff --git a/llvm/test/CodeGen/AMDGPU/atomic_optimizations_buffer.ll b/llvm/test/CodeGen/AMDGPU/atomic_optimizations_buffer.ll
index f358dc2..72c1211 100644 (file)
--- a/llvm/test/CodeGen/AMDGPU/atomic_optimizations_buffer.ll
+++ b/llvm/test/CodeGen/AMDGPU/atomic_optimizations_buffer.ll
@@ -5,8 +5,9 @@
 ; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=gfx1010 -mattr=+wavefrontsize32,-wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -amdgpu-dpp-combine=false -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GCN32,GFX8MORE,GFX8MORE32 %s
 
 declare i32 @llvm.amdgcn.workitem.id.x()
-declare i32 @llvm.amdgcn.buffer.atomic.add(i32, <4 x i32>, i32, i32, i1)
-declare i32 @llvm.amdgcn.buffer.atomic.sub(i32, <4 x i32>, i32, i32, i1)
+declare i32 @llvm.amdgcn.raw.buffer.atomic.add(i32, <4 x i32>, i32, i32, i32 immarg)
+declare i32 @llvm.amdgcn.struct.buffer.atomic.add(i32, <4 x i32>, i32, i32, i32, i32 immarg)
+declare i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32, <4 x i32>, i32, i32, i32 immarg)
 
 ; Show that what the atomic optimization pass will do for raw buffers.
 
