[llvm] 7f62800 - [AMDGPU][True16][CodeGen] select vgpr16 for asm inline 16bit vreg (#140946)

via llvm-commits llvm-commits at lists.llvm.org
Wed May 21 14:47:31 PDT 2025


Author: Brox Chen
Date: 2025-05-21T17:47:28-04:00
New Revision: 7f62800fb89a7389fea386369496484876df0d44

URL: https://github.com/llvm/llvm-project/commit/7f62800fb89a7389fea386369496484876df0d44
DIFF: https://github.com/llvm/llvm-project/commit/7f62800fb89a7389fea386369496484876df0d44.diff

LOG: [AMDGPU][True16][CodeGen] select vgpr16 for asm inline 16bit vreg (#140946)

select vgpr16 for asm inline 16bit vreg in true16 mode

Added: 
    llvm/test/CodeGen/AMDGPU/inlineasm-16-fake16.ll
    llvm/test/CodeGen/AMDGPU/inlineasm-16-true16.ll

Modified: 
    llvm/lib/Target/AMDGPU/SIISelLowering.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
index ba7e11a853347..2d337fafe6dc2 100644
--- a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -16062,7 +16062,8 @@ SITargetLowering::getRegForInlineAsmConstraint(const TargetRegisterInfo *TRI_,
     case 'v':
       switch (BitWidth) {
       case 16:
-        RC = &AMDGPU::VGPR_32RegClass;
+        RC = Subtarget->useRealTrue16Insts() ? &AMDGPU::VGPR_16RegClass
+                                             : &AMDGPU::VGPR_32RegClass;
         break;
       default:
         RC = TRI->getVGPRClassForBitWidth(BitWidth);

diff  --git a/llvm/test/CodeGen/AMDGPU/inlineasm-16-fake16.ll b/llvm/test/CodeGen/AMDGPU/inlineasm-16-fake16.ll
new file mode 100644
index 0000000000000..d695a1fad604a
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/inlineasm-16-fake16.ll
@@ -0,0 +1,79 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=-real-true16 < %s | FileCheck -enable-var-scope -check-prefixes=GFX11 %s
+
+define amdgpu_kernel void @s_input_output_i16() #0 {
+; GFX11-LABEL: s_input_output_i16:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    ;;#ASMSTART
+; GFX11-NEXT:    s_mov_b32 s0, -1
+; GFX11-NEXT:    ;;#ASMEND
+; GFX11-NEXT:    s_and_b32 s0, s0, 0xffff
+; GFX11-NEXT:    ;;#ASMSTART
+; GFX11-NEXT:    ; use s0
+; GFX11-NEXT:    ;;#ASMEND
+; GFX11-NEXT:    s_endpgm
+  %v = tail call i16 asm sideeffect "s_mov_b32 $0, -1", "=s"()
+  tail call void asm sideeffect "; use $0", "s"(i16 %v) #0
+  ret void
+}
+
+define amdgpu_kernel void @s_input_output_f16() #0 {
+; GFX11-LABEL: s_input_output_f16:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    ;;#ASMSTART
+; GFX11-NEXT:    s_mov_b32 s0, -1
+; GFX11-NEXT:    ;;#ASMEND
+; GFX11-NEXT:    ;;#ASMSTART
+; GFX11-NEXT:    ; use s0
+; GFX11-NEXT:    ;;#ASMEND
+; GFX11-NEXT:    s_endpgm
+  %v = tail call half asm sideeffect "s_mov_b32 $0, -1", "=s"() #0
+  tail call void asm sideeffect "; use $0", "s"(half %v)
+  ret void
+}
+
+define amdgpu_kernel void @v_input_output_f16() #0 {
+; GFX11-LABEL: v_input_output_f16:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    ;;#ASMSTART
+; GFX11-NEXT:    v_mov_b32 v0, -1
+; GFX11-NEXT:    ;;#ASMEND
+; GFX11-NEXT:    ;;#ASMSTART
+; GFX11-NEXT:    ; use v0
+; GFX11-NEXT:    ;;#ASMEND
+; GFX11-NEXT:    s_endpgm
+  %v = tail call half asm sideeffect "v_mov_b32 $0, -1", "=v"() #0
+  tail call void asm sideeffect "; use $0", "v"(half %v)
+  ret void
+}
+
+define amdgpu_kernel void @v_input_output_i16() #0 {
+; GFX11-LABEL: v_input_output_i16:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    ;;#ASMSTART
+; GFX11-NEXT:    v_mov_b32 v0, -1
+; GFX11-NEXT:    ;;#ASMEND
+; GFX11-NEXT:    v_and_b32_e32 v0, 0xffff, v0
+; GFX11-NEXT:    ;;#ASMSTART
+; GFX11-NEXT:    ; use v0
+; GFX11-NEXT:    ;;#ASMEND
+; GFX11-NEXT:    s_endpgm
+  %v = tail call i16 asm sideeffect "v_mov_b32 $0, -1", "=v"() #0
+  tail call void asm sideeffect "; use $0", "v"(i16 %v)
+  ret void
+}
+
+define amdgpu_kernel void @i16_imm_input_phys_vgpr() {
+; GFX11-LABEL: i16_imm_input_phys_vgpr:
+; GFX11:       ; %bb.0: ; %entry
+; GFX11-NEXT:    v_mov_b32_e32 v0, 0xffff
+; GFX11-NEXT:    ;;#ASMSTART
+; GFX11-NEXT:    ; use v0
+; GFX11-NEXT:    ;;#ASMEND
+; GFX11-NEXT:    s_endpgm
+entry:
+  call void asm sideeffect "; use $0 ", "{v0}"(i16 65535)
+  ret void
+}
+
+attributes #0 = { nounwind }

