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

Author: jayfoad

llvm/lib/Target/AMDGPU/AMDGPU.td

@@ -1501,7 +1501,8 @@ def FeatureISAVersion12 : FeatureSet<
    FeaturePseudoScalarTrans,
    FeatureHasRestrictedSOffset,
    FeatureVGPRSingleUseHintInsts,
-   FeatureScalarDwordx3Loads]>;
+   FeatureScalarDwordx3Loads,
+   FeatureDPPSrc1SGPR]>;
 
 //===----------------------------------------------------------------------===//
 

llvm/test/CodeGen/AMDGPU/dpp_combine_gfx11.mir

@@ -1,5 +1,6 @@
 # RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -run-pass=gcn-dpp-combine -verify-machineinstrs -o - %s | FileCheck %s -check-prefixes=GCN,GFX1100
 # RUN: llc -mtriple=amdgcn -mcpu=gfx1150 -run-pass=gcn-dpp-combine -verify-machineinstrs -o - %s | FileCheck %s -check-prefixes=GCN,GFX1150
+# RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -run-pass=gcn-dpp-combine -verify-machineinstrs -o - %s | FileCheck %s -check-prefixes=GCN,GFX1150
 
 ---
 

llvm/test/MC/AMDGPU/gfx1150_asm_features.s

@@ -17,3 +17,9 @@ v_add3_u32_e64_dpp v5, v1, s2, v0 dpp8:[7,6,5,4,3,2,1,0]
 
 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]
+
+v_add3_u32_e64_dpp v5, v1, s2, s3 dpp8:[7,6,5,4,3,2,1,0]
+// GFX1150: encoding: [0x05,0x00,0x55,0xd6,0xe9,0x04,0x0c,0x00,0x01,0x77,0x39,0x05]
+
+v_cmp_ne_i32_e64_dpp vcc_lo, v1, s2 dpp8:[7,6,5,4,3,2,1,0]
+// GFX1150: encoding: [0x6a,0x00,0x45,0xd4,0xe9,0x04,0x00,0x00,0x01,0x77,0x39,0x05]

llvm/test/MC/AMDGPU/gfx12_asm_features.s

@@ -1,5 +1,28 @@
 // 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]
+
+v_add3_u32_e64_dpp v5, v1, s2, s3 dpp8:[7,6,5,4,3,2,1,0]
+// GFX1150: encoding: [0x05,0x00,0x55,0xd6,0xe9,0x04,0x0c,0x00,0x01,0x77,0x39,0x05]
+
+v_cmp_ne_i32_e64_dpp vcc_lo, v1, s2 dpp8:[7,6,5,4,3,2,1,0]
+// GFX1150: encoding: [0x6a,0x00,0x45,0xd4,0xe9,0x04,0x00,0x00,0x01,0x77,0x39,0x05]
+
 //
 // Elements of CPol operand can be given in any order
 //

llvm/test/MC/Disassembler/AMDGPU/gfx1150_dasm_features.txt

@@ -11,3 +11,9 @@
 
 # GFX1150: 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
+
+# GFX1150: v_add3_u32_e64_dpp v5, v1, s2, s3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x55,0xd6,0xe9,0x04,0x0c,0x00,0x01,0x77,0x39,0x05]
+0x05,0x00,0x55,0xd6,0xe9,0x04,0x0c,0x00,0x01,0x77,0x39,0x05
+
+# GFX1150: v_cmp_ne_i32_e64_dpp vcc_lo, v1, s2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x6a,0x00,0x45,0xd4,0xe9,0x04,0x00,0x00,0x01,0x77,0x39,0x05]
+0x6a,0x00,0x45,0xd4,0xe9,0x04,0x00,0x00,0x01,0x77,0x39,0x05

llvm/test/MC/Disassembler/AMDGPU/gfx12_dasm_features.txt

@@ -0,0 +1,19 @@
+# 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
+
+# GFX1150: v_add3_u32_e64_dpp v5, v1, s2, s3 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x05,0x00,0x55,0xd6,0xe9,0x04,0x0c,0x00,0x01,0x77,0x39,0x05]
+0x05,0x00,0x55,0xd6,0xe9,0x04,0x0c,0x00,0x01,0x77,0x39,0x05
+
+# GFX1150: v_cmp_ne_i32_e64_dpp vcc_lo, v1, s2 dpp8:[7,6,5,4,3,2,1,0] ; encoding: [0x6a,0x00,0x45,0xd4,0xe9,0x04,0x00,0x00,0x01,0x77,0x39,0x05]
+0x6a,0x00,0x45,0xd4,0xe9,0x04,0x00,0x00,0x01,0x77,0x39,0x05