diff --git a/llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp b/llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp
@@ -517,6 +517,13 @@
   } else
     return false;
 
+  // The 24 bit mul intrinsics yields the low-order 32 bits. The result's bit
+  // width should not exceed 32 if `Size` > 32.
+  if (Size > 32 &&
+      numBitsUnsigned(LHS, Size) + numBitsUnsigned(RHS, Size) > 32) {
+    return false;
+  }
+
   SmallVector<Value *, 4> LHSVals;
   SmallVector<Value *, 4> RHSVals;
   SmallVector<Value *, 4> ResultVals;
diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu-codegenprepare-mul24.ll b/llvm/test/CodeGen/AMDGPU/amdgpu-codegenprepare-mul24.ll
--- a/llvm/test/CodeGen/AMDGPU/amdgpu-codegenprepare-mul24.ll
+++ b/llvm/test/CodeGen/AMDGPU/amdgpu-codegenprepare-mul24.ll
@@ -173,10 +173,7 @@
 ; SI-NEXT:    [[LHS24:%.*]] = ashr i64 [[SHL_LHS]], 40
 ; SI-NEXT:    [[LSHR_RHS:%.*]] = shl i64 [[RHS:%.*]], 40
 ; SI-NEXT:    [[RHS24:%.*]] = ashr i64 [[LHS]], 40
-; SI-NEXT:    [[TMP1:%.*]] = trunc i64 [[LHS24]] to i32
-; SI-NEXT:    [[TMP2:%.*]] = trunc i64 [[RHS24]] to i32
-; SI-NEXT:    [[TMP3:%.*]] = call i32 @llvm.amdgcn.mul.i24(i32 [[TMP1]], i32 [[TMP2]])
-; SI-NEXT:    [[MUL:%.*]] = sext i32 [[TMP3]] to i64
+; SI-NEXT:    [[MUL:%.*]] = mul i64 [[LHS24]], [[RHS24]]
 ; SI-NEXT:    ret i64 [[MUL]]
 ;
 ; VI-LABEL: @smul24_i64(
@@ -184,10 +181,7 @@
 ; VI-NEXT:    [[LHS24:%.*]] = ashr i64 [[SHL_LHS]], 40
 ; VI-NEXT:    [[LSHR_RHS:%.*]] = shl i64 [[RHS:%.*]], 40
 ; VI-NEXT:    [[RHS24:%.*]] = ashr i64 [[LHS]], 40
-; VI-NEXT:    [[TMP1:%.*]] = trunc i64 [[LHS24]] to i32
-; VI-NEXT:    [[TMP2:%.*]] = trunc i64 [[RHS24]] to i32
-; VI-NEXT:    [[TMP3:%.*]] = call i32 @llvm.amdgcn.mul.i24(i32 [[TMP1]], i32 [[TMP2]])
-; VI-NEXT:    [[MUL:%.*]] = sext i32 [[TMP3]] to i64
+; VI-NEXT:    [[MUL:%.*]] = mul i64 [[LHS24]], [[RHS24]]
 ; VI-NEXT:    ret i64 [[MUL]]
 ;
 ; DISABLED-LABEL: @smul24_i64(
@@ -210,19 +204,13 @@
 ; SI-LABEL: @umul24_i64(
 ; SI-NEXT:    [[LHS24:%.*]] = and i64 [[LHS:%.*]], 16777215
 ; SI-NEXT:    [[RHS24:%.*]] = and i64 [[RHS:%.*]], 16777215
-; SI-NEXT:    [[TMP1:%.*]] = trunc i64 [[LHS24]] to i32
-; SI-NEXT:    [[TMP2:%.*]] = trunc i64 [[RHS24]] to i32
-; SI-NEXT:    [[TMP3:%.*]] = call i32 @llvm.amdgcn.mul.u24(i32 [[TMP1]], i32 [[TMP2]])
-; SI-NEXT:    [[MUL:%.*]] = zext i32 [[TMP3]] to i64
+; SI-NEXT:    [[MUL:%.*]] = mul i64 [[LHS24]], [[RHS24]]
 ; SI-NEXT:    ret i64 [[MUL]]
 ;
 ; VI-LABEL: @umul24_i64(
 ; VI-NEXT:    [[LHS24:%.*]] = and i64 [[LHS:%.*]], 16777215
 ; VI-NEXT:    [[RHS24:%.*]] = and i64 [[RHS:%.*]], 16777215
