[AMDGPU][True16] Fix the VGPR register class for 16-bit values. (llvm…

…#76170)
ROCm · Dec 26, 2023 · d51e06c · d51e06c
1 parent 7a48039
commit d51e06c
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 6 deletions.
diff --git a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
@@ -2661,7 +2661,7 @@ SIRegisterInfo::getVGPRClassForBitWidth(unsigned BitWidth) const {
   if (BitWidth == 1)
     return &AMDGPU::VReg_1RegClass;
   if (BitWidth == 16)
-    return &AMDGPU::VGPR_LO16RegClass;
+    return &AMDGPU::VGPR_16RegClass;
   if (BitWidth == 32)
     return &AMDGPU::VGPR_32RegClass;
   return ST.needsAlignedVGPRs() ? getAlignedVGPRClassForBitWidth(BitWidth)

diff --git a/llvm/test/CodeGen/AMDGPU/fadd.f16.ll b/llvm/test/CodeGen/AMDGPU/fadd.f16.ll
@@ -100,7 +100,9 @@ define amdgpu_kernel void @fadd_f16(
 ; GFX11-GISEL-NEXT:    s_waitcnt vmcnt(0)
 ; GFX11-GISEL-NEXT:    buffer_load_u16 v1, off, s[0:3], 0 glc dlc
 ; GFX11-GISEL-NEXT:    s_waitcnt vmcnt(0)
-; GFX11-GISEL-NEXT:    v_add_f16_e32 v0.l, v0.l, v1.l
+; GFX11-GISEL-NEXT:    v_mov_b16_e32 v0.h, v1.l
+; GFX11-GISEL-NEXT:    s_delay_alu instid0(VALU_DEP_1)
+; GFX11-GISEL-NEXT:    v_add_f16_e32 v0.l, v0.l, v0.h
 ; GFX11-GISEL-NEXT:    buffer_store_b16 v0, off, s[4:7], 0
 ; GFX11-GISEL-NEXT:    s_nop 0
 ; GFX11-GISEL-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
@@ -257,13 +259,14 @@ define amdgpu_kernel void @fadd_f16_imm_a(
 ; GFX11-GISEL-NEXT:    s_load_b128 s[0:3], s[0:1], 0x24
 ; GFX11-GISEL-NEXT:    s_mov_b32 s6, -1
 ; GFX11-GISEL-NEXT:    s_mov_b32 s7, 0x31016000
-; GFX11-GISEL-NEXT:    v_mov_b16_e32 v1.l, 0x3c00
 ; GFX11-GISEL-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX11-GISEL-NEXT:    s_mov_b64 s[4:5], s[2:3]
 ; GFX11-GISEL-NEXT:    s_mov_b64 s[2:3], s[6:7]
 ; GFX11-GISEL-NEXT:    buffer_load_u16 v0, off, s[4:7], 0
 ; GFX11-GISEL-NEXT:    s_waitcnt vmcnt(0)
-; GFX11-GISEL-NEXT:    v_add_f16_e32 v0.l, v0.l, v1.l
+; GFX11-GISEL-NEXT:    v_mov_b16_e32 v0.h, 0x3c00
+; GFX11-GISEL-NEXT:    s_delay_alu instid0(VALU_DEP_1)
+; GFX11-GISEL-NEXT:    v_add_f16_e32 v0.l, v0.l, v0.h
 ; GFX11-GISEL-NEXT:    buffer_store_b16 v0, off, s[0:3], 0
 ; GFX11-GISEL-NEXT:    s_nop 0
 ; GFX11-GISEL-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
@@ -400,13 +403,14 @@ define amdgpu_kernel void @fadd_f16_imm_b(
 ; GFX11-GISEL-NEXT:    s_load_b128 s[0:3], s[0:1], 0x24
 ; GFX11-GISEL-NEXT:    s_mov_b32 s6, -1
 ; GFX11-GISEL-NEXT:    s_mov_b32 s7, 0x31016000
-; GFX11-GISEL-NEXT:    v_mov_b16_e32 v1.l, 0x4000
 ; GFX11-GISEL-NEXT:    s_waitcnt lgkmcnt(0)
 ; GFX11-GISEL-NEXT:    s_mov_b64 s[4:5], s[2:3]
 ; GFX11-GISEL-NEXT:    s_mov_b64 s[2:3], s[6:7]
 ; GFX11-GISEL-NEXT:    buffer_load_u16 v0, off, s[4:7], 0
 ; GFX11-GISEL-NEXT:    s_waitcnt vmcnt(0)
-; GFX11-GISEL-NEXT:    v_add_f16_e32 v0.l, v0.l, v1.l
+; GFX11-GISEL-NEXT:    v_mov_b16_e32 v0.h, 0x4000
+; GFX11-GISEL-NEXT:    s_delay_alu instid0(VALU_DEP_1)
+; GFX11-GISEL-NEXT:    v_add_f16_e32 v0.l, v0.l, v0.h
 ; GFX11-GISEL-NEXT:    buffer_store_b16 v0, off, s[0:3], 0
 ; GFX11-GISEL-NEXT:    s_nop 0
 ; GFX11-GISEL-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)