[llvm] [AMDGPU] Src1 of VOP3 DPP instructions can be SGPR on GFX12 (PR #77929)

[via llvm-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-mc

Author: Jay Foad (jayfoad)

<details>
<summary>Changes</summary>



---
Full diff: https://github.com/llvm/llvm-project/pull/77929.diff


4 Files Affected:

- (modified) llvm/lib/Target/AMDGPU/AMDGPU.td (+2-1) 
- (modified) llvm/test/CodeGen/AMDGPU/dpp_combine_gfx11.mir (+1) 
- (modified) llvm/test/MC/AMDGPU/gfx12_asm_features.s (+17) 
- (added) llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_features.txt (+13) 


``````````diff
diff --git a/llvm/lib/Target/AMDGPU/AMDGPU.td b/llvm/lib/Target/AMDGPU/AMDGPU.td
index b27edb1e9e14bb..682ca6c57c973b 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPU.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPU.td
@@ -1502,7 +1502,8 @@ def FeatureISAVersion12 : FeatureSet<
    FeatureHasRestrictedSOffset,
    FeatureVGPRSingleUseHintInsts,
    FeatureMADIntraFwdBug,
-   FeatureScalarDwordx3Loads]>;
+   FeatureScalarDwordx3Loads,
+   FeatureDPPSrc1SGPR]>;
 
 //===----------------------------------------------------------------------===//
 
diff --git a/llvm/test/CodeGen/AMDGPU/dpp_combine_gfx11.mir b/llvm/test/CodeGen/AMDGPU/dpp_combine_gfx11.mir
index fe1345e29f133d..7d081a1491da6e 100644
--- a/llvm/test/CodeGen/AMDGPU/dpp_combine_gfx11.mir
+++ b/llvm/test/CodeGen/AMDGPU/dpp_combine_gfx11.mir
@@ -1,5 +1,6 @@
 # RUN: llc -march=amdgcn -mcpu=gfx1100 -run-pass=gcn-dpp-combine -verify-machineinstrs -o - %s | FileCheck %s -check-prefixes=GCN,GFX1100
 # RUN: llc -march=amdgcn -mcpu=gfx1150 -run-pass=gcn-dpp-combine -verify-machineinstrs -o - %s | FileCheck %s -check-prefixes=GCN,GFX1150
+# RUN: llc -march=amdgcn -mcpu=gfx1200 -run-pass=gcn-dpp-combine -verify-machineinstrs -o - %s | FileCheck %s -check-prefixes=GCN,GFX1150
 
 ---
 
diff --git a/llvm/test/MC/AMDGPU/gfx12_asm_features.s b/llvm/test/MC/AMDGPU/gfx12_asm_features.s
index 7e58bdb3b444e1..da4464c6494dbf 100644
--- a/llvm/test/MC/AMDGPU/gfx12_asm_features.s
+++ b/llvm/test/MC/AMDGPU/gfx12_asm_features.s
@@ -1,5 +1,22 @@
 // RUN: llvm-mc -arch=amdgcn -show-encoding -mcpu=gfx1200 %s | FileCheck --check-prefix=GFX12 %s
 
+//
+// Subtargets allow src1 of VOP3 DPP instructions to be SGPR or inlinable
+// constant.
+//
+
+v_add3_u32_e64_dpp v5, v1, s2, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf
+// GFX1150: encoding: [0x05,0x00,0x55,0xd6,0xfa,0x04,0x0c,0x04,0x01,0x1b,0x00,0xff]
+
+v_add3_u32_e64_dpp v5, v1, 42, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf
+// GFX1150: encoding: [0x05,0x00,0x55,0xd6,0xfa,0x54,0x0d,0x04,0x01,0x1b,0x00,0xff]
+
+v_add3_u32_e64_dpp v5, v1, s2, v0 dpp8:[7,6,5,4,3,2,1,0]
+// GFX1150: encoding: [0x05,0x00,0x55,0xd6,0xe9,0x04,0x00,0x04,0x01,0x77,0x39,0x05]
+
+v_add3_u32_e64_dpp v5, v1, 42, v0 dpp8:[7,6,5,4,3,2,1,0]
+// GFX1150: encoding: [0x05,0x00,0x55,0xd6,0xe9,0x54,0x01,0x04,0x01,0x77,0x39,0x05]
+
 //
 // Elements of CPol operand can be given in any order
 //
diff --git a/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_features.txt b/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_features.txt
new file mode 100644
index 00000000000000..2c64522422ad0d
--- /dev/null
+++ b/llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_features.txt
@@ -0,0 +1,13 @@
+# RUN: llvm-mc -arch=amdgcn -mcpu=gfx1200 -disassemble -show-encoding < %s | FileCheck -check-prefixes=GFX12 %s
+
+# GFX12: v_add3_u32_e64_dpp v5, v1, s2, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x55,0xd6,0xfa,0x04,0x0c,0x04,0x01,0x1b,0x00,0xff]
+0x05,0x00,0x55,0xd6,0xfa,0x04,0x0c,0x04,0x01,0x1b,0x00,0xff
+
+# GFX12: v_add3_u32_e64_dpp v5, v1, 42, v3 quad_perm:[3,2,1,0] row_mask:0xf bank_mask:0xf ; encoding: [0x05,0x00,0x55,0xd6,0xfa,0x54,0x0d,0x04,0x01,0x1b,0x00,0xff]
+0x05,0x00,0x55,0xd6,0xfa,0x54,0x0d,0x04,0x01,0x1b,0x00,0xff
+
+# GFX12: v_add3_u32_e64_dpp v5, v1, s2, v0 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x55,0xd6,0xe9,0x04,0x00,0x04,0x01,0x77,0x39,0x05]
+0x05,0x00,0x55,0xd6,0xe9,0x04,0x00,0x04,0x01,0x77,0x39,0x05
+
+# GFX12: v_add3_u32_e64_dpp v5, v1, 42, v0 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x55,0xd6,0xe9,0x54,0x01,0x04,0x01,0x77,0x39,0x05]
+0x05,0x00,0x55,0xd6,0xe9,0x54,0x01,0x04,0x01,0x77,0x39,0x05

``````````

</details>


https://github.com/llvm/llvm-project/pull/77929