-; VI-NEXT:    [[TMP1:%.*]] = trunc i64 [[LHS24]] to i32
-; VI-NEXT:    [[TMP2:%.*]] = trunc i64 [[RHS24]] to i32
-; VI-NEXT:    [[TMP3:%.*]] = call i32 @llvm.amdgcn.mul.u24(i32 [[TMP1]], i32 [[TMP2]])
-; VI-NEXT:    [[MUL:%.*]] = zext i32 [[TMP3]] to i64
+; VI-NEXT:    [[MUL:%.*]] = mul i64 [[LHS24]], [[RHS24]]
 ; VI-NEXT:    ret i64 [[MUL]]
 ;
 ; DISABLED-LABEL: @umul24_i64(
@@ -423,10 +411,7 @@
 ; SI-NEXT:    [[LHS24:%.*]] = ashr i33 [[SHL_LHS]], 9
 ; SI-NEXT:    [[LSHR_RHS:%.*]] = shl i33 [[RHS:%.*]], 9
 ; SI-NEXT:    [[RHS24:%.*]] = ashr i33 [[LHS]], 9
-; SI-NEXT:    [[TMP1:%.*]] = trunc i33 [[LHS24]] to i32
-; SI-NEXT:    [[TMP2:%.*]] = trunc i33 [[RHS24]] to i32
-; SI-NEXT:    [[TMP3:%.*]] = call i32 @llvm.amdgcn.mul.i24(i32 [[TMP1]], i32 [[TMP2]])
-; SI-NEXT:    [[MUL:%.*]] = sext i32 [[TMP3]] to i33
+; SI-NEXT:    [[MUL:%.*]] = mul i33 [[LHS24]], [[RHS24]]
 ; SI-NEXT:    ret i33 [[MUL]]
 ;
 ; VI-LABEL: @smul24_i33(
@@ -434,10 +419,7 @@
 ; VI-NEXT:    [[LHS24:%.*]] = ashr i33 [[SHL_LHS]], 9
 ; VI-NEXT:    [[LSHR_RHS:%.*]] = shl i33 [[RHS:%.*]], 9
 ; VI-NEXT:    [[RHS24:%.*]] = ashr i33 [[LHS]], 9
-; VI-NEXT:    [[TMP1:%.*]] = trunc i33 [[LHS24]] to i32
-; VI-NEXT:    [[TMP2:%.*]] = trunc i33 [[RHS24]] to i32
-; VI-NEXT:    [[TMP3:%.*]] = call i32 @llvm.amdgcn.mul.i24(i32 [[TMP1]], i32 [[TMP2]])
-; VI-NEXT:    [[MUL:%.*]] = sext i32 [[TMP3]] to i33
+; VI-NEXT:    [[MUL:%.*]] = mul i33 [[LHS24]], [[RHS24]]
 ; VI-NEXT:    ret i33 [[MUL]]
 ;
 ; DISABLED-LABEL: @smul24_i33(
@@ -460,19 +442,13 @@
 ; SI-LABEL: @umul24_i33(
 ; SI-NEXT:    [[LHS24:%.*]] = and i33 [[LHS:%.*]], 16777215
 ; SI-NEXT:    [[RHS24:%.*]] = and i33 [[RHS:%.*]], 16777215
-; SI-NEXT:    [[TMP1:%.*]] = trunc i33 [[LHS24]] to i32
-; SI-NEXT:    [[TMP2:%.*]] = trunc i33 [[RHS24]] to i32
-; SI-NEXT:    [[TMP3:%.*]] = call i32 @llvm.amdgcn.mul.u24(i32 [[TMP1]], i32 [[TMP2]])
-; SI-NEXT:    [[MUL:%.*]] = zext i32 [[TMP3]] to i33
+; SI-NEXT:    [[MUL:%.*]] = mul i33 [[LHS24]], [[RHS24]]
 ; SI-NEXT:    ret i33 [[MUL]]
 ;
 ; VI-LABEL: @umul24_i33(
 ; VI-NEXT:    [[LHS24:%.*]] = and i33 [[LHS:%.*]], 16777215
 ; VI-NEXT:    [[RHS24:%.*]] = and i33 [[RHS:%.*]], 16777215
-; VI-NEXT:    [[TMP1:%.*]] = trunc i33 [[LHS24]] to i32
-; VI-NEXT:    [[TMP2:%.*]] = trunc i33 [[RHS24]] to i32
-; VI-NEXT:    [[TMP3:%.*]] = call i32 @llvm.amdgcn.mul.u24(i32 [[TMP1]], i32 [[TMP2]])
-; VI-NEXT:    [[MUL:%.*]] = zext i32 [[TMP3]] to i33
+; VI-NEXT:    [[MUL:%.*]] = mul i33 [[LHS24]], [[RHS24]]
 ; VI-NEXT:    ret i33 [[MUL]]
 ;
 ; DISABLED-LABEL: @umul24_i33(
@@ -551,20 +527,7 @@
 ; SI-NEXT:    [[LHS24:%.*]] = ashr <2 x i33> [[SHL_LHS]], <i33 9, i33 9>
