[llvm] 371fdba - [AMDGPU] Sign extend simm16 in setreg intrinsic (#77997)

[via llvm-commits]

Author: Stanislav Mekhanoshin
Date: 2024-01-16T09:17:18-08:00
New Revision: 371fdbaa57c3eaeea0f99591ae9675ecaa0cd1ad

URL: https://github.com/llvm/llvm-project/commit/371fdbaa57c3eaeea0f99591ae9675ecaa0cd1ad
DIFF: https://github.com/llvm/llvm-project/commit/371fdbaa57c3eaeea0f99591ae9675ecaa0cd1ad.diff

LOG: [AMDGPU] Sign extend simm16 in setreg intrinsic (#77997)

We currently force users to use a negative contant in the intrinsic
call. Changing it zext would break existing programs, so just sign
extend an argument.

Added: 
    

Modified: 
    llvm/lib/Target/AMDGPU/SIInstrInfo.td
    llvm/lib/Target/AMDGPU/SOPInstructions.td
    llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.setreg.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AMDGPU/SIInstrInfo.td b/llvm/lib/Target/AMDGPU/SIInstrInfo.td
index 7a65f8038c6983..e0e9aee3ebe002 100644
--- a/llvm/lib/Target/AMDGPU/SIInstrInfo.td
+++ b/llvm/lib/Target/AMDGPU/SIInstrInfo.td
@@ -767,12 +767,9 @@ class bitextract_imm<int bitnum> : SDNodeXForm<imm, [{
   return CurDAG->getTargetConstant(Bit, SDLoc(N), MVT::i1);
 }]>;
 
-def SIMM16bit : ImmLeaf <i32,
-  [{return isInt<16>(Imm);}]
->;
-
-def UIMM16bit : ImmLeaf <i32,
-  [{return isUInt<16>(Imm);}]
+def SIMM16bit : TImmLeaf <i32,
+  [{return isInt<16>(Imm) || isUInt<16>(Imm);}],
+  as_i16timm
 >;
 
 def i64imm_32bit : ImmLeaf<i64, [{

diff  --git a/llvm/lib/Target/AMDGPU/SOPInstructions.td b/llvm/lib/Target/AMDGPU/SOPInstructions.td
index 46fa3d57a21cb2..c0e0a368394386 100644
--- a/llvm/lib/Target/AMDGPU/SOPInstructions.td
+++ b/llvm/lib/Target/AMDGPU/SOPInstructions.td
@@ -1124,7 +1124,7 @@ class S_SETREG_B32_Pseudo <list<dag> pattern=[]> : SOPK_Pseudo <
   pattern>;
 
 def S_SETREG_B32 : S_SETREG_B32_Pseudo <
-  [(int_amdgcn_s_setreg (i32 timm:$simm16), i32:$sdst)]> {
+  [(int_amdgcn_s_setreg (i32 SIMM16bit:$simm16), i32:$sdst)]> {
   // Use custom inserter to optimize some cases to
   // S_DENORM_MODE/S_ROUND_MODE/S_SETREG_B32_mode.
   let usesCustomInserter = 1;

diff  --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.setreg.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.setreg.ll
index d2c14f2401fc35..99d80b5dd14b33 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.setreg.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.s.setreg.ll
@@ -1433,6 +1433,72 @@ define amdgpu_kernel void @test_setreg_set_4_bits_straddles_round_and_denorm() {
   ret void
 }
 
+define amdgpu_ps void @test_63489(i32 inreg %var.mode) {
+; GFX6-LABEL: test_63489:
+; GFX6:       ; %bb.0:
+; GFX6-NEXT:    s_setreg_b32 hwreg(HW_REG_MODE), s0 ; encoding: [0x01,0xf8,0x80,0xb9]
+; GFX6-NEXT:    ;;#ASMSTART
+; GFX6-NEXT:    ;;#ASMEND
+; GFX6-NEXT:    s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
+;
+; GFX789-LABEL: test_63489:
+; GFX789:       ; %bb.0:
+; GFX789-NEXT:    s_setreg_b32 hwreg(HW_REG_MODE), s0 ; encoding: [0x01,0xf8,0x00,0xb9]
+; GFX789-NEXT:    ;;#ASMSTART
+; GFX789-NEXT:    ;;#ASMEND
+; GFX789-NEXT:    s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
+;
+; GFX10-LABEL: test_63489:
+; GFX10:       ; %bb.0:
+; GFX10-NEXT:    s_setreg_b32 hwreg(HW_REG_MODE), s0 ; encoding: [0x01,0xf8,0x80,0xb9]
+; GFX10-NEXT:    ;;#ASMSTART
+; GFX10-NEXT:    ;;#ASMEND
+; GFX10-NEXT:    s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
+;
+; GFX11-LABEL: test_63489:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    s_setreg_b32 hwreg(HW_REG_MODE), s0 ; encoding: [0x01,0xf8,0x00,0xb9]
+; GFX11-NEXT:    ;;#ASMSTART
+; GFX11-NEXT:    ;;#ASMEND
+; GFX11-NEXT:    s_endpgm ; encoding: [0x00,0x00,0xb0,0xbf]
+  call void @llvm.amdgcn.s.setreg(i32 63489, i32 %var.mode)
+  call void asm sideeffect "", ""()
+  ret void
+}
+
+define amdgpu_ps void @test_minus_2047(i32 inreg %var.mode) {
+; GFX6-LABEL: test_minus_2047:
+; GFX6:       ; %bb.0:
+; GFX6-NEXT:    s_setreg_b32 hwreg(HW_REG_MODE), s0 ; encoding: [0x01,0xf8,0x80,0xb9]
+; GFX6-NEXT:    ;;#ASMSTART
+; GFX6-NEXT:    ;;#ASMEND
+; GFX6-NEXT:    s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
+;
+; GFX789-LABEL: test_minus_2047:
+; GFX789:       ; %bb.0:
+; GFX789-NEXT:    s_setreg_b32 hwreg(HW_REG_MODE), s0 ; encoding: [0x01,0xf8,0x00,0xb9]
+; GFX789-NEXT:    ;;#ASMSTART
+; GFX789-NEXT:    ;;#ASMEND
+; GFX789-NEXT:    s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
+;
+; GFX10-LABEL: test_minus_2047:
+; GFX10:       ; %bb.0:
+; GFX10-NEXT:    s_setreg_b32 hwreg(HW_REG_MODE), s0 ; encoding: [0x01,0xf8,0x80,0xb9]
+; GFX10-NEXT:    ;;#ASMSTART
+; GFX10-NEXT:    ;;#ASMEND
+; GFX10-NEXT:    s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
+;
+; GFX11-LABEL: test_minus_2047:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    s_setreg_b32 hwreg(HW_REG_MODE), s0 ; encoding: [0x01,0xf8,0x00,0xb9]
+; GFX11-NEXT:    ;;#ASMSTART
+; GFX11-NEXT:    ;;#ASMEND
+; GFX11-NEXT:    s_endpgm ; encoding: [0x00,0x00,0xb0,0xbf]
+  call void @llvm.amdgcn.s.setreg(i32 -2047, i32 %var.mode)
+  call void asm sideeffect "", ""()
+  ret void
+}
+
 ; FIXME: Broken for DAG
 ; define void @test_setreg_roundingmode_var_vgpr(i32 %var.mode) {
 ;   call void @llvm.amdgcn.s.setreg(i32 4097, i32 %var.mode)