@@ -22,7 +23,7 @@ declare i32 @llvm.amdgcn.buffer.atomic.sub(i32, <4 x i32>, i32, i32, i1)
 ; GCN: buffer_atomic_add v[[value]]
 define amdgpu_kernel void @add_i32_constant(i32 addrspace(1)* %out, <4 x i32> %inout) {
 entry:
-  %old = call i32 @llvm.amdgcn.buffer.atomic.add(i32 5, <4 x i32> %inout, i32 0, i32 0, i1 0)
+  %old = call i32 @llvm.amdgcn.raw.buffer.atomic.add(i32 5, <4 x i32> %inout, i32 0, i32 0, i32 0)
   store i32 %old, i32 addrspace(1)* %out
   ret void
 }
@@ -40,7 +41,7 @@ entry:
 ; GCN: buffer_atomic_add v[[value]]
 define amdgpu_kernel void @add_i32_uniform(i32 addrspace(1)* %out, <4 x i32> %inout, i32 %additive) {
 entry:
-  %old = call i32 @llvm.amdgcn.buffer.atomic.add(i32 %additive, <4 x i32> %inout, i32 0, i32 0, i1 0)
+  %old = call i32 @llvm.amdgcn.raw.buffer.atomic.add(i32 %additive, <4 x i32> %inout, i32 0, i32 0, i32 0)
   store i32 %old, i32 addrspace(1)* %out
   ret void
 }
@@ -64,7 +65,31 @@ entry:
 define amdgpu_kernel void @add_i32_varying_vdata(i32 addrspace(1)* %out, <4 x i32> %inout) {
 entry:
   %lane = call i32 @llvm.amdgcn.workitem.id.x()
-  %old = call i32 @llvm.amdgcn.buffer.atomic.add(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i1 0)
+  %old = call i32 @llvm.amdgcn.raw.buffer.atomic.add(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i32 0)
+  store i32 %old, i32 addrspace(1)* %out
+  ret void
+}
+
+; GCN-LABEL: struct_add_i32_varying_vdata:
+; GFX7LESS-NOT: v_mbcnt_lo_u32_b32
+; GFX7LESS-NOT: v_mbcnt_hi_u32_b32
+; GFX7LESS-NOT: s_bcnt1_i32_b64
+; GFX7LESS: buffer_atomic_add v{{[0-9]+}}
+; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v{{[0-9]+}} row_shr:1 row_mask:0xf bank_mask:0xf
+; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v{{[0-9]+}} row_shr:2 row_mask:0xf bank_mask:0xf
+; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v{{[0-9]+}} row_shr:4 row_mask:0xf bank_mask:0xf
+; GFX8MORE: v_mov_b32_dpp v{{[0-9]+}}, v{{[0-9]+}} row_shr:8 row_mask:0xf bank_mask:0xf
+; GFX89:    v_mov_b32_dpp v{{[0-9]+}}, v{{[0-9]+}} row_bcast:15 row_mask:0xa bank_mask:0xf
+; GFX89:    v_mov_b32_dpp v{{[0-9]+}}, v{{[0-9]+}} row_bcast:31 row_mask:0xc bank_mask:0xf
+; GFX8MORE32: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 31
+; GFX8MORE64: v_readlane_b32 s[[scalar_value:[0-9]+]], v{{[0-9]+}}, 63
+; GFX89: v_mov_b32_dpp v{{[0-9]+}}, v{{[0-9]+}} wave_shr:1 row_mask:0xf bank_mask:0xf
+; GFX8MORE: v_mov_b32{{(_e[0-9]+)?}} v[[value:[0-9]+]], s[[scalar_value]]
+; GFX8MORE: buffer_atomic_add v[[value]]
+define amdgpu_kernel void @struct_add_i32_varying_vdata(i32 addrspace(1)* %out, <4 x i32> %inout, i32 %vindex) {
+entry:
+  %lane = call i32 @llvm.amdgcn.workitem.id.x()
+  %old = call i32 @llvm.amdgcn.struct.buffer.atomic.add(i32 %lane, <4 x i32> %inout, i32 %vindex, i32 0, i32 0, i32 0)
   store i32 %old, i32 addrspace(1)* %out
   ret void
 }
@@ -77,7 +102,7 @@ entry:
 define amdgpu_kernel void @add_i32_varying_offset(i32 addrspace(1)* %out, <4 x i32> %inout) {
 entry:
   %lane = call i32 @llvm.amdgcn.workitem.id.x()
-  %old = call i32 @llvm.amdgcn.buffer.atomic.add(i32 1, <4 x i32> %inout, i32 %lane, i32 0, i1 0)
+  %old = call i32 @llvm.amdgcn.raw.buffer.atomic.add(i32 1, <4 x i32> %inout, i32 %lane, i32 0, i32 0)
   store i32 %old, i32 addrspace(1)* %out
   ret void
 }
@@ -94,7 +119,7 @@ entry:
 ; GCN: buffer_atomic_sub v[[value]]
 define amdgpu_kernel void @sub_i32_constant(i32 addrspace(1)* %out, <4 x i32> %inout) {
 entry:
-  %old = call i32 @llvm.amdgcn.buffer.atomic.sub(i32 5, <4 x i32> %inout, i32 0, i32 0, i1 0)
+  %old = call i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32 5, <4 x i32> %inout, i32 0, i32 0, i32 0)
   store i32 %old, i32 addrspace(1)* %out
   ret void
 }
@@ -112,7 +137,7 @@ entry:
 ; GCN: buffer_atomic_sub v[[value]]
 define amdgpu_kernel void @sub_i32_uniform(i32 addrspace(1)* %out, <4 x i32> %inout, i32 %subitive) {
 entry:
-  %old = call i32 @llvm.amdgcn.buffer.atomic.sub(i32 %subitive, <4 x i32> %inout, i32 0, i32 0, i1 0)
+  %old = call i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32 %subitive, <4 x i32> %inout, i32 0, i32 0, i32 0)
   store i32 %old, i32 addrspace(1)* %out
   ret void
 }
@@ -136,7 +161,7 @@ entry:
 define amdgpu_kernel void @sub_i32_varying_vdata(i32 addrspace(1)* %out, <4 x i32> %inout) {
 entry:
   %lane = call i32 @llvm.amdgcn.workitem.id.x()
-  %old = call i32 @llvm.amdgcn.buffer.atomic.sub(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i1 0)
+  %old = call i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32 %lane, <4 x i32> %inout, i32 0, i32 0, i32 0)
   store i32 %old, i32 addrspace(1)* %out
   ret void
 }
@@ -149,7 +174,7 @@ entry:
 define amdgpu_kernel void @sub_i32_varying_offset(i32 addrspace(1)* %out, <4 x i32> %inout) {
 entry:
   %lane = call i32 @llvm.amdgcn.workitem.id.x()
-  %old = call i32 @llvm.amdgcn.buffer.atomic.sub(i32 1, <4 x i32> %inout, i32 %lane, i32 0, i1 0)
+  %old = call i32 @llvm.amdgcn.raw.buffer.atomic.sub(i32 1, <4 x i32> %inout, i32 %lane, i32 0, i32 0)
   store i32 %old, i32 addrspace(1)* %out
   ret void
 }

diff --git a/llvm/test/CodeGen/AMDGPU/atomic_optimizations_pixelshader.ll b/llvm/test/CodeGen/AMDGPU/atomic_optimizations_pixelshader.ll
index 39c2d99..d41c140 100644 (file)
--- a/llvm/test/CodeGen/AMDGPU/atomic_optimizations_pixelshader.ll
+++ b/llvm/test/CodeGen/AMDGPU/atomic_optimizations_pixelshader.ll
@@ -5,8 +5,8 @@
 ; RUN: llc -mtriple=amdgcn-- -mcpu=gfx1010 -mattr=+wavefrontsize32,-wavefrontsize64 -mattr=-flat-for-global -amdgpu-atomic-optimizations=true -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GCN32,GFX8MORE,GFX8MORE32 %s
 
 declare i1 @llvm.amdgcn.wqm.vote(i1)
-declare i32 @llvm.amdgcn.buffer.atomic.add(i32, <4 x i32>, i32, i32, i1)
-declare void @llvm.amdgcn.buffer.store.f32(float, <4 x i32>, i32, i32, i1, i1)
+declare i32 @llvm.amdgcn.raw.buffer.atomic.add(i32, <4 x i32>, i32, i32, i32 immarg)
+declare void @llvm.amdgcn.raw.buffer.store.f32(float, <4 x i32>, i32, i32, i32 immarg)
 
 ; Show that what the atomic optimization pass will do for raw buffers.
 