 ; SI-NEXT:    [[LSHR_RHS:%.*]] = shl <2 x i33> [[RHS:%.*]], <i33 9, i33 9>
 ; SI-NEXT:    [[RHS24:%.*]] = ashr <2 x i33> [[LHS]], <i33 9, i33 9>
-; SI-NEXT:    [[TMP1:%.*]] = extractelement <2 x i33> [[LHS24]], i64 0
-; SI-NEXT:    [[TMP2:%.*]] = extractelement <2 x i33> [[LHS24]], i64 1
-; SI-NEXT:    [[TMP3:%.*]] = extractelement <2 x i33> [[RHS24]], i64 0
-; SI-NEXT:    [[TMP4:%.*]] = extractelement <2 x i33> [[RHS24]], i64 1
-; SI-NEXT:    [[TMP5:%.*]] = trunc i33 [[TMP1]] to i32
-; SI-NEXT:    [[TMP6:%.*]] = trunc i33 [[TMP3]] to i32
-; SI-NEXT:    [[TMP7:%.*]] = call i32 @llvm.amdgcn.mul.i24(i32 [[TMP5]], i32 [[TMP6]])
-; SI-NEXT:    [[TMP8:%.*]] = sext i32 [[TMP7]] to i33
-; SI-NEXT:    [[TMP9:%.*]] = trunc i33 [[TMP2]] to i32
-; SI-NEXT:    [[TMP10:%.*]] = trunc i33 [[TMP4]] to i32
-; SI-NEXT:    [[TMP11:%.*]] = call i32 @llvm.amdgcn.mul.i24(i32 [[TMP9]], i32 [[TMP10]])
-; SI-NEXT:    [[TMP12:%.*]] = sext i32 [[TMP11]] to i33
-; SI-NEXT:    [[TMP13:%.*]] = insertelement <2 x i33> undef, i33 [[TMP8]], i64 0
-; SI-NEXT:    [[MUL:%.*]] = insertelement <2 x i33> [[TMP13]], i33 [[TMP12]], i64 1
+; SI-NEXT:    [[MUL:%.*]] = mul <2 x i33> [[LHS24]], [[RHS24]]
 ; SI-NEXT:    ret <2 x i33> [[MUL]]
 ;
 ; VI-LABEL: @smul24_v2i33(
@@ -572,20 +535,7 @@
 ; VI-NEXT:    [[LHS24:%.*]] = ashr <2 x i33> [[SHL_LHS]], <i33 9, i33 9>
 ; VI-NEXT:    [[LSHR_RHS:%.*]] = shl <2 x i33> [[RHS:%.*]], <i33 9, i33 9>
 ; VI-NEXT:    [[RHS24:%.*]] = ashr <2 x i33> [[LHS]], <i33 9, i33 9>
-; VI-NEXT:    [[TMP1:%.*]] = extractelement <2 x i33> [[LHS24]], i64 0
-; VI-NEXT:    [[TMP2:%.*]] = extractelement <2 x i33> [[LHS24]], i64 1
-; VI-NEXT:    [[TMP3:%.*]] = extractelement <2 x i33> [[RHS24]], i64 0
-; VI-NEXT:    [[TMP4:%.*]] = extractelement <2 x i33> [[RHS24]], i64 1
-; VI-NEXT:    [[TMP5:%.*]] = trunc i33 [[TMP1]] to i32
-; VI-NEXT:    [[TMP6:%.*]] = trunc i33 [[TMP3]] to i32
-; VI-NEXT:    [[TMP7:%.*]] = call i32 @llvm.amdgcn.mul.i24(i32 [[TMP5]], i32 [[TMP6]])
-; VI-NEXT:    [[TMP8:%.*]] = sext i32 [[TMP7]] to i33
-; VI-NEXT:    [[TMP9:%.*]] = trunc i33 [[TMP2]] to i32
-; VI-NEXT:    [[TMP10:%.*]] = trunc i33 [[TMP4]] to i32
-; VI-NEXT:    [[TMP11:%.*]] = call i32 @llvm.amdgcn.mul.i24(i32 [[TMP9]], i32 [[TMP10]])
-; VI-NEXT:    [[TMP12:%.*]] = sext i32 [[TMP11]] to i33
-; VI-NEXT:    [[TMP13:%.*]] = insertelement <2 x i33> undef, i33 [[TMP8]], i64 0
-; VI-NEXT:    [[MUL:%.*]] = insertelement <2 x i33> [[TMP13]], i33 [[TMP12]], i64 1
+; VI-NEXT:    [[MUL:%.*]] = mul <2 x i33> [[LHS24]], [[RHS24]]
 ; VI-NEXT:    ret <2 x i33> [[MUL]]
 ;
 ; DISABLED-LABEL: @smul24_v2i33(