From aa8587d1fcfba6b54a826d2590ddf477261b6800 Mon Sep 17 00:00:00 2001
From: Roman Lebedev <lebedev.ri@gmail.com>
Date: Fri, 15 Jun 2018 09:56:31 +0000
Subject: [PATCH] [AMDGPU] Recognize  x &  (-1 >> (32 - y))  pattern.

Summary:
D47980 will canonicalize the `x << (32 - y) >> (32 - y)`,
which is the pattern the AMDGPU expects to `x &  (-1 >> (32 - y))`,
which is not recognized by AMDGPU.

Thus, it needs to be recognized, too.

Reviewers: nhaehnle, bogner, tstellar, arsenm

Reviewed By: arsenm

Subscribers: arsenm, kzhuravl, wdng, yaxunl, dstuttard, tpr, t-tye, llvm-commits

Tags: #amdgpu

Differential Revision: https://reviews.llvm.org/D48007

llvm-svn: 334815
---
 llvm/lib/Target/AMDGPU/AMDGPUInstructions.td |  7 ++++
 llvm/test/CodeGen/AMDGPU/extract-lowbits.ll  | 40 +++++---------------
 2 files changed, 17 insertions(+), 30 deletions(-)

diff --git a/llvm/lib/Target/AMDGPU/AMDGPUInstructions.td b/llvm/lib/Target/AMDGPU/AMDGPUInstructions.td
index 4d7da21a591c..22a7a9c44a3c 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUInstructions.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPUInstructions.td
@@ -682,6 +682,13 @@ multiclass BFEPattern <Instruction UBFE, Instruction SBFE, Instruction MOV> {
     (UBFE $src, $rshift, (MOV (i32 (IMMPopCount $mask))))
   >;
 
+  // x & (-1 >> (bitwidth - y))
+  def : AMDGPUPat <
+    (and i32:$src, (srl_oneuse -1, (sub 32, i32:$width))),
+    (UBFE $src, (i32 0), $width)
+  >;
+
+  // x << (bitwidth - y) >> (bitwidth - y)
   def : AMDGPUPat <
     (srl (shl_oneuse i32:$src, (sub 32, i32:$width)), (sub 32, i32:$width)),
     (UBFE $src, (i32 0), $width)
diff --git a/llvm/test/CodeGen/AMDGPU/extract-lowbits.ll b/llvm/test/CodeGen/AMDGPU/extract-lowbits.ll
index 563756271f36..150b064569a5 100644
--- a/llvm/test/CodeGen/AMDGPU/extract-lowbits.ll
+++ b/llvm/test/CodeGen/AMDGPU/extract-lowbits.ll
@@ -153,21 +153,11 @@ define i32 @bzhi32_b4_commutative(i32 %val, i32 %numlowbits) nounwind {
 ; ---------------------------------------------------------------------------- ;
 
 define i32 @bzhi32_c0(i32 %val, i32 %numlowbits) nounwind {
-; SI-LABEL: bzhi32_c0:
-; SI:       ; %bb.0:
-; SI-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; SI-NEXT:    v_sub_i32_e32 v1, vcc, 32, v1
-; SI-NEXT:    v_lshr_b32_e32 v1, -1, v1
-; SI-NEXT:    v_and_b32_e32 v0, v1, v0
-; SI-NEXT:    s_setpc_b64 s[30:31]
-;
-; VI-LABEL: bzhi32_c0:
-; VI:       ; %bb.0:
-; VI-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; VI-NEXT:    v_sub_u32_e32 v1, vcc, 32, v1
-; VI-NEXT:    v_lshrrev_b32_e64 v1, v1, -1
-; VI-NEXT:    v_and_b32_e32 v0, v1, v0
-; VI-NEXT:    s_setpc_b64 s[30:31]
+; GCN-LABEL: bzhi32_c0:
+; GCN:       ; %bb.0:
+; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN-NEXT:    v_bfe_u32 v0, v0, 0, v1
+; GCN-NEXT:    s_setpc_b64 s[30:31]
   %numhighbits = sub i32 32, %numlowbits
   %mask = lshr i32 -1, %numhighbits
   %masked = and i32 %mask, %val
@@ -200,21 +190,11 @@ define i32 @bzhi32_c1_indexzext(i32 %val, i8 %numlowbits) nounwind {
 }
 
 define i32 @bzhi32_c4_commutative(i32 %val, i32 %numlowbits) nounwind {
-; SI-LABEL: bzhi32_c4_commutative:
-; SI:       ; %bb.0:
-; SI-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; SI-NEXT:    v_sub_i32_e32 v1, vcc, 32, v1
-; SI-NEXT:    v_lshr_b32_e32 v1, -1, v1
-; SI-NEXT:    v_and_b32_e32 v0, v0, v1
-; SI-NEXT:    s_setpc_b64 s[30:31]
-;
-; VI-LABEL: bzhi32_c4_commutative:
-; VI:       ; %bb.0:
-; VI-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; VI-NEXT:    v_sub_u32_e32 v1, vcc, 32, v1
-; VI-NEXT:    v_lshrrev_b32_e64 v1, v1, -1
-; VI-NEXT:    v_and_b32_e32 v0, v0, v1
-; VI-NEXT:    s_setpc_b64 s[30:31]
+; GCN-LABEL: bzhi32_c4_commutative:
+; GCN:       ; %bb.0:
+; GCN-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN-NEXT:    v_bfe_u32 v0, v0, 0, v1
+; GCN-NEXT:    s_setpc_b64 s[30:31]
   %numhighbits = sub i32 32, %numlowbits
   %mask = lshr i32 -1, %numhighbits
   %masked = and i32 %val, %mask ; swapped order