@@ -25,13 +25,13 @@ declare void @llvm.amdgcn.buffer.store.f32(float, <4 x i32>, i32, i32, i1, i1)
 define amdgpu_ps void @add_i32_constant(<4 x i32> inreg %out, <4 x i32> inreg %inout) {
 entry:
   %cond1 = call i1 @llvm.amdgcn.wqm.vote(i1 true)
-  %old = call i32 @llvm.amdgcn.buffer.atomic.add(i32 5, <4 x i32> %inout, i32 0, i32 0, i1 0)
+  %old = call i32 @llvm.amdgcn.raw.buffer.atomic.add(i32 5, <4 x i32> %inout, i32 0, i32 0, i32 0)
   %cond2 = call i1 @llvm.amdgcn.wqm.vote(i1 true)
   %cond = and i1 %cond1, %cond2
   br i1 %cond, label %if, label %else
 if:
   %bitcast = bitcast i32 %old to float
-  call void @llvm.amdgcn.buffer.store.f32(float %bitcast, <4 x i32> %out, i32 0, i32 0, i1 0, i1 0)
+  call void @llvm.amdgcn.raw.buffer.store.f32(float %bitcast, <4 x i32> %out, i32 0, i32 0, i32 0)
   ret void
 else:
   ret void
@@ -55,13 +55,13 @@ else:
 define amdgpu_ps void @add_i32_varying(<4 x i32> inreg %out, <4 x i32> inreg %inout, i32 %val) {
 entry:
   %cond1 = call i1 @llvm.amdgcn.wqm.vote(i1 true)
-  %old = call i32 @llvm.amdgcn.buffer.atomic.add(i32 %val, <4 x i32> %inout, i32 0, i32 0, i1 0)
+  %old = call i32 @llvm.amdgcn.raw.buffer.atomic.add(i32 %val, <4 x i32> %inout, i32 0, i32 0, i32 0)
   %cond2 = call i1 @llvm.amdgcn.wqm.vote(i1 true)
   %cond = and i1 %cond1, %cond2
   br i1 %cond, label %if, label %else
 if:
   %bitcast = bitcast i32 %old to float
-  call void @llvm.amdgcn.buffer.store.f32(float %bitcast, <4 x i32> %out, i32 0, i32 0, i1 0, i1 0)
+  call void @llvm.amdgcn.raw.buffer.store.f32(float %bitcast, <4 x i32> %out, i32 0, i32 0, i32 0)
   ret void
 else:
   ret void

diff --git a/llvm/test/Transforms/StructurizeCFG/rebuild-ssa-infinite-loop.ll b/llvm/test/Transforms/StructurizeCFG/rebuild-ssa-infinite-loop.ll
index 9d3a843..ecfdabf 100644 (file)
--- a/llvm/test/Transforms/StructurizeCFG/rebuild-ssa-infinite-loop.ll
+++ b/llvm/test/Transforms/StructurizeCFG/rebuild-ssa-infinite-loop.ll
@@ -9,7 +9,7 @@ target triple = "amdgcn--"
 define amdgpu_vs void @wrapper(i32 inreg %arg, i32 %arg1) {
 main_body:
   %tmp = add i32 %arg1, %arg
-  %tmp2 = call <4 x float> @llvm.amdgcn.buffer.load.format.v4f32(<4 x i32> undef, i32 %tmp, i32 0, i1 false, i1 false)
+  %tmp2 = call <4 x float> @llvm.amdgcn.struct.buffer.load.format.v4f32(<4 x i32> undef, i32 %tmp, i32 0, i32 0, i32 0)
   %tmp3 = extractelement <4 x float> %tmp2, i32 1
   %tmp4 = fptosi float %tmp3 to i32
   %tmp5 = insertelement <2 x i32> undef, i32 %tmp4, i32 1
@@ -45,10 +45,7 @@ main.exit:                                        ; preds = %if28.i, %loop11.i
 ; Function Attrs: nounwind
 declare void @llvm.amdgcn.exp.f32(i32, i32, float, float, float, float, i1, i1) #0
 
-; Function Attrs: nounwind readnone
-declare <4 x float> @llvm.amdgcn.buffer.load.format.v4f32(<4 x i32>, i32, i32, i1, i1) #2
-
-; Function Attrs: nounwind readonly
+declare <4 x float> @llvm.amdgcn.struct.buffer.load.format.v4f32(<4 x i32>, i32, i32, i32, i32 immarg) #2
 declare <4 x float> @llvm.amdgcn.image.load.v4f32.v2i32.v8i32(<2 x i32>, <8 x i32>, i32, i1, i1, i1, i1) #2
 
 attributes #0 = { nounwind }