diff  --git a/llvm/test/CodeGen/AMDGPU/inlineasm-16-true16.ll b/llvm/test/CodeGen/AMDGPU/inlineasm-16-true16.ll
new file mode 100644
index 0000000000000..5c5dc09f573ee
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/inlineasm-16-true16.ll
@@ -0,0 +1,91 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -mattr=+real-true16 < %s | FileCheck -enable-var-scope -check-prefixes=GFX11 %s
+
+define amdgpu_kernel void @s_input_output_i16() #0 {
+; GFX11-LABEL: s_input_output_i16:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    ;;#ASMSTART
+; GFX11-NEXT:    s_mov_b32 s0, -1
+; GFX11-NEXT:    ;;#ASMEND
+; GFX11-NEXT:    s_and_b32 s0, s0, 0xffff
+; GFX11-NEXT:    ;;#ASMSTART
+; GFX11-NEXT:    ; use s0
+; GFX11-NEXT:    ;;#ASMEND
+; GFX11-NEXT:    s_endpgm
+  %v = tail call i16 asm sideeffect "s_mov_b32 $0, -1", "=s"()
+  tail call void asm sideeffect "; use $0", "s"(i16 %v) #0
+  ret void
+}
+
+define amdgpu_kernel void @s_input_output_f16() #0 {
+; GFX11-LABEL: s_input_output_f16:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    ;;#ASMSTART
+; GFX11-NEXT:    s_mov_b32 s0, -1
+; GFX11-NEXT:    ;;#ASMEND
+; GFX11-NEXT:    ;;#ASMSTART
+; GFX11-NEXT:    ; use s0
+; GFX11-NEXT:    ;;#ASMEND
+; GFX11-NEXT:    s_endpgm
+  %v = tail call half asm sideeffect "s_mov_b32 $0, -1", "=s"() #0
+  tail call void asm sideeffect "; use $0", "s"(half %v)
+  ret void
+}
+
+define amdgpu_kernel void @v_input_output_f16() #0 {
+; GFX11-LABEL: v_input_output_f16:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    ;;#ASMSTART
+; GFX11-NEXT:    v_mov_b16 v0.l, -1
+; GFX11-NEXT:    ;;#ASMEND
+; GFX11-NEXT:    ;;#ASMSTART
+; GFX11-NEXT:    ; use v0.l
+; GFX11-NEXT:    ;;#ASMEND
+; GFX11-NEXT:    s_endpgm
+  %v = tail call half asm sideeffect "v_mov_b16 $0, -1", "=v"() #0
+  tail call void asm sideeffect "; use $0", "v"(half %v)
+  ret void
+}
+
+define amdgpu_kernel void @v_input_output_i16() #0 {
+; GFX11-LABEL: v_input_output_i16:
+; GFX11:       ; %bb.0:
+; GFX11-NEXT:    ;;#ASMSTART
+; GFX11-NEXT:    v_mov_b16 v0.l, -1
+; GFX11-NEXT:    ;;#ASMEND
+; GFX11-NEXT:    ;;#ASMSTART
+; GFX11-NEXT:    ; use v0.l
+; GFX11-NEXT:    ;;#ASMEND
+; GFX11-NEXT:    s_endpgm
+  %v = tail call i16 asm sideeffect "v_mov_b16 $0, -1", "=v"() #0
+  tail call void asm sideeffect "; use $0", "v"(i16 %v)
+  ret void
+}
+
+define amdgpu_kernel void @i16_imm_input_phys_vgpr_lo() {
+; GFX11-LABEL: i16_imm_input_phys_vgpr_lo:
+; GFX11:       ; %bb.0: ; %entry
+; GFX11-NEXT:    v_mov_b16_e32 v0.l, -1
+; GFX11-NEXT:    ;;#ASMSTART
+; GFX11-NEXT:    ; use v0.l
+; GFX11-NEXT:    ;;#ASMEND
+; GFX11-NEXT:    s_endpgm
+entry:
+  call void asm sideeffect "; use $0 ", "{v0.l}"(i16 65535)
+  ret void
+}
+
+define amdgpu_kernel void @i16_imm_input_phys_vgpr_hi() {
+; GFX11-LABEL: i16_imm_input_phys_vgpr_hi:
+; GFX11:       ; %bb.0: ; %entry
+; GFX11-NEXT:    v_mov_b16_e32 v0.h, -1
+; GFX11-NEXT:    ;;#ASMSTART
+; GFX11-NEXT:    ; use v0.h
+; GFX11-NEXT:    ;;#ASMEND
+; GFX11-NEXT:    s_endpgm
+entry:
+  call void asm sideeffect "; use $0 ", "{v0.h}"(i16 65535)
+  ret void
+}
+
+attributes #0 = { nounwind }


        


More information about the llvm-commits mailing list