[PATCH] D37758: [AMDGPU] For amdpal, widen interpolation mode workaround

[Tim Renouf via Phabricator via llvm-commits]

tpr updated this revision to Diff 117569.
tpr added a comment.

Really address review comment.


https://reviews.llvm.org/D37758

Files:
  lib/Target/AMDGPU/SIISelLowering.cpp
  test/CodeGen/AMDGPU/amdpal-psenable.ll


Index: test/CodeGen/AMDGPU/amdpal-psenable.ll
===================================================================
--- /dev/null
+++ test/CodeGen/AMDGPU/amdpal-psenable.ll
@@ -0,0 +1,21 @@
+; RUN: llc -mtriple=amdgcn--amdpal -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI %s
+; RUN: llc -mtriple=amdgcn--amdpal -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI %s
+; RUN: llc -mtriple=amdgcn--amdpal -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=GFX9 -enable-var-scope %s
+
+; This pixel shader does not use the result of its interpolation, so it would
+; end up with an interpolation mode set in PSAddr but not PSEnable. This test tests
+; the workaround that ensures that an interpolation mode is also set in PSEnable.
+; GCN-LABEL: {{^}}amdpal_psenable:
+; GCN: .amdgpu_pal_metadata{{.*}}0xa1b3,0x2,0xa1b4,0x2,
+define amdgpu_ps void @amdpal_psenable(i32 inreg, i32 inreg, i32 inreg, i32 inreg %m0, <2 x float> %pos) #6 {
+  %inst23 = extractelement <2 x float> %pos, i32 0
+  %inst24 = extractelement <2 x float> %pos, i32 1
+  %inst25 = tail call float @llvm.amdgcn.interp.p1(float %inst23, i32 0, i32 0, i32 %m0)
+  %inst26 = tail call float @llvm.amdgcn.interp.p2(float %inst25, float %inst24, i32 0, i32 0, i32 %m0)
+  ret void
+}
+
+declare float @llvm.amdgcn.interp.p1(float, i32, i32, i32) #2
+declare float @llvm.amdgcn.interp.p2(float, float, i32, i32, i32) #2
+
+attributes #6 = { nounwind "InitialPSInputAddr"="2" }
Index: lib/Target/AMDGPU/SIISelLowering.cpp
===================================================================
--- lib/Target/AMDGPU/SIISelLowering.cpp
+++ lib/Target/AMDGPU/SIISelLowering.cpp
@@ -1492,14 +1492,31 @@
     // - At least one of PERSP_* (0xF) or LINEAR_* (0x70) must be enabled.
     // - If POS_W_FLOAT (11) is enabled, at least one of PERSP_* must be
     //   enabled too.
-    if (CallConv == CallingConv::AMDGPU_PS &&
-        ((Info->getPSInputAddr() & 0x7F) == 0 ||
-         ((Info->getPSInputAddr() & 0xF) == 0 &&
-          Info->isPSInputAllocated(11)))) {
-      CCInfo.AllocateReg(AMDGPU::VGPR0);
-      CCInfo.AllocateReg(AMDGPU::VGPR1);
-      Info->markPSInputAllocated(0);
-      Info->markPSInputEnabled(0);
+    if (CallConv == CallingConv::AMDGPU_PS) {
+      if ((Info->getPSInputAddr() & 0x7F) == 0 ||
+           ((Info->getPSInputAddr() & 0xF) == 0 &&
+            Info->isPSInputAllocated(11))) {
+        CCInfo.AllocateReg(AMDGPU::VGPR0);
+        CCInfo.AllocateReg(AMDGPU::VGPR1);
+        Info->markPSInputAllocated(0);
+        Info->markPSInputEnabled(0);
+      }
+      if (Subtarget->isAmdPalOS()) {
+        // For isAmdPalOS, the user does not enable some bits after compilation
+        // based on run-time states; the register values being generated here are
+        // the final ones set in hardware. Therefore we need to apply the
+        // workaround to PSInputAddr and PSInputEnable together.  (The case where
+        // a bit is set in PSInputAddr but not PSInputEnable is where the
+        // frontend set up an input arg for a particular interpolation mode, but
+        // nothing uses that input arg. Really we should have an earlier pass
+        // that removes such an arg.)
+        unsigned PsInputBits = Info->getPSInputAddr() & Info->getPSInputEnable();
+        if ((PsInputBits & 0x7F) == 0 ||
+            ((PsInputBits & 0xF) == 0 &&
+             (PsInputBits >> 11 & 1)))
+          Info->markPSInputEnabled(
+              countTrailingZeros(Info->getPSInputAddr(), ZB_Undefined));
+      }
     }
 
     assert(!Info->hasDispatchPtr() &&


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D37758.117569.patch
Type: text/x-patch
Size: 3653 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20171003/8c051ae9/attachment